The remarkable success of Large Language Models (LLMs) has extended to the multimodal domain, achieving outstanding performance in image understanding and generation. Recent efforts to develop unified Multimodal Large Language Models (MLLMs) that integrate these capabilities have shown promising results. However, existing approaches often involve complex designs in model architecture or training pipeline, increasing the difficulty of model training and scaling. In this paper, we propose SynerGen-VL, a simple yet powerful encoder-free MLLM capable of both image understanding and generation. To address challenges identified in existing encoder-free unified MLLMs, we introduce the token folding mechanism and the vision-expert-based progressive alignment pretraining strategy, which effectively support high-resolution image understanding while reducing training complexity. After being trained on large-scale mixed image-text data with a unified next-token prediction objective, SynerGen-VL achieves or surpasses the performance of existing encoder-free unified MLLMs with comparable or smaller parameter sizes, and narrows the gap with task-specific state-of-the-art models, highlighting a promising path toward future unified MLLMs. Our code and models are released at https://github.com/cpsxhao/SynerGen-VL.

This work introduces a new Transformer model called Cached Transformer, which uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiable memory cache of tokens. GRC attention enables attending to both past and current tokens, increasing the receptive field of attention and allowing for exploring long-range dependencies. By utilizing a recurrent gating unit to continuously update the cache, our model achieves significant advancements in \textbf{six} language and vision tasks, including language modeling, machine translation, ListOPs, image classification, object detection, and instance segmentation. Furthermore, our approach surpasses previous memory-based techniques in tasks such as language modeling and displays the ability to be applied to a broader range of situations.

In this work, we present Digital Life Project, a framework utilizing language as the universal medium to build autonomous 3D characters, who are capable of engaging in social interactions and expressing with articulated body motions, thereby simulating life in a digital environment. Our framework comprises two primary components: 1) SocioMind: a meticulously crafted digital brain that models personalities with systematic few-shot exemplars, incorporates a reflection process based on psychology principles, and emulates autonomy by initiating dialogue topics; 2) MoMat-MoGen: a text-driven motion synthesis paradigm for controlling the character's digital body. It integrates motion matching, a proven industry technique to ensure motion quality, with cutting-edge advancements in motion generation for diversity. Extensive experiments demonstrate that each module achieves state-of-the-art performance in its respective domain. Collectively, they enable virtual characters to initiate and sustain dialogues autonomously, while evolving their socio-psychological states. Concurrently, these characters can perform contextually relevant bodily movements. Additionally, an extension of DLP enables a virtual character to recognize and appropriately respond to human players' actions.

Many reinforcement learning environments (e.g., Minecraft) provide only sparse rewards that indicate task completion or failure with binary values. The challenge in exploration efficiency in such environments makes it difficult for reinforcement-learning-based agents to learn complex tasks. To address this, this paper introduces an advanced learning system, named Auto MC-Reward, that leverages Large Language Models (LLMs) to automatically design dense reward functions, thereby enhancing the learning efficiency. Auto MC-Reward consists of three important components: Reward Designer, Reward Critic, and Trajectory Analyzer. Given the environment information and task descriptions, the Reward Designer first design the reward function by coding an executable Python function with predefined observation inputs. Then, our Reward Critic will be responsible for verifying the code, checking whether the code is self-consistent and free of syntax and semantic errors. Further, the Trajectory Analyzer summarizes possible failure causes and provides refinement suggestions according to collected trajectories. In the next round, Reward Designer will further refine and iterate the dense reward function based on feedback. Experiments demonstrate a significant improvement in the success rate and learning efficiency of our agents in complex tasks in Minecraft, such as obtaining diamond with the efficient ability to avoid lava, and efficiently explore trees and animals that are sparse in the plains biome.

Image recognition and generation have long been developed independently of each other. With the recent trend towards general-purpose representation learning, the development of general representations for both recognition and generation tasks is also promoted. However, preliminary attempts mainly focus on generation performance, but are still inferior on recognition tasks. These methods are modeled in the vector-quantized (VQ) space, whereas leading recognition methods use pixels as inputs. Our key insights are twofold: *(1) pixels as inputs are crucial for recognition tasks; (2) VQ tokens as reconstruction targets are beneficial for generation tasks.* These observations motivate us to propose an **Alternating Denoising Diffusion Process (ADDP)** that integrates these two spaces within a single representation learning framework. In each denoising step, our method first decodes pixels from previous VQ tokens, then generates new VQ tokens from the decoded pixels. The diffusion process gradually masks out a portion of VQ tokens to construct the training samples. The learned representations can be used to generate diverse high-fidelity images and also demonstrate excellent transfer performance on recognition tasks. Extensive experiments show that our method achieves competitive performance on unconditional generation, ImageNet classification, COCO detection, and ADE20k segmentation. Importantly, our method represents *the first successful development* of general representations applicable to both generation and dense recognition tasks. Code shall be released.

Consistency Models (CMs) have made significant progress in accelerating the generation of diffusion models. However, their application to high-resolution, text-conditioned image generation in the latent space remains unsatisfactory. In this paper, we identify three key flaws in the current design of Latent Consistency Models~(LCMs). We investigate the reasons behind these limitations and propose Phased Consistency Models (PCMs), which generalize the design space and address the identified limitations. Our evaluations demonstrate that PCMs outperform LCMs across 1--16 step generation settings. While PCMs are specifically designed for multi-step refinement, they achieve comparable 1-step generation results to previously state-of-the-art specifically designed 1-step methods. Furthermore, we show the methodology of PCMs is versatile and applicable to video generation, enabling us to train the state-of-the-art few-step text-to-video generator. Our code is available at https://github.com/G-U-N/Phased-Consistency-Model.

Unsupervised domain adaptation (UDA) aims at adapting the model trained on a labeled source-domain dataset to an unlabeled target-domain dataset. The task of UDA on open-set person reidentification (re-ID) is even more challenging as the identities (classes) do not have overlap between the two domains. One major research direction was based on domain translation, which, however, has fallen out of favor in recent years due to inferior performance compared with pseudo-label-based methods. We argue that domain translation has great potential on exploiting valuable source-domain data but the existing methods did not provide proper regularization on the translation process. Specifically, previous methods only focus on maintaining the identities of the translated images while ignoring the intersample relations during translation. To tackle the challenges, we propose an end-to-end structured domain adaptation framework with an online relation-consistency regularization term. During training, the person feature encoder is optimized to model intersample relations on-the-fly for supervising relation-consistency domain translation, which in turn improves the encoder with informative translated images. The encoder can be further improved with pseudo labels, where the source-to-target translated images with ground-truth identities and target-domain images with pseudo identities are jointly used for training. In the experiments, our proposed framework is shown to achieve state-of-the-art performance on multiple UDA tasks of person re-ID. With the synthetic→real translated images from our structured domain-translation network, we achieved second place in the Visual Domain Adaptation Challenge (VisDA) in 2020.

To effectively exploit the potential of large-scale models, various pre-training strategies supported by massive data from different sources are proposed, including supervised pre-training, weakly-supervised pre-training, and self-supervised pre-training. It has been proved that combining multiple pre-training strategies and data from various modalities/sources can greatly boost the training of large-scale models. However, current works adopt a multi-stage pre-training system, where the complex pipeline may increase the uncertainty and instability of the pre-training. It is thus desirable that these strategies can be integrated in a single-stage manner. In this paper, we first propose a general multimodal mutual information formula as a unified optimization target and demonstrate that all mainstream approaches are special cases of our framework. Under this unified perspective, we propose an all-in-one single-stage pre-training approach, named Maximizing Multi-modal Mutual Information Pre-Training (M3I Pre-training). Our approach achieves better performance than previous pre-training methods on various vision benchmarks, including ImageNet classification, COCO object detection, LVIS long-tailed object detection, and ADE20k semantic segmentation. Notably, we successfully pre-train a billion-level parameter image backbone and achieve state-of-the-art performance on various benchmarks under public data setting. Code shall be released at https://github.com/OpenGVLab/M3I-Pre-Training.

Video restoration, which aims to restore clear frames from degraded videos, has numerous important applications. The key to video restoration depends on utilizing inter-frame information. However, existing deep learning methods often rely on complicated network architectures, such as optical flow estimation, deformable convo-lution, and cross-frame self-attention layers, resulting in high computational costs. In this study, we propose a sim-ple yet effective framework for video restoration. Our approach is based on grouped spatial-temporal shift, which is a lightweight and straightforward technique that can implicitly capture inter-frame correspondences for multi-frame aggregation. By introducing grouped spatial shift, we attain expansive effective receptive fields. Combined with basic 2D convolution, this simple framework can effectively aggregate inter-frame information. Extensive experiments demonstrate that our framework outperforms the previous state-of-the-art method, while using less than a quarter of its computational cost, on both video deblurring and video denoising tasks. These results indicate the potential for our approach to significantly reduce computational overhead while maintaining high-quality results. Code is avaliable at https://github.com/dasonglil/Shift-Net.

Despite the remarkable success of foundation models, their task-specific fine-tuning paradigm makes them inconsistent with the goal of general perception modeling. The key to eliminating this inconsistency is to use generalist models for general task modeling. However, existing attempts at generalist models are inadequate in both versatility and performance. In this paper, we propose Uni-Perceiver v2, which is the first generalist model capable of handling major large-scale vision and vision-language tasks with competitive performance. Specifically, images are encoded as general region proposals, while texts are encoded via a Transformer-based language model. The encoded representations are transformed by a task-agnostic decoder. Different tasks are formulated as a unified maximum likelihood estimation problem. We further propose an effective optimization technique named Task-Balanced Gradient Normalization to ensure stable multi-task learning with an unmixed sampling strategy, which is helpful for tasks requiring large batch-size training. After being jointly trained on various tasks, Uni-Perceiver v2 is capable of directly handling downstream tasks without any task-specific adaptation. Results show that Uni-Perceiver v2 outperforms all existing generalist models in both versatility and performance. Meanwhile, compared with the commonly-recognized strong baselines that require tasks-specific fine-tuning, Uni-Perceiver v2 achieves competitive performance on a broad range of vision and vision-language tasks.

Self-supervised learning (SSL) has delivered superior performance on a variety of downstream vision tasks. Two main-stream SSL frameworks have been proposed, i.e., Instance Discrimination (ID) and Masked Image Modeling (MIM). ID pulls together representations from different views of the same image, while avoiding feature collapse. It lacks spatial sensitivity, which requires modeling the local structure within each image. On the other hand, MIM reconstructs the original content given a masked image. It instead does not have good semantic alignment, which requires projecting semantically similar views into nearby representations. To address this dilemma, we observe that (1) semantic alignment can be achieved by matching different image views with strong augmentations; (2) spatial sensitivity can benefit from predicting dense representations with masked images. Driven by these analysis, we propose Siamese Image Modeling (SiameseIM), which predicts the dense representations of an augmented view, based on another masked view from the same image but with different augmentations. SiameseIM uses a Siamese network with two branches. The online branch encodes the first view, and predicts the second view's representation according to the relative positions between these two views. The target branch produces the target by encoding the second view. SiameseIM can surpass both ID and MIM on a wide range of downstream tasks, including ImageNet finetuning and linear probing, COCO and LVIS detection, and ADE20k semantic segmentation. The improvement is more significant in few-shot, long-tail and robustness-concerned scenarios. Code shall be released.

Compared to the great progress of large-scale vision transformers (ViTs) in recent years, large-scale models based on convolutional neural networks (CNNs) are still in an early state. This work presents a new large-scale CNN-based foundation model, termed InternImage, which can obtain the gain from increasing parameters and training data like ViTs. Different from the recent CNNs that focus on large dense kernels, InternImage takes deformable convolution as the core operator, so that our model not only has the large effective receptive field required for downstream tasks such as detection and segmentation, but also has the adaptive spatial aggregation conditioned by input and task information. As a result, the proposed InternImage reduces the strict inductive bias of traditional CNNs and makes it possible to learn stronger and more robust patterns with large-scale parameters from massive data like ViTs. The effectiveness of our model is proven on challenging benchmarks including ImageNet, COCO, andADE20K. It is worth mentioning that InternImage-H achieved a new record 65.4 mAP on COCO test-dev and 62.9 mIoU on ADE20K, outperforming current leading CNNs and ViTs.

Controllable image denoising aims to generate clean samples with human perceptual priors and balance sharpness and smoothness. In traditional filter-based denoising methods, this can be easily achieved by adjusting the filtering strength. However, for NN (Neural Network)-based models, adjusting the final denoising strength requires performing network inference each time, making it almost impossible for real-time user interaction. In this paper, we introduce Real-time Controllable Denoising (RCD), the first deep image and video denoising pipeline that provides a fully controllable user interface to edit arbitrary denoising levels in real-time with only one-time network inference. Unlike existing controllable denoising methods that require multiple denoisers and training stages, RCD replaces the last output layer (which usually outputs a single noise map) of an existing CNN-based model with a lightweight module that outputs multiple noise maps. We propose a novel Noise Decorrelation process to enforce the orthogonality of the noise feature maps, allowing arbitrary noise level control through noise map interpolation. This process is network-free and does not require network inference. Our experiments show that RCD can enable real-time editable image and video denoising for various existing heavy-weight models without sacrificing their original performance.

Diffusion Probabilistic Models (DPMs) have recently shown remarkable performance in image generation tasks, which are capable of generating highly realistic images. When adopting DPMs for image restoration tasks, the crucial aspect lies in how to integrate the conditional information to guide the DPMs to generate accurate and natural output, which has been largely overlooked in existing works. In this paper, we present a unified conditional framework based on diffusion models for image restoration. We leverage a lightweight UNet to predict initial guidance and the diffusion model to learn the residual of the guidance. By carefully designing the basic module and integration module for the diffusion model block, we integrate the guidance and other auxiliary conditional information into every block of the diffusion model to achieve spatially-adaptive generation conditioning. To handle high-resolution images, we propose a simple yet effective inter-step patch-splitting strategy to produce arbitrary-resolution images without grid artifacts. We evaluate our conditional framework on three challenging tasks: extreme low-light denoising, deblurring, and JPEG restoration, demonstrating its significant improvements in perceptual quality and the generalization to restoration tasks. The code will be released at https://zhangyi-3.github.io/project/UCDIR/.

Abstract 3D object detection is receiving increasing attention from both industry and academia thanks to its wide applications in various fields. In this paper, we propose Point-Voxel Region-based Convolution Neural Networks (PV-RCNNs) for 3D object detection on point clouds. First, we propose a novel 3D detector, PV-RCNN, which boosts the 3D detection performance by deeply integrating the feature learning of both point-based set abstraction and voxel-based sparse convolution through two novel steps, i.e. , the voxel-to-keypoint scene encoding and the keypoint-to-grid RoI feature abstraction. Second, we propose an advanced framework, PV-RCNN++, for more efficient and accurate 3D object detection. It consists of two major improvements: sectorized proposal-centric sampling for efficiently producing more representative keypoints, and VectorPool aggregation for better aggregating local point features with much less resource consumption. With these two strategies, our PV-RCNN++ is about $$3\times $$ 3 × faster than PV-RCNN, while also achieving better performance. The experiments demonstrate that our proposed PV-RCNN++ framework achieves state-of-the-art 3D detection performance on the large-scale and highly-competitive Waymo Open Dataset with 10 FPS inference speed on the detection range of $$150m \times 150m$$ 150 m × 150 m .

Both high-level and high-resolution feature representations are of great importance in various visual understanding tasks. To acquire high-resolution feature maps with high-level semantic information, one common strategy is to adopt dilated convolutions in the backbone networks to extract high-resolution feature maps, such as the dilatedFCN-based methods for semantic segmentation. However, due to many convolution operations are conducted on the high-resolution feature maps, such methods have large computational complexity and memory consumption. To balance the performance and efficiency, there also exist encoder-decoder structures that gradually recover the spatial information by combining multi-level feature maps from a feature encoder, such as the FPN architecture for object detection and the U-Net for semantic segmentation. Although being more efficient, the performances of existing encoder-decoder methods for semantic segmentation are far from comparable with the dilatedFCN-based methods. In this paper, we propose one novel holistically-guided decoder which is introduced to obtain the high-resolution semantic-rich feature maps via the multi-scale features from the encoder. The decoding is achieved via novel holistic codeword generation and codeword assembly operations, which take advantages of both the high-level and low-level features from the encoder features. With the proposed holistically-guided decoder, we implement the EfficientFCN architecture for semantic segmentation and HGD-FPN for object detection and instance segmentation. The EfficientFCN achieves comparable or even better performance than state-of-the-art methods with only 1/3 of their computational costs for semantic segmentation on PASCAL Context, PASCAL VOC, ADE20K datasets. Meanwhile, the proposed HGD-FPN achieves higher mean Average Precision (mAP) when integrated into several object detection frameworks with ResNet-50 encoding backbones.

Training a good supernet in one-shot NAS methods is difficult since the search space is usually considerably huge$(\mathrm{e}.\mathrm{g}.,\ 13^{21})$. In order to enhance the supernet's evaluation ability, one greedy strategy is to sample good paths, and let the supernet lean towards the good ones and ease its evaluation burden as a result. However, in practice the search can be still quite inefficient since the identification of good paths is not accurate enough and sampled paths still scatter around the whole search space. In this paper, we leverage an explicit path filter to capture the characteristics of paths and directly filter those weak ones, so that the search can be thus implemented on the shrunk space more greedily and efficiently. Concretely, based on the fact that good paths are much less than the weak ones in the space, we argue that the label of “weak paths” will be more confident and reliable than that of “good paths” in multi-path sampling. In this way, we thus cast the training of path filter in the positive and unlabeled (PU) learning paradigm, and also encourage a path embedding as better path/operation representation to enhance the identification capacity of the learned filter. By dint of this embedding, we can further shrink the search space by aggregating similar operations with similar embeddings, and the search can be more efficient and accurate. Extensive experiments validate the effectiveness of the proposed method GreedyNASv2. For example, our obtained GreedyNASv2-L achieves 81.1% Top-1 accuracy on ImageNet dataset, significantly outperforming the ResNet-50 strong baselines.

Unsupervised point cloud completion aims at estimating the corresponding complete point cloud of a partial point cloud in an unpaired manner. It is a crucial but challenging problem since there is no paired partial-complete supervision that can be exploited directly. In this work, we pro-pose a novel framework, which learns a unified and structured latent space that encoding both partial and complete point clouds. Specifically, we map a series of related par-tial point clouds into multiple complete shape and occlusion code pairs and fuse the codes to obtain their repre-sentations in the unified latent space. To enforce the learning of such a structured latent space, the proposed method adopts a series of constraints including structured ranking regularization, latent code swapping constraint, and distribution supervision on the related partial point clouds. By establishing such a unified and structured latent space, better partial-complete geometry consistency and shape completion accuracy can be achieved. Extensive experi-ments show that our proposed method consistently outper-forms state-of-the-art unsupervised methods on both syn-thetic ShapeNet and real-world KITTI, ScanNet, and Mat- terport3D datasets.

6-DoF object pose estimation from a monocular image is challenging, and a post-refinement procedure is generally needed for high-precision estimation. In this paper, we propose a framework based on a recurrent neural network (RNN) for object pose refinement, which is robust to erroneous initial poses and occlusions. During the recurrent iterations, object pose refinement is formulated as a nonlinear least squares problem based on the estimated correspondence field (between a rendered image and the observed image). The problem is then solved by a differentiable Levenberg-Marquardt (LM) algorithm enabling end-to-end training. The correspondence field estimation and pose refinement are conducted alternatively in each iteration to recover the object poses. Furthermore, to improve the robustness to occlusion, we introduce a consistency-check mechanism based on the learned descriptors of the 3D model and observed 2D images, which downweights the unreliable correspondences during pose optimization. Extensive experiments on LINEMOD, Occlusion-LINEMOD, and YCB-Video datasets validate the effectiveness of our method and demonstrate state-of-the-art performance.

We present a simple and effective framework, named Point2Seq, for 3D object detection from point clouds. In contrast to previous methods that normally predict attributes of 3D objects all at once, we expressively model the interdependencies between attributes of 3D objects, which in turn enables a better detection accuracy. Specifically, we view each 3D object as a sequence of words and reformulate the 3D object detection task as decoding words from 3D scenes in an auto-regressive manner. We further propose a lightweight scene-to-sequence decoder that can auto-regressively generate words conditioned on features from a 3D scene as well as cues from the preceding words. The predicted words eventually constitute a set of sequences that completely describe the 3D objects in the scene, and all the predicted sequences are then automatically assigned to the respective ground truths through similarity-based sequence matching. Our approach is conceptually intuitive and can be readily plugged upon most existing 3D-detection backbones without adding too much computational over-head; the sequential decoding paradigm we proposed, on the other hand, can better exploit information from complex 3D scenes with the aid of preceding predicted words. Without bells and whistles, our method significantly out-performs previous anchor- and center-based 3D object detection frameworks, yielding the new state of the art on the challenging ONCE dataset as well as the Waymo Open Dataset. Code is available at https://github.com/ocNflag/point2seq.

Vision transformers have achieved great successes in many computer vision tasks. Most methods generate vision tokens by splitting an image into a regular and fixed grid and treating each cell as a token. However, not all regions are equally important in human-centric vision tasks, e.g., the human body needs a fine representation with many tokens, while the image background can be modeled by a few tokens. To address this problem, we propose a novel Vision Transformer, called Token Clustering Transformer (TCFormer), which merges tokens by progressive clustering, where the tokens can be merged from different locations with flexible shapes and sizes. The tokens in TCFormer can not only focus on important areas but also adjust the token shapes to fit the semantic concept and adopt a fine resolution for regions containing critical details, which is beneficial to capturing detailed information. Extensive experiments show that TCFormer consistently outperforms its counterparts on different challenging human-centric tasks and datasets, including whole-body pose estimation on COCO-WholeBody and 3D human mesh reconstruction on 3DPW. Code is available at https://github.com/zengwang430521/TCFormer.git.

The lack of large-scale noisy-clean image pairs restricts supervised denoising methods' deployment in actual applications. While existing unsupervised methods are able to learn image denoising without ground-truth clean images, they either show poor performance or work under impractical settings (e.g., paired noisy images). In this paper, we present a practical unsupervised image denoising method to achieve state-of-the-art denoising performance. Our method only requires single noisy images and a noise model, which is easily accessible in practical raw image denoising. It performs two steps iteratively: (1) Constructing a noisier-noisy dataset with random noise from the noise model; (2) training a model on the noisier-noisy dataset and using the trained model to refine noisy images to obtain the targets used in the next round. We further approximate our full iterative method with a fast algorithm for more efficient training while keeping its original high performance. Experiments on real-world, synthetic, and correlated noise show that our proposed unsupervised denoising approach has superior performances over existing unsupervised methods and competitive performance with supervised methods. In addition, we argue that existing denoising datasets are of low quality and contain only a small number of scenes. To evaluate raw image denoising performance in real-world applications, we build a high-quality raw image dataset SenseNoise-500 that contains 500 real-life scenes. The dataset can serve as a strong benchmark for better evaluating raw image denoising. Code and dataset will be released11https://github.com/zhangyi-3/IDR

To build an artificial neural network like the biological intelligence system, recent works have unified numerous tasks into a generalist model, which can process various tasks with shared parameters and do not have any task-specific modules. While generalist models achieve promising results on various benchmarks, they have performance degradation on some tasks compared with task-specialized models. In this work, we find that interference among different tasks and modalities is the main factor to this phenomenon. To mitigate such interference, we introduce the Conditional Mixture-of-Experts (Conditional MoEs) to generalist models. Routing strategies under different levels of conditions are proposed to take both the training/inference cost and generalization ability into account. By incorporating the proposed Conditional MoEs, the recently proposed generalist model Uni-Perceiver can effectively mitigate the interference across tasks and modalities, and achieves state-of-the-art results on a series of downstream tasks via prompt tuning on 1% of downstream data. Moreover, the introduction of Conditional MoEs still holds the generalization ability of generalist models to conduct zero-shot inference on new tasks, e.g., videotext retrieval and video caption. Code and pre-trained generalist models are publicly released at https://github.com/fundamentalvision/Uni-Perceiver.

Multi-scale representations deeply learned via convolutional neural networks have shown tremendous importance for various pixel-level prediction problems. In this paper we present a novel approach that advances the state of the art on pixel-level prediction in a fundamental aspect, i.e. structured multi-scale features learning and fusion. In contrast to previous works directly considering multi-scale feature maps obtained from the inner layers of a primary CNN architecture, and simply fusing the features with weighted averaging or concatenation, we propose a probabilistic graph attention network structure based on a novel Attention-Gated Conditional Random Fields (AG-CRFs) model for learning and fusing multi-scale representations in a principled manner. In order to further improve the learning capacity of the network structure, we propose to exploit feature dependant conditional kernels within the deep probabilistic framework. Extensive experiments are conducted on four publicly available datasets (i.e. BSDS500, NYUD-V2, KITTI and Pascal-Context) and on three challenging pixel-wise prediction problems involving both discrete and continuous labels (i.e. monocular depth estimation, object contour prediction and semantic segmentation). Quantitative and qualitative results demonstrate the effectiveness of the proposed latent AG-CRF model and the overall probabilistic graph attention network with feature conditional kernels for structured feature learning and pixel-wise prediction.

Conditional generative adversarial networks (cGANs) target at synthesizing diverse images given the input conditions and latent codes, but unfortunately, they usually suffer from the issue of mode collapse. To solve this issue, previous works [47], [22] mainly focused on encouraging the correlation between the latent codes and their generated images, while ignoring the relations between images generated from various latent codes. The recent MSGAN [27] tried to encourage the diversity of the generated image but only considers "negative" relations between the image pairs.In this paper, we propose a novel DivCo framework to properly constrain both "positive" and "negative" relations between the generated images specified in the latent space. To the best of our knowledge, this is the first attempt to use contrastive learning for diverse conditional image synthesis. A novel latent-augmented contrastive loss is introduced, which encourages images generated from adjacent latent codes to be similar and those generated from distinct latent codes to be dissimilar. The proposed latent-augmented contrastive loss is well compatible with various cGAN architectures. Extensive experiments demonstrate that the proposed DivCo can produce more diverse images than state-of-the-art methods without sacrificing visual quality in multiple unpaired and paired image generation tasks. Training code and pretrained models are available at https://github.com/ruiliu-ai/DivCo.

Semantic Scene Completion aims at reconstructing a complete 3D scene with precise voxel-wise semantics from a single-view depth or RGBD image. It is a crucial but challenging problem for indoor scene understanding. In this work, we present a novel framework named Scene-Instance-Scene Network (SISNet), which takes advantages of both in-stance and scene level semantic information. Our method is capable of inferring fine-grained shape details as well as nearby objects whose semantic categories are easily mixed-up. The key insight is that we decouple the instances from a coarsely completed semantic scene instead of a raw input image to guide the reconstruction of instances and the over-all scene. SISNet conducts iterative scene-to-instance (SI) and instance-to-scene (IS) semantic completion. Specifically, the SI is able to encode objects’ surrounding context for effectively decoupling instances from the scene and each instance could be voxelized into higher resolution to capture finer details. With IS, fine-grained instance information can be integrated back into the 3D scene and thus leads to more accurate semantic scene completion. Utilizing such an iterative mechanism, the scene and instance completion benefits each other to achieve higher completion accuracy. Extensively experiments show that our proposed method consistently outperforms state-of-the-art methods on both real NYU, NYUCAD and synthetic SUNCG-RGBD datasets. The code and the supplementary material will be available at https://github.com/yjcaimeow/SISNet.

Human pose estimation has achieved significant progress in recent years. However, most of the recent methods focus on improving accuracy using complicated models and ignoring real-time efficiency. To achieve a better trade-off between accuracy and efficiency, we propose a novel neural architecture search (NAS) method, termed ViP-NAS, to search networks in both spatial and temporal levels for fast online video pose estimation. In the spatial level, we carefully design the search space with five different dimensions including network depth, width, kernel size, group number, and attentions. In the temporal level, we search from a series of temporal feature fusions to optimize the total accuracy and speed across multiple video frames. To the best of our knowledge, we are the first to search for the temporal feature fusion and automatic computation allocation in videos. Extensive experiments demonstrate the effectiveness of our approach on the challenging COCO2017 and PoseTrack2018 datasets. Our discovered model family, S-ViPNAS and T-ViPNAS, achieve significantly higher inference speed (CPU real-time) without sacrificing the accuracy compared to the previous state-of-the-art methods.

Stereophonic audio, especially binaural audio, plays an essential role in immersive viewing environments. Recent research has explored generating visually guided stereophonic audios supervised by multi-channel audio collections. However, due to the requirement of professional recording devices, existing datasets are limited in scale and variety, which impedes the generalization of supervised methods in real-world scenarios. In this work, we propose PseudoBinaural, an effective pipeline that is free of binaural recordings. The key insight is to carefully build pseudo visual-stereo pairs with mono data for training. Specifically, we leverage spherical harmonic decomposition and head-related impulse response (HRIR) to identify the relationship between spatial locations and received binaural audios. Then in the visual modality, corresponding visual cues of the mono data are manually placed at sound source positions to form the pairs. Compared to fully-supervised paradigms, our binaural-recording-free pipeline shows great stability in cross-dataset evaluation and achieves comparable performance under subjective preference. Moreover, combined with binaural recordings, our method is able to further boost the performance of binaural audio generation under supervised settings1.

While accurate lip synchronization has been achieved for arbitrary-subject audio-driven talking face generation, the problem of how to efficiently drive the head pose remains. Previous methods rely on pre-estimated structural information such as landmarks and 3D parameters, aiming to generate personalized rhythmic movements. However, the inaccuracy of such estimated information under extreme conditions would lead to degradation problems. In this paper, we propose a clean yet effective framework to generate pose-controllable talking faces. We operate on non-aligned raw face images, using only a single photo as an identity reference. The key is to modularize audio-visual representations by devising an implicit low-dimension pose code. Substantially, both speech content and head pose information lie in a joint non-identity embedding space. While speech content information can be defined by learning the intrinsic synchronization between audio-visual modalities, we identify that a pose code will be complementarily learned in a modulated convolution-based reconstruction framework.Extensive experiments show that our method generates accurately lip-synced talking faces whose poses are controllable by other videos. Moreover, our model has multiple advanced capabilities including extreme view robustness and talking face frontalization.1

The recently proposed Detection Transformer (DETR) model successfully applies Transformer to objects detection and achieves comparable performance with two-stage object detection frameworks, such as Faster-RCNN. However, DETR suffers from its slow convergence. Training DETR [4] from scratch needs 500 epochs to achieve a high accuracy. To accelerate its convergence, we propose a simple yet effective scheme for improving the DETR framework, namely Spatially Modulated Co-Attention (SMCA) mechanism. The core idea of SMCA is to conduct location-aware co-attention in DETR by constraining co-attention responses to be high near initially estimated bounding box locations. Our proposed SMCA increases DETR’s convergence speed by replacing the original co-attention mechanism in the decoder while keeping other operations in DETR unchanged. Furthermore, by integrating multi-head and scale-selection attention designs into SMCA, our fully-fledged SMCA can achieve better performance compared to DETR with a dilated convolution-based backbone (45.6 mAP at 108 epochs vs. 43.3 mAP at 500 epochs). We perform extensive ablation studies on COCO dataset to validate SMCA. Code is released at https://github.com/gaopengcuhk/SMCA-DETR.

Transformer, as a strong and flexible architecture for modelling long-range relations, has been widely explored in vision tasks. However, when used in video inpainting that requires fine-grained representation, existed method still suffers from yielding blurry edges in detail due to the hard patch splitting. Here we aim to tackle this problem by proposing FuseFormer, a Transformer model designed for video inpainting via fine-grained feature fusion based on novel Soft Split and Soft Composition operations. The soft split divides feature map into many patches with given overlapping interval. On the contrary, the soft composition operates by stitching different patches into a whole feature map where pixels in overlapping regions are summed up. These two modules are first used in tokenization before Transformer layers and de-tokenization after Transformer layers, for effective mapping between tokens and features. Therefore, sub-patch level information interaction is enabled for more effective feature propagation between neighboring patches, resulting in synthesizing vivid content for hole regions in videos. Moreover, in FuseFormer, we elaborately insert the soft composition and soft split into the feed-forward network, enabling the 1D linear layers to have the capability of modelling 2D structure. And, the sub-patch level feature fusion ability is further enhanced. In both quantitative and qualitative evaluations, our proposed FuseFormer surpasses state-of-the-art methods. We also conduct detailed analysis to examine its superiority. Code and pretrained models are available at https://github.com/ruiliu-ai/FuseFormer.

Stereo-based 3D detection aims at detecting 3D objects from stereo images, which provides a low-cost solution for 3D perception. However, its performance is still inferior compared with LiDAR-based detection algorithms. To detect and localize accurate 3D bounding boxes, LiDAR-based detectors encode high-level representations from Li-DAR point clouds, such as accurate object boundaries and surface normal directions. In contrast, high-level features learned by stereo-based detectors are easily affected by the erroneous depth estimation due to the limitation of stereo matching. To solve the problem, we propose LIGA-Stereo (LiDAR Geometry Aware Stereo Detector) to learn stereo-based 3D detectors under the guidance of high-level geometry-aware representations of LiDAR-based detection models. In addition, we found existing voxel-based stereo detectors failed to learn semantic features effectively from indirect 3D supervisions. We attach an auxiliary 2D detection head to provide direct 2D semantic supervisions. Experiment results show that the above two strategies improved the geometric and semantic representation capabilities. Compared with the state-of-the-art stereo detector, our method has improved the 3D detection performance of cars, pedestrians, cyclists by 10.44%, 5.69%, 5.97% mAP respectively on the official KITTI benchmark. The gap between stereo-based and LiDAR-based 3D detectors is further narrowed. The code is available at https://xy-guo.github.io/liga/.

Multi-objective multi-task learning aims to boost the performance of all tasks by leveraging their correlation and conflict appropriately. Nevertheless, in real practice, users may have preference for certain tasks, and other tasks simply serve as privileged or auxiliary tasks to assist the training of target tasks. The privileged tasks thus possess less or even no priority in the final task assessment by users. Motivated by this, we propose a privileged multiple descent algorithm to arbitrate the learning of target tasks and privileged tasks. Concretely, we introduce a privileged parameter so that the optimization direction does not necessarily follow the gradient from the privileged tasks, but concentrates more on the target tasks. Besides, we also encourage a priority parameter for the target tasks to control the potential distraction of optimization direction from the privileged tasks. In this way, the optimization direction can be more aggressively determined by weighting the gradients among target and privileged tasks, and thus highlight more the performance of target tasks under the unified multi-task learning context. Extensive experiments on synthetic and real-world datasets indicate that our method can achieve versatile Pareto solutions under varying preference for the target tasks.

Image and video enhancement such as color constancy, low light enhancement, and tone mapping on smartphones is challenging, because high-quality images should be achieved efficiently with a limited resource budget. Unlike prior works that either used very deep CNNs or large Trans-former models, we propose a structure-aware lightweight Transformer, termed STAR, for real-time image enhancement. STAR is formulated to capture long-range dependencies between image patches, which naturally and implicitly captures the structural relationships of different regions in an image. STAR is a general architecture that can be easily adapted to different image enhancement tasks. Extensive experiments show that STAR can effectively boost the quality and efficiency of many tasks such as illumination enhancement, auto white balance, and photo retouching, which are indispensable components for image processing on smartphones. For example, STAR reduces model complexity and improves image quality compared to the recent state-of-the-art [19] on the MIT-Adobe FiveK dataset [7] (i.e., 1.8dB PSNR improvements with 25% parameters and 13% float operations.)

The lack of large-scale real raw image denoising dataset gives rise to challenges on synthesizing realistic raw image noise for training denoising models. However, the real raw image noise is contributed by many noise sources and varies greatly among different sensors. Existing methods are unable to model all noise sources accurately, and building a noise model for each sensor is also laborious. In this paper, we introduce a new perspective to synthesize noise by directly sampling from the sensor’s real noise. It inherently generates accurate raw image noise for different camera sensors. Two efficient and generic techniques: pattern-aligned patch sampling and high-bit reconstruction help accurate synthesis of spatial-correlated noise and high-bit noise respectively. We conduct systematic experiments on SIDD and ELD datasets. The results show that (1) our method outperforms existing methods and demonstrates wide generalization on different sensors and lighting conditions. (2) Recent conclusions derived from DNN-based noise modeling methods are actually based on inaccurate noise parameters. The DNN-based methods still cannot outperform physics-based statistical methods. The code will be available at https://github.com/zhangyi-3/.

Unsupervised visual representation learning has gained much attention from the computer vision community because of the recent achievement of contrastive learning. Most of the existing contrastive learning frameworks adopt the instance discrimination as the pretext task, which treating every single instance as a different class. However, such method will inevitably cause class collision problems, which hurts the quality of the learned representation. Motivated by this observation, we introduced a weakly supervised contrastive learning framework (WCL) to tackle this issue. Specifically, our proposed framework is based on two projection heads, one of which will perform the regular instance discrimination task. The other head will use a graph-based method to explore similar samples and generate a weak label, then perform a supervised contrastive learning task based on the weak label to pull the similar images closer. We further introduced a K-Nearest Neighbor based multi-crop strategy to expand the number of positive samples. Extensive experimental results demonstrate WCL improves the quality of self-supervised representations across different datasets. Notably, we get a new state-of-the-art result for semi-supervised learning. With only 1% and 10% labeled examples, WCL achieves 65% and 72% ImageNet Top-1 Accuracy using ResNet50, which is even higher than SimCLRv2 with ResNet101.

Model quantization is challenging due to many tedious hyper-parameters such as precision (bitwidth), dynamic range (minimum and maximum discrete values) and stepsize (interval between discrete values). Unlike prior arts that carefully tune these values, we present a fully differentiable approach to learn all of them, named Differentiable Dynamic Quantization (DDQ), which has several benefits. (1) DDQ is able to quantize challenging lightweight architectures like MobileNets, where different layers prefer different quantization parameters. (2) DDQ is hardware-friendly and can be easily implemented using low-precision matrix-vector multiplication, making it capable in many hardware such as ARM. (3) Extensive experiments show that DDQ outperforms prior arts on many networks and benchmarks, especially when models are already efficient and compact. e.g., DDQ is the first approach that achieves lossless 4-bit quantization for MobileNetV2 on ImageNet.

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most of methods mainly focus on the instance level information (\ie, the different augmented images of the same instance should have the same feature or cluster into the same class), but there is a lack of attention on the relationships between different instances. In this paper, we introduced a novel SSL paradigm, which we term as relational self-supervised learning (ReSSL) framework that learns representations by modeling the relationship between different instances. Specifically, our proposed method employs sharpened distribution of pairwise similarities among different instances as \textit{relation} metric, which is thus utilized to match the feature embeddings of different augmentations. Moreover, to boost the performance, we argue that weak augmentations matter to represent a more reliable relation, and leverage momentum strategy for practical efficiency. Experimental results show that our proposed ReSSL significantly outperforms the previous state-of-the-art algorithms in terms of both performance and training efficiency.

Person re-identification (re-ID) aims to robustly measure visual affinities between person images. It has wide applications in intelligent surveillance by associating same persons' images across multiple cameras. It is generally treated as an image retrieval problem: given a probe person image, the affinities between the probe image and gallery images (P2G affinities) are used to rank the retrieved gallery images. There exist two main challenges for effectively solving this problem. 1) Person images usually show significant variations because of different person poses and viewing angles. The spatial layouts and correspondences between person images are therefore vital information for tackling this problem. State-of-the-art methods either ignore such spatial variation or utilize extra pose information for handling the challenge. 2) Most existing person re-ID methods rank gallery images considering only P2G affinities but ignore the affinities between the gallery images (G2G affinity). Such affinities could provide important clues for accurate gallery image ranking but were only utilized in post-processing stages by current methods. In this article, we propose a unified end-to-end deep learning framework to tackle the two challenges. For handling viewpoint and pose variations between compared person images, we propose a novel Kronecker Product Matching operation to match and warp feature maps of different persons. Comparing warped feature maps results in more accurate P2G affinities. To fully utilize all available P2G and G2G affinities for accurately ranking gallery person images, a novel group-shuffling random walk operation is proposed. Both Kronecker Product Matching and Group-shuffling Random Walk operations are end-to-end trainable and are shown to improve the learned visual features if integrated in the deep learning framework. The proposed approach outperforms state-of-the-art methods on Market-1501, CUHK03 and DukeMTMC datasets, which demonstrates the effectiveness and generalization ability of our proposed approach. Code is available at https://github.com/YantaoShen/kpm_rw_person_reid.

3D object detection from LiDAR point cloud is a challenging problem in 3D scene understanding and has many practical applications. In this paper, we extend our preliminary work PointRCNN to a novel and strong point-cloud-based 3D object detection framework, the part-aware and aggregation neural network (Part-A2net). The whole framework consists of the part-aware stage and the part-aggregation stage. First, the part-aware stage for the first time fully utilizes free-of-charge part supervisions derived from 3D ground-truth boxes to simultaneously predict high quality 3D proposals and accurate intra-object part locations. The predicted intra-object part locations within the same proposal are grouped by our new-designed RoI-aware point cloud pooling module, which results in an effective representation to encode the geometry-specific features of each 3D proposal. Then the part-aggregation stage learns to re-score the box and refine the box location by exploring the spatial relationship of the pooled intra-object part locations. Extensive experiments are conducted to demonstrate the performance improvements from each component of our proposed framework. Our Part-A2net outperforms all existing 3D detection methods and achieves new state-of-the-art on KITTI 3D object detection dataset by utilizing only the LiDAR point cloud data.

Monocular 3D object detection task aims to predict the 3D bounding boxes of objects based on monocular RGB images. Since the location recovery in 3D space is quite difficult on account of absence of depth information, this paper proposes a novel unified framework which decomposes the detection problem into a structured polygon prediction task and a depth recovery task. Different from the widely studied 2D bounding boxes, the proposed novel structured polygon in the 2D image consists of several projected surfaces of the target object. Compared to the widely-used 3D bounding box proposals, it is shown to be a better representation for 3D detection. In order to inversely project the predicted 2D structured polygon to a cuboid in the 3D physical world, the following depth recovery task uses the object height prior to complete the inverse projection transformation with the given camera projection matrix. Moreover, a fine-grained 3D box refinement scheme is proposed to further rectify the 3D detection results. Experiments are conducted on the challenging KITTI benchmark, in which our method achieves state-of-the-art detection accuracy.

Deep Neural Networks are vulnerable to adversarial samples, which can fool classifiers by adding small perturbations onto the original image. Since the pioneering optimization-based adversarial attack method, many following methods have been proposed in the past several years. However most of these methods add perturbations in a "pixel-wise" and "global" way. Firstly, because of the contradiction between the local smoothness of natural images and the noisy property of these adversarial perturbations, this "pixel-wise" way makes these methods not robust to image processing based defense methods and steganalysis based detection methods. Secondly, we find adding perturbations to the background is less useful than to the salient object, thus the "global" way is also not optimal. Based on these two considerations, we propose the first robust superpixel-guided attentional adversarial attack method. Specifically, the adversarial perturbations are only added to the salient regions and guaranteed to be same within each superpixel. Through extensive experiments, we demonstrate our method can preserve the attack ability even in this highly constrained modification space. More importantly, compared to existing methods, it is significantly more robust to image processing based defense and steganalysis based detection.

Clustering has many applications in research and industry. However, traditional clustering methods, such as K-means, DBSCAN and HAC, impose oversimplifying assumptions and thus are not well-suited to face clustering. To adapt to the distribution of realistic problems, a natural approach is to use Graph Convolutional Networks (GCNs) to enhance features for clustering. However, GCNs can only utilize local information, which ignores the overall characterisitcs of the clusters. In this paper, we propose a Density-Aware Feature Embedding Network (DA-Net) for the task of face clustering, which utilizes both local and non-local information, to learn a robust feature embedding. Specifically, DA-Net uses GCNs to aggregate features locally, and then incorporates non-local information using a density chain, which is a chain of faces from low density to high density. This density chain exploits the non-uniform distribution of face images in the dataset. Then, an LSTM takes the density chain as input to generate the final feature embedding. Once this embedding is generated, traditional clustering methods, such as density-based clustering, can be used to obtain the final clustering results. Extensive experiments verify the effectiveness of the proposed feature embedding method, which can achieve state-of-the-art performance on public benchmarks.

Standard Knowledge Distillation (KD) approaches distill the knowledge of a cumbersome teacher model into the parameters of a student model with a pre-defined architecture. However, the knowledge of a neural network, which is represented by the network's output distribution conditioned on its input, depends not only on its parameters but also on its architecture. Hence, a more generalized approach for KD is to distill the teacher's knowledge into both the parameters and architecture of the student. To achieve this, we present a new \textit{Architecture-aware Knowledge Distillation (AKD)} approach that finds student models (pearls for the teacher) that are best for distilling the given teacher model. In particular, we leverage Neural Architecture Search (NAS), equipped with our KD-guided reward, to search for the best student architectures for a given teacher. Experimental results show our proposed AKD consistently outperforms the conventional NAS plus KD approach, and achieves state-of-the-art results on the ImageNet classification task under various latency settings. Furthermore, the best AKD student architecture for the ImageNet classification task also transfers well to other tasks such as million level face recognition and ensemble learning.

Large-scale synthetic datasets are beneficial to stereo matching but usually introduce known domain bias. Although unsupervised image-to-image translation networks represented by CycleGAN show great potential in dealing with domain gap, it is non-trivial to generalize this method to stereo matching due to the problem of pixel distortion and stereo mismatch after translation. In this paper, we propose an end-to-end training framework with domain translation and stereo matching networks to tackle this challenge. First, joint optimization between domain translation and stereo matching networks in our end-to-end framework makes the former facilitate the latter one to the maximum extent. Second, this framework introduces two novel losses, i.e., bidirectional multi-scale feature re-projection loss and correlation consistency loss, to help translate all synthetic stereo images into realistic ones as well as maintain epipolar constraints. The effective combination of above two contributions leads to impressive stereo-consistent translation and disparity estimation accuracy. In addition, a mode seeking regularization term is added to endow the synthetic-to-real translation results with higher fine-grained diversity. Extensive experiments demonstrate the effectiveness of the proposed framework on bridging the synthetic-to-real domain gap on stereo matching.

We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds. Our proposed method deeply integrates both 3D voxel Convolutional Neural Network (CNN) and PointNet-based set abstraction to learn more discriminative point cloud features. It takes advantages of efficient learning and high-quality proposals of the 3D voxel CNN and the flexible receptive fields of the PointNet-based networks. Specifically, the proposed framework summarizes the 3D scene with a 3D voxel CNN into a small set of keypoints via a novel voxel set abstraction module to save follow-up computations and also to encode representative scene features. Given the high-quality 3D proposals generated by the voxel CNN, the RoI-grid pooling is proposed to abstract proposal-specific features from the keypoints to the RoI-grid points via keypoint set abstraction. Compared with conventional pooling operations, the RoI-grid feature points encode much richer context information for accurately estimating object confidences and locations. Extensive experiments on both the KITTI dataset and the Waymo Open dataset show that our proposed PV-RCNN surpasses state-of-the-art 3D detection methods with remarkable margins.

The "shared head for classification and localization'' (sibling head), firstly denominated in Fast RCNN, has been leading the fashion of the object detection community in the past five years. This paper provides the observation that the spatial misalignment between the two object functions in the sibling head can considerably hurt the training process, but this misalignment can be resolved by a very simple operator called task-aware spatial disentanglement (TSD). Considering the classification and regression, TSD decouples them from the spatial dimension by generating two disentangled proposals for them, which are estimated by the shared proposal. This is inspired by the natural insight that for one instance, the features in some salient area may have rich information for classification while these around the boundary may be good at bounding box regression. Surprisingly, this simple design can boost all backbones and models on both MS COCO and Google OpenImage consistently by ~3% mAP. Further, we propose a progressive constraint to enlarge the performance margin between the disentangled and the shared proposals, and gain ~1% more mAP. We show the TSD breaks through the upper bound of nowadays single-model detector by a large margin (mAP 49.4 with ResNet-101, 51.2 with SENet154), and is the core model of our 1st place solution on the Google OpenImage Challenge 2019.

Estimating 3D mesh of the human body from a single 2D image is an important task with many applications such as augmented reality and Human-Robot interaction. However, prior works reconstructed 3D mesh from global image feature extracted by using convolutional neural network (CNN), where the dense correspondences between the mesh surface and the image pixels are missing, leading to suboptimal solution. This paper proposes a model-free 3D human mesh estimation framework, named DecoMR, which explicitly establishes the dense correspondence between the mesh and the local image features in the UV space (i.e. a 2D space used for texture mapping of 3D mesh). DecoMR first predicts pixel-to-surface dense correspondence map (i.e., IUV image), with which we transfer local features from the image space to the UV space. Then the transferred local image features are processed in the UV space to regress a location map, which is well aligned with transferred features. Finally we reconstruct 3D human mesh from the regressed location map with a predefined mapping function. We also observe that the existing discontinuous UV map are unfriendly to the learning of network. Therefore, we propose a novel UV map that maintains most of the neighboring relations on the original mesh surface. Experiments demonstrate that our proposed local feature alignment and continuous UV map outperforms existing 3D mesh based methods on multiple public benchmarks. Code will be made available at https: //github.com/zengwang430521/DecoMR.

Though face rotation has achieved rapid progress in recent years, the lack of high-quality paired training data remains a great hurdle for existing methods. The current generative models heavily rely on datasets with multi-view images of the same person. Thus, their generated results are restricted by the scale and domain of the data source. To overcome these challenges, we propose a novel unsupervised framework that can synthesize photo-realistic rotated faces using only single-view image collections in the wild. Our key insight is that rotating faces in the 3D space back and forth, and re-rendering them to the 2D plane can serve as a strong self-supervision. We leverage the recent advances in 3D face modeling and high-resolution GAN to constitute our building blocks. Since the 3D rotation-and-render on faces can be applied to arbitrary angles without losing details, our approach is extremely suitable for in-the-wild scenarios (i.e. no paired data are available), where existing methods fall short. Extensive experiments demonstrate that our approach has superior synthesis quality as well as identity preservation over the state-of-the-art methods, across a wide range of poses and domains. Furthermore, we validate that our rotate-and-render framework naturally can act as an effective data augmentation engine for boosting modern face recognition systems even on strong baseline models.

Convolutional Neural Networks (CNNs) are typically constructed by stacking multiple building blocks, each of which contains a normalization layer such as batch normalization (BN) and a rectified linear function such as ReLU. However, this work shows that the combination of normalization and rectified linear function leads to inhibited channels, which have small magnitude and contribute little to the learned feature representation, impeding the generalization ability of CNNs. Unlike prior arts that simply removed the inhibited channels, we propose to “wake them up” during training by designing a novel neural building block, termed Channel Equilibrium (CE) block, which enables channels at the same layer to contribute equally to the learned representation. We show that CE is able to prevent inhibited channels both empirically and theoretically. CE has several appealing benefits. (1) It can be integrated into many advanced CNN architectures such as ResNet and MobileNet, outperforming their original networks. (2) CE has an interesting connection with the Nash Equilibrium, a well-known solution of a non-cooperative game. (3) Extensive experiments show that CE achieves state-of-the-art performance on various challenging benchmarks such as ImageNet and COCO.

Abstract Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images. Deep learning techniques have emerged as a powerful strategy for learning feature representations directly from data and have led to remarkable breakthroughs in the field of generic object detection. Given this period of rapid evolution, the goal of this paper is to provide a comprehensive survey of the recent achievements in this field brought about by deep learning techniques. More than 300 research contributions are included in this survey, covering many aspects of generic object detection: detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics. We finish the survey by identifying promising directions for future research.

Dense depth cues are important and have wide applications in various computer vision tasks. In autonomous driving, LIDAR sensors are adopted to acquire depth measurements around the vehicle to perceive the surrounding environments. However, depth maps obtained by LIDAR are generally sparse because of its hardware limitation. The task of depth completion attracts increasing attention, which aims at generating a dense depth map from an input sparse depth map. To effectively utilize multi-scale features, we propose three novel sparsity-invariant operations, based on which, a sparsity-invariant multi-scale encoder-decoder network (HMS-Net) for handling sparse inputs and sparse feature maps is also proposed. Additional RGB features could be incorporated to further improve the depth completion performance. Our extensive experiments and component analysis on two public benchmarks, KITTI depth completion benchmark and NYU-depth-v2 dataset, demonstrate the effectiveness of the proposed approach. As of Aug. 12th, 2018, on KITTI depth completion leaderboard, our proposed model without RGB guidance ranks 1st among all peer-reviewed methods without using RGB information, and our model with RGB guidance ranks 2nd among all RGB-guided methods.

Despite the great success of two-stage detectors, single-stage detector is still a more elegant and efficient way, yet suffers from the two well-known disharmonies during training, i.e. the huge difference in quantity between positive and negative examples as well as between easy and hard examples. In this work, we first point out that the essential effect of the two disharmonies can be summarized in term of the gradient. Further, we propose a novel gradient harmonizing mechanism (GHM) to be a hedging for the disharmonies. The philosophy behind GHM can be easily embedded into both classification loss function like cross-entropy (CE) and regression loss function like smooth-L1 (SL1) loss. To this end, two novel loss functions called GHM-C and GHM-R are designed to balancing the gradient flow for anchor classification and bounding box refinement, respectively. Ablation study on MS COCO demonstrates that without laborious hyper-parameter tuning, both GHM-C and GHM-R can bring substantial improvement for single-stage detector. Without any whistles and bells, the proposed model achieves 41.6 mAP on COCO testdev set which surpass the state-of-the-art method, Focal Loss (FL) + SL1, by 0.8. The code1 is released to facilitate future research.

Unsupervised cross-spectral stereo matching aims at recovering disparity given cross-spectral image pairs without any depth or disparity supervision. The estimated depth provides additional information complementary to original images, which can be helpful for other vision tasks such as tracking, recognition and detection. However, there are large appearance variations between images from different spectral bands, which is a challenge for cross-spectral stereo matching. Existing deep unsupervised stereo matching methods are sensitive to the appearance variations and do not perform well on cross-spectral data. We propose a novel unsupervised crossspectral stereo matching framework based on image-to-image translation. First, a style adaptation network transforms images across different spectral bands by cycle consistency and adversarial learning, during which appearance variations are minimized. Then, a stereo matching network is trained with image pairs from the same spectra using view reconstruction loss. At last, the estimated disparity is utilized to supervise the spectral translation network in an end-to-end way. Moreover, a novel style adaptation network F-cycleGAN is proposed to improve the robustness of spectral translation. Our method can tackle appearance variations and enhance the robustness of unsupervised cross-spectral stereo matching. Experimental results show that our method achieves good performance without using depth supervision or explicit semantic information.

Talking face generation aims to synthesize a sequence of face images that correspond to a clip of speech. This is a challenging task because face appearance variation and semantics of speech are coupled together in the subtle movements of the talking face regions. Existing works either construct specific face appearance model on specific subjects or model the transformation between lip motion and speech. In this work, we integrate both aspects and enable arbitrary-subject talking face generation by learning disentangled audio-visual representation. We find that the talking face sequence is actually a composition of both subject-related information and speech-related information. These two spaces are then explicitly disentangled through a novel associative-and-adversarial training process. This disentangled representation has an advantage where both audio and video can serve as inputs for generation. Extensive experiments show that the proposed approach generates realistic talking face sequences on arbitrary subjects with much clearer lip motion patterns than previous work. We also demonstrate the learned audio-visual representation is extremely useful for the tasks of automatic lip reading and audio-video retrieval.

Learning effective fusion of multi-modality features is at the heart of visual question answering. We propose a novel method of dynamically fuse multi-modal features with intra- and inter-modality information flow, which alternatively pass dynamic information between and across the visual and language modalities. It can robustly capture the high-level interactions between language and vision domains, thus significantly improves the performance of visual question answering. We also show that, the proposed dynamic intra modality attention flow conditioned on the other modality can dynamically modulate the intra-modality attention of the current modality, which is vital for multimodality feature fusion. Experimental evaluations on the VQA 2.0 dataset show that the proposed method achieves the state-of-the-art VQA performance. Extensive ablation studies are carried out for the comprehensive analysis of the proposed method.

Understanding fashion images has been advanced by benchmarks with rich annotations such as DeepFashion, whose labels include clothing categories, landmarks, and consumer-commercial image pairs. However, DeepFashion has nonnegligible issues such as single clothing-item per image, sparse landmarks (4∼8 only), and no per-pixel masks, making it had significant gap from real-world scenarios. We fill in the gap by presenting DeepFashion2 to address these issues. It is a versatile benchmark of four tasks including clothes detection, pose estimation, segmentation, and retrieval. It has 801K clothing items where each item has rich annotations such as style, scale, view- point, occlusion, bounding box, dense landmarks (e.g. 39 for ‘long sleeve outwear’ and 15 for ‘vest’), and masks. There are also 873K Commercial-Consumer clothes pairs. The annotations of DeepFashion2 are much larger than its counterparts such as 8× of FashionAI Global Challenge. A strong baseline is proposed, called Match R- CNN, which builds upon Mask R-CNN to solve the above four tasks in an end-to-end manner. Extensive evaluations are conducted with different criterions in Deep- Fashion2. DeepFashion2 Dataset will be released at : https://github.com/switchablenorms/DeepFashion2

Stereo matching estimates the disparity between a rectified image pair, which is of great importance to depth sensing, autonomous driving, and other related tasks. Previous works built cost volumes with cross-correlation or concatenation of left and right features across all disparity levels, and then a 2D or 3D convolutional neural network is utilized to regress the disparity maps. In this paper, we propose to construct the cost volume by group-wise correlation. The left features and the right features are divided into groups along the channel dimension, and correlation maps are computed among each group to obtain multiple matching cost proposals, which are then packed into a cost volume. Group-wise correlation provides efficient representations for measuring feature similarities and will not lose too much information like full correlation. It also preserves better performance when reducing parameters compared with previous methods. The 3D stacked hourglass network proposed in previous works is improved to boost the performance and decrease the inference computational cost. Experiment results show that our method outperforms previous methods on Scene Flow, KITTI 2012, and KITTI 2015 datasets.

Few-shot learning is an important area of research. Conceptually, humans are readily able to understand new concepts given just a few examples, while in more pragmatic terms, limited-example training situations are common practice. Recent effective approaches to few-shot learning employ a metric-learning framework to learn a feature similarity comparison between a query (test) example, and the few support (training) examples. However, these approaches treat each support class independently from one another, never looking at the entire task as a whole. Because of this, they are constrained to use a single set of features for all possible test-time tasks, which hinders the ability to distinguish the most relevant dimensions for the task at hand. In this work, we introduce a Category Traversal Module that can be inserted as a plug-and-play module into most metric-learning based few-shot learners. This component traverses across the entire support set at once, identifying task-relevant features based on both intra-class commonality and inter-class uniqueness in the feature space. Incorporating our module improves performance considerably (5%-10% relative) over baseline systems on both miniImageNet and tieredImageNet benchmarks, with overall performance competitive with the most recent state-of-the-art systems.

We present an efficient 3D object detection framework based on a single RGB image in the scenario of autonomous driving. Our efforts are put on extracting the underlying 3D information in a 2D image and determining the accurate 3D bounding box of object without point cloud or stereo data. Leveraging the off-the-shelf 2D object detector, we propose an artful approach to efficiently obtain a coarse cuboid for each predicted 2D box. The coarse cuboid has enough accuracy to guide us to determine the 3D box of the object by refinement. In contrast to previous state-of-the-art methods that only use the features extracted from the 2D bounding box for box refinement, we explore the 3D structure information of the object by employing the visual features of visible surfaces. The new features from surfaces are utilized to eliminate the problem of representation ambiguity brought by only using 2D bounding box. Moreover, we investigate different methods of 3D box refinement and discover that a classification formulation with quality aware loss have much better performance than regression. Evaluated on KITTI benchmark, our approach outperforms current state-of-the-art methods for single RGB image based 3D object detection.

Flow-based generative models show great potential in image synthesis due to its reversible pipeline and exact log-likelihood target, yet it suffers from weak ability for conditional image synthesis, especially for multi-label or unaware conditions. This is because the potential distribution of image conditions is hard to measure precisely from its latent variable $z$. In this paper, based on modeling a joint probabilistic density of an image and its conditions, we propose a novel flow-based generative model named conditional adversarial generative flow (CAGlow). Instead of disentangling attributes from latent space, we blaze a new trail for learning an encoder to estimate the mapping from condition space to latent space in an adversarial manner. Given a specific condition $c$, CAGlow can encode it to a sampled $z$, and then enable robust conditional image synthesis in complex situations like combining person identity with multiple attributes. The proposed CAGlow can be implemented in both supervised and unsupervised manners, thus can synthesize images with conditional information like categories, attributes, and even some unknown properties. Extensive experiments show that CAGlow ensures the independence of different conditions and outperforms regular Glow to a significant extent.

Referring expression grounding aims at locating certain objects or persons in an image with a referring expression, where the key challenge is to comprehend and align various types of information from visual and textual domain, such as visual attributes, location and interactions with surrounding regions. Although the attention mechanism has been successfully applied for cross-modal alignments, previous attention models focus on only the most dominant features of both modalities, and neglect the fact that there could be multiple comprehensive textual-visual correspondences between images and referring expressions. To tackle this issue, we design a novel cross-modal attention-guided erasing approach, where we discard the most dominant information from either textual or visual domains to generate difficult training samples online, and to drive the model to discover complementary textual-visual correspondences. Extensive experiments demonstrate the effectiveness of our proposed method, which achieves state-of-the-art performance on three referring expression grounding datasets.

This paper proposes the novel task of video generation conditioned on a SINGLE semantic label map, which provides a good balance between flexibility and quality in the generation process. Different from typical end-to-end approaches, which model both scene content and dynamics in a single step, we propose to decompose this difficult task into two sub-problems. As current image generation methods do better than video generation in terms of detail, we synthesize high quality content by only generating the first frame. Then we animate the scene based on its semantic meaning to obtain temporally coherent video, giving us excellent results overall. We employ a cVAE for predicting optical flow as a beneficial intermediate step to generate a video sequence conditioned on the initial single frame. A semantic label map is integrated into the flow prediction module to achieve major improvements in the image-to-video generation process. Extensive experiments on the Cityscapes dataset show that our method outperforms all competing methods.

Normalization methods improve both optimization and generalization of ConvNets. To further boost performance, the recently-proposed switchable normalization (SN) provides a new perspective for deep learning: it learns to select different normalizers for different convolution layers of a ConvNet. However, SN uses softmax function to learn importance ratios to combine normalizers, leading to redundant computations compared to a single normalizer. This work addresses this issue by presenting Sparse Switchable Normalization (SSN) where the importance ratios are constrained to be sparse. Unlike $\ell_1$ and $\ell_0$ constraints that impose difficulties in optimization, we turn this constrained optimization problem into feed-forward computation by proposing SparsestMax, which is a sparse version of softmax. SSN has several appealing properties. (1) It inherits all benefits from SN such as applicability in various tasks and robustness to a wide range of batch sizes. (2) It is guaranteed to select only one normalizer for each normalization layer, avoiding redundant computations. (3) SSN can be transferred to various tasks in an end-to-end manner. Extensive experiments show that SSN outperforms its counterparts on various challenging benchmarks such as ImageNet, Cityscapes, ADE20K, and Kinetics. Code is available at \url{https://github.com/switchablenorms/Sparse_SwitchNorm}.

In this paper, we propose PointRCNN for 3D object detection from raw point cloud. The whole framework is composed of two stages: stage-1 for the bottom-up 3D proposal generation and stage-2 for refining proposals in the canonical coordinates to obtain the final detection results. Instead of generating proposals from RGB image or projecting point cloud to bird's view or voxels as previous methods do, our stage-1 sub-network directly generates a small number of high-quality 3D proposals from point cloud in a bottom-up manner via segmenting the point cloud of the whole scene into foreground points and background. The stage-2 sub-network transforms the pooled points of each proposal to canonical coordinates to learn better local spatial features, which is combined with global semantic features of each point learned in stage-1 for accurate box refinement and confidence prediction. Extensive experiments on the 3D detection benchmark of KITTI dataset show that our proposed architecture outperforms state-of-the-art methods with remarkable margins by using only point cloud as input. The code is available at https://github.com/sshaoshuai/PointRCNN.

Synthesizing photo-realistic images from text descriptions is a challenging problem. Previous studies have shown remarkable progresses on visual quality of the generated images. In this paper, we consider semantics from the input text descriptions in helping render photo-realistic images. However, diverse linguistic expressions pose challenges in extracting consistent semantics even they depict the same thing. To this end, we propose a novel photo-realistic text-to-image generation model that implicitly disentangles semantics to both fulfill the high-level semantic consistency and low-level semantic diversity. To be specific, we design (1) a Siamese mechanism in the discriminator to learn consistent high-level semantics, and (2) a visual-semantic embedding strategy by semantic-conditioned batch normalization to find diverse low-level semantics. Extensive experiments and ablation studies on CUB and MS-COCO datasets demonstrate the superiority of the proposed method in comparison to state-of-the-art methods.

Dense captioning aims at simultaneously localizing semantic regions and describing these regions-of-interest (ROIs) with short phrases or sentences in natural language. Previous studies have shown remarkable progresses, but they are often vulnerable to the aperture problem that a caption generated by the features inside one ROI lacks contextual coherence with its surrounding context in the input image. In this work, we investigate contextual reasoning based on multi-scale message propagations from the neighboring contents to the target ROIs. To this end, we design a novel end-to-end context and attribute grounded dense captioning framework consisting of 1) a contextual visual mining module and 2) a multi-level attribute grounded description generation module. Knowing that captions often co-occur with the linguistic attributes (such as who, what and where), we also incorporate an auxiliary supervision from hierarchical linguistic attributes to augment the distinctiveness of the learned captions. Extensive experiments and ablation studies on Visual Genome dataset demonstrate the superiority of the proposed model in comparison to state-of-the-art methods.

Cosine-based softmax losses significantly improve the performance of deep face recognition networks. However, these losses always include sensitive hyper-parameters which can make training process unstable, and it is very tricky to set suitable hyper parameters for a specific dataset. This paper addresses this challenge by directly designing the gradients for training in an adaptive manner. We first investigate and unify previous cosine softmax losses from the perspective of gradients. This unified view inspires us to propose a novel gradient called P2SGrad (Probability-to-Similarity Gradient), which leverages a cosine similarity instead of classification probability to control the gradients for updating neural network parameters. P2SGrad is adaptive and hyper-parameter free, which makes training process more efficient and faster. We evaluate our P2SGrad on three face recognition benchmarks, LFW, MegaFace, and IJB-C. The results show that P2SGrad is stable in training, robust to noise, and achieves state-of-the-art performance on all the three benchmarks.

The cosine-based softmax losses and their variants achieve great success in deep learning based face recognition. However, hyperparameter settings in these losses have significant influences on the optimization path as well as the final recognition performance. Manually tuning those hyperparameters heavily relies on user experience and requires many training tricks. In this paper, we investigate in depth the effects of two important hyperparameters of cosine-based softmax losses, the scale parameter and angular margin parameter, by analyzing how they modulate the predicted classification probability. Based on these analysis, we propose a novel cosine-based softmax loss, AdaCos, which is hyperparameter-free and leverages an adaptive scale parameter to automatically strengthen the training supervisions during the training process. We apply the proposed AdaCos loss to large-scale face verification and identification datasets, including LFW, MegaFace, and IJB-C 1:1 Verification. Our results show that training deep neural networks with the AdaCos loss is stable and able to achieve high face recognition accuracy. Our method outperforms state-of-the-art softmax losses on all the three datasets.

Exploiting relationships between visual regions and question words have achieved great success in learning multi-modality features for Visual Question Answering (VQA). However, we argue that existing methods mostly model relations between individual visual regions and words, which are not enough to correctly answer the question. From humans' perspective, answering a visual question requires understanding the summarizations of visual and language information. In this paper, we proposed the Multi-modality Latent Interaction module (MLI) to tackle this problem. The proposed module learns the cross-modality relationships between latent visual and language summarizations, which summarize visual regions and question into a small number of latent representations to avoid modeling uninformative individual region-word relations. The cross-modality information between the latent summarizations are propagated to fuse valuable information from both modalities and are used to update the visual and word features. Such MLI modules can be stacked for several stages to model complex and latent relations between the two modalities and achieves highly competitive performance on public VQA benchmarks, VQA v2.0 and TDIUC . In addition, we show that the performance of our methods could be significantly improved by combining with pre-trained language model BERT.

ConvNets achieve good results when training from clean data, but learning from noisy labels significantly degrades performances and remains challenging. Unlike previous works constrained by many conditions, making them infeasible to real noisy cases, this work presents a novel deep self-learning framework to train a robust network on the real noisy datasets without extra supervision. The proposed approach has several appealing benefits. (1) Different from most existing work, it does not rely on any assumption on the distribution of the noisy labels, making it robust to real noises. (2) It does not need extra clean supervision or accessorial network to help training. (3) A self-learning framework is proposed to train the network in an iterative end-to-end manner, which is effective and efficient. Extensive experiments in challenging benchmarks such as Clothing1M and Food101-N show that our approach outperforms its counterparts in all empirical settings.

Modern deep neural networks are often vulnerable to adversarial samples. Based on the first optimization-based attacking method, many following methods are proposed to improve the attacking performance and speed. Recently, generation-based methods have received much attention since they directly use feed-forward networks to generate the adversarial samples, which avoid the time-consuming iterative attacking procedure in optimization-based and gradient-based methods. However, current generation-based methods are only able to attack one specific target (category) within one model, thus making them not applicable to real classification systems that often have hundreds/thousands of categories. In this paper, we propose the first Multi-target Adversarial Network (MAN), which can generate multi-target adversarial samples with a single model. By incorporating the specified category information into the intermediate features, it can attack any category of the target classification model during runtime. Experiments show that the proposed MAN can produce stronger attack results and also have better transferability than previous state-of-the-art methods in both multi-target attack task and single-target attack task. We further use the adversarial samples generated by our MAN to improve the robustness of the classification model. It can also achieve better classification accuracy than other methods when attacked by various methods.

This paper proposes a differentiable kernel evolution (DKE) algorithm to find a better layer-operator for the convolutional neural network. Unlike most of the other neural architecture searching (NAS) technologies, we consider the searching space in a fundamental scope: kernel space, which encodes the assembly of basic multiplyaccumulate (MAC) operations into a conv-kernel. We first deduce a strict form of the generalized convolutional operator by some necessary constraints and construct a continuous searching space for its extra freedom-of-degree, namely, the connection of each MAC. Then a novel unsupervised greedy evolution algorithm called gradient agreement guided searching (GAGS) is proposed to learn the optimal location for each MAC in the spatially continuous searching space. We leverage DKE on multiple kinds of tasks such as object classification, face/object detection, large-scale finegrained and recognition, with various kinds of backbone architecture. Not to mention the consistent performance gain, we found the proposed DKE can further act as an autodilated operator, which makes it easy to boost the performance of miniaturized neural networks in multiple tasks.

Point cloud is an important type of 3D representation. However, directly applying convolutions on point clouds is challenging due to the sparse, irregular and unordered data structure. In this paper, we propose a novel Interpolated Convolution operation, InterpConv, to tackle the point cloud feature learning and understanding problem. The key idea is to utilize a set of discrete kernel weights and interpolate point features to neighboring kernel-weight coordinates by an interpolation function for convolution. A normalization term is introduced to handle neighborhoods of different sparsity levels. Our InterpConv is shown to be permutation and sparsity invariant, and can directly handle irregular inputs. We further design Interpolated Convolutional Neural Networks (InterpCNNs) based on InterpConv layers to handle point cloud recognition tasks including shape classification, object part segmentation and indoor scene semantic parsing. Experiments show that the networks can capture both fine-grained local structures and global shape context information effectively. The proposed approach achieves state-of-the-art performance on public benchmarks including ModelNet40, ShapeNet Parts and S3DIS.

In this paper we tackle the joint learning problem of keyframe detection and visual odometry towards monocular visual SLAM systems. As an important task in visual SLAM, keyframe selection helps efficient camera relocalization and effective augmentation of visual odometry. To benefit from it, we first present a deep network design for the keyframe selection, which is able to reliably detect keyframes and localize new frames, then an end-to-end unsupervised deep framework further proposed for simultaneously learning the keyframe selection and the visual odometry tasks. As far as we know, it is the first work to jointly optimize these two complementary tasks in a single deep framework. To make the two tasks facilitate each other in the learning, a collaborative optimization loss based on both geometric and visual metrics is proposed. Extensive experiments on publicly available datasets (i.e. KITTI raw dataset and its odometry split [12]) clearly demonstrate the effectiveness of the proposed approach, and new state-ofthe-art results are established on the unsupervised depth and pose estimation from monocular video.

Text-image cross-modal retrieval is a challenging task in the field of language and vision. Most previous approaches independently embed images and sentences into a joint embedding space and compare their similarities. However, previous approaches rarely explore the interactions between images and sentences before calculating similarities in the joint space. Intuitively, when matching between images and sentences, human beings would alternatively attend to regions in images and words in sentences, and select the most salient information considering the interaction between both modalities. In this paper, we propose Cross-modal Adaptive Message Passing (CAMP), which adaptively controls the information flow for message passing across modalities. Our approach not only takes comprehensive and fine-grained cross-modal interactions into account, but also properly handles negative pairs and irrelevant information with an adaptive gating scheme. Moreover, instead of conventional joint embedding approaches for text-image matching, we infer the matching score based on the fused features, and propose a hardest negative binary cross-entropy loss for training. Results on COCO and Flickr30k significantly surpass state-of-the-art methods, demonstrating the effectiveness of our approach.

Group convolution, which divides the channels of ConvNets into groups, has achieved impressive improvement over the regular convolution operation. However, existing models, \eg ResNext, still suffers from the sub-optimal performance due to manually defining the number of groups as a constant over all of the layers. Toward addressing this issue, we present Groupable ConvNet (GroupNet) built by using a novel dynamic grouping convolution (DGConv) operation, which is able to learn the number of groups in an end-to-end manner. The proposed approach has several appealing benefits. (1) DGConv provides a unified convolution representation and covers many existing convolution operations such as regular dense convolution, group convolution, and depthwise convolution. (2) DGConv is a differentiable and flexible operation which learns to perform various convolutions from training data. (3) GroupNet trained with DGConv learns different number of groups for different convolution layers. Extensive experiments demonstrate that GroupNet outperforms its counterparts such as ResNet and ResNeXt in terms of accuracy and computational complexity. We also present introspection and reproducibility study, for the first time, showing the learning dynamics of training group numbers.

Multi-modality perception is essential to develop interactive intelligence. In this work, we consider a new task of visual information-infused audio inpainting, i.e. synthesizing missing audio segments that correspond to their accompanying videos. We identify two key aspects for a successful inpainter: (1) It is desirable to operate on spectrograms instead of raw audios. Recent advances in deep semantic image inpainting could be leveraged to go beyond the limitations of traditional audio inpainting. (2) To synthesize visually indicated audio, a visual-audio joint feature space needs to be learned with synchronization of audio and video. To facilitate a large-scale study, we collect a new multi-modality instrument-playing dataset called MUSIC-Extra-Solo (MUSICES) by enriching MUSIC dataset [51]. Extensive experiments demonstrate that our framework is capable of inpainting realistic and varying audio segments with or without visual contexts. More importantly, our synthesized audio segments are coherent with their video counterparts, showing the effectiveness of our proposed Vision-Infused Audio Inpainter (VIAI). Code, models, dataset and video results are available at https://github.com/Hangz-nju-cuhk/ Vision-Infused-Audio-Inpainter-VIAI.

Despite some exciting progress on high-quality image generation from structured (scene graphs) or free-form (sentences) descriptions, most of them only guarantee the image-level semantical consistency, i.e. the generated image matching the semantic meaning of the description. They still lack the investigations on synthesizing the images in a more controllable way, like finely manipulating the visual appearance of every object. Therefore, to generate the images with preferred objects and rich interactions, we propose a semi-parametric method, PasteGAN, for generating the image from the scene graph and the image crops, where spatial arrangements of the objects and their pair-wise relationships are defined by the scene graph and the object appearances are determined by the given object crops. To enhance the interactions of the objects in the output, we design a Crop Refining Network and an Object-Image Fuser to embed the objects as well as their relationships into one map. Multiple losses work collaboratively to guarantee the generated images highly respecting the crops and complying with the scene graphs while maintaining excellent image quality. A crop selector is also proposed to pick the most-compatible crops from our external object tank by encoding the interactions around the objects in the scene graph if the crops are not provided. Evaluated on Visual Genome and COCO-Stuff dataset, our proposed method significantly outperforms the SOTA methods on Inception Score, Diversity Score and Fréchet Inception Distance. Extensive experiments also demonstrate our method’s ability to generate complex and diverse images with given objects. The code is available at https://github.com/yikang-li/PasteGAN.

Semantic image synthesis aims at generating photorealistic images from semantic layouts. Previous approaches with conditional generative adversarial networks (GAN) show state-of-the-art performance on this task, which either feed the semantic label maps as inputs to the generator, or use them to modulate the activations in normalization layers via affine transformations. We argue that convolutional kernels in the generator should be aware of the distinct semantic labels at different locations when generating images. In order to better exploit the semantic layout for the image generator, we propose to predict convolutional kernels conditioned on the semantic label map to generate the intermediate feature maps from the noise maps and eventually generate the images. Moreover, we propose a feature pyramid semantics-embedding discriminator, which is more effective in enhancing fine details and semantic alignments between the generated images and the input semantic layouts than previous multi-scale discriminators. We achieve state-of-the-art results on both quantitative metrics and subjective evaluation on various semantic segmentation datasets, demonstrating the effectiveness of our approach.

The papers in this special section examine compact and efficient feature representation and learning in computer vision.

Depth cues have been proved very useful in various computer vision and robotic tasks. This paper addresses the problem of monocular depth estimation from a single still image. Inspired by the effectiveness of recent works on multi-scale convolutional neural networks (CNN), we propose a deep model which fuses complementary information derived from multiple CNN side outputs. Different from previous methods using concatenation or weighted average schemes, the integration is obtained by means of continuous Conditional Random Fields (CRFs). In particular, we propose two different variations, one based on a cascade of multiple CRFs, the other on a unified graphical model. By designing a novel CNN implementation of mean-field updates for continuous CRFs, we show that both proposed models can be regarded as sequential deep networks and that training can be performed end-to-end. Through an extensive experimental evaluation, we demonstrate the effectiveness of the proposed approach and establish new state of the art results for the monocular depth estimation task on three publicly available datasets, i.e., NYUD-V2, Make3D and KITTI.

Although Generative Adversarial Networks (GANs) have shown remarkable success in various tasks, they still face challenges in generating high quality images. In this paper, we propose Stacked Generative Adversarial Networks (StackGANs) aimed at generating high-resolution photo-realistic images. First, we propose a two-stage generative adversarial network architecture, StackGAN-v1, for text-to-image synthesis. The Stage-I GAN sketches the primitive shape and colors of a scene based on a given text description, yielding low-resolution images. The Stage-II GAN takes Stage-I results and the text description as inputs, and generates high-resolution images with photo-realistic details. Second, an advanced multi-stage generative adversarial network architecture, StackGAN-v2, is proposed for both conditional and unconditional generative tasks. Our StackGAN-v2 consists of multiple generators and multiple discriminators arranged in a tree-like structure; images at multiple scales corresponding to the same scene are generated from different branches of the tree. StackGAN-v2 shows more stable training behavior than StackGAN-v1 by jointly approximating multiple distributions. Extensive experiments demonstrate that the proposed stacked generative adversarial networks significantly outperform other state-of-the-art methods in generating photo-realistic images.

Online multi-object tracking (MOT) is a challenging problem and has many important applications including intelligence surveillance, robot navigation, and autonomous driving. In existing MOT methods, individual object's movements and inter-object relations are mostly modeled separately and relations between them are still manually tuned. In addition, inter-object relations are mostly modeled in a symmetric way, which we argue is not an optimal setting. To tackle those difficulties, in this paper, we propose a deep continuous conditional random field (DCCRF) for solving the online MOT problem in a track-by-detection framework. The DCCRF consists of unary and pairwise terms. The unary terms estimate tracked objects' displacements across time based on visual appearance information. They are modeled as deep convolution neural networks, which are able to learn discriminative visual features for tracklet association. The asymmetric pairwise terms model inter-object relations in an asymmetric way, which encourages high-confidence tracklets to help correct errors of low-confidence tracklets and not to be affected by low-confidence ones much. The DCCRF is trained in an end-to-end manner for better adapting the influences of visual information as well as inter-object relations. Extensive experimental comparisons with state-of-the-arts as well as detailed component analysis of our proposed DCCRF on two public benchmarks demonstrate the effectiveness of our proposed MOT framework.

Video person re-identification has attracted much attention in recent years. It aims to match image sequences of pedestrians from different camera views. Previous approaches usually improve this task from three aspects, including: 1) selecting more discriminative frames; 2) generating more informative temporal representations; and 3) developing more effective distance metrics. To address the above issues, we present a novel and practical deep architecture for video person re-identification termed self-and-collaborative attention network (SCAN), which adopts the video pairs as the input and outputs their matching scores. SCAN has several appealing properties. First, SCAN adopts a non-parametric attention mechanism to refine the intra-sequence and inter-sequence feature representation of videos and outputs self-and-collaborative feature representation for each video, making the discriminative frames aligned between the probe and gallery sequences. Second, beyond the existing models, a generalized pairwise similarity measurement is proposed to generate the similarity feature representation of video pair by calculating the Hadamard product of their self-representation difference and collaborative-representation difference. Thus, the matching result can be predicted by the binary classifier. Third, a dense clip segmentation strategy is also introduced to generate rich probe-gallery pairs to optimize the model. In the test phase, the final matching score of two videos is determined by averaging the scores of top-ranked clip-pairs. Extensive experiments demonstrate the effectiveness of SCAN, which outperforms the top-1 accuracies of the best-performing baselines on iLIDS-VID, PRID2011, and MARS datasets, respectively.

Recently, the Visual Question Answering (VQA) task has gained increasing attention in artificial intelligence. Existing VQA methods mainly adopt the visual attention mechanism to associate the input question with corresponding image regions for effective question answering. The free-form region based and the detection-based visual attention mechanisms are mostly investigated, with the former ones attending free-form image regions and the latter ones attending pre-specified detection-box regions. We argue that the two attention mechanisms are able to provide complementary information and should be effectively integrated to better solve the VQA problem. In this paper, we propose a novel deep neural network for VQA that integrates both attention mechanisms. Our proposed framework effectively fuses features from free-form image regions, detection boxes, and question representations via a multi-modal multiplicative feature embedding scheme to jointly attend question-related free-form image regions and detection boxes for more accurate question answering. The proposed method is extensively evaluated on two publicly available datasets, COCO-QA and VQA, and outperforms state-of-the-art approaches. Source code is available at https://github.com/lupantech/dual-mfa-vqa.

Convolutional neural networks (CNNs) are usually built by stacking convolutional operations layer-by-layer. Although CNN has shown strong capability to extract semantics from raw pixels, its capacity to capture spatial relationships of pixels across rows and columns of an image is not fully explored. These relationships are important to learn semantic objects with strong shape priors but weak appearance coherences, such as traffic lanes, which are often occluded or not even painted on the road surface as shown in Fig. 1 (a). In this paper, we propose Spatial CNN (SCNN), which generalizes traditional deep layer-by-layer convolutions to slice-by-slice convolutions within feature maps, thus enabling message passings between pixels across rows and columns in a layer. Such SCNN is particular suitable for long continuous shape structure or large objects, with strong spatial relationship but less appearance clues, such as traffic lanes, poles, and wall. We apply SCNN on a newly released very challenging traffic lane detection dataset and Cityscapse dataset. The results show that SCNN could learn the spatial relationship for structure output and significantly improves the performance. We show that SCNN outperforms the recurrent neural network (RNN) based ReNet and MRF+CNN (MRFNet) in the lane detection dataset by 8.7% and 4.6% respectively. Moreover, our SCNN won the 1st place on the TuSimple Benchmark Lane Detection Challenge, with an accuracy of 96.53%.

Depth estimation and scene parsing are two particularly important tasks in visual scene understanding. In this paper we tackle the problem of simultaneous depth estimation and scene parsing in a joint CNN. The task can be typically treated as a deep multi-task learning problem [42]. Different from previous methods directly optimizing multiple tasks given the input training data, this paper proposes a novel multi-task guided prediction-and-distillation network (PAD-Net), which first predicts a set of intermediate auxiliary tasks ranging from low level to high level, and then the predictions from these intermediate auxiliary tasks are utilized as multi-modal input via our proposed multi-modal distillation modules for the final tasks. During the joint learning, the intermediate tasks not only act as supervision for learning more robust deep representations but also provide rich multi-modal information for improving the final tasks. Extensive experiments are conducted on two challenging datasets (i.e. NYUD-v2 and Cityscapes) for both the depth estimation and scene parsing tasks, demonstrating the effectiveness of the proposed approach.

Recent work has made significant progress in improving spatial resolution for pixelwise labeling with Fully Convolutional Network (FCN) framework by employing Dilated/Atrous convolution, utilizing multi-scale features and refining boundaries. In this paper, we explore the impact of global contextual information in semantic segmentation by introducing the Context Encoding Module, which captures the semantic context of scenes and selectively highlights class-dependent featuremaps. The proposed Context Encoding Module significantly improves semantic segmentation results with only marginal extra computation cost over FCN. Our approach has achieved new state-of-the-art results 51.7% mIoU on PASCAL-Context, 85.9% mIoU on PASCAL VOC 2012. Our single model achieves a final score of 0.5567 on ADE20K test set, which surpasses the winning entry of COCO-Place Challenge 2017. In addition, we also explore how the Context Encoding Module can improve the feature representation of relatively shallow networks for the image classification on CIFAR-10 dataset. Our 14 layer network has achieved an error rate of 3.45%, which is comparable with state-of-the-art approaches with over 10Ã- more layers. The source code for the complete system are publicly available1.

This paper proposes learning disentangled but complementary face features with a minimal supervision by face identification. Specifically, we construct an identity Distilling and Dispelling Autoencoder (D2AE) framework that adversarially learns the identity-distilled features for identity verification and the identity-dispelled features to fool the verification system. Thanks to the design of two-stream cues, the learned disentangled features represent not only the identity or attribute but the complete input image. Comprehensive evaluations further demonstrate that the proposed features not only preserve state-of-the-art identity verification performance on LFW, but also acquire comparable discriminative power for face attribute recognition on CelebA and LFWA. Moreover, the proposed system is ready to semantically control the face generation/editing based on various identities and attributes in an unsupervised manner.

Person re-identification benefits greatly from deep neural networks (DNN) to learn accurate similarity metrics and robust feature embeddings. However, most of the current methods impose only local constraints for similarity learning. In this paper, we incorporate constraints on large image groups by combining the CRF with deep neural networks. The proposed method aims to learn the "local similarity" metrics for image pairs while taking into account the dependencies from all the images in a group, forming "group similarities". Our method involves multiple images to model the relationships among the local and global similarities in a unified CRF during training, while combines multi-scale local similarities as the predicted similarity in testing. We adopt an approximate inference scheme for estimating the group similarity, enabling end-to-end training. Extensive experiments demonstrate the effectiveness of our model that combines DNN and CRF for learning robust multi-scale local similarities. The overall results outperform those by state-of-the-arts with considerable margins on three widely-used benchmarks.

In this paper, we address video-based person re-identification with competitive snippet-similarity aggregation and co-attentive snippet embedding. Our approach divides long person sequences into multiple short video snippets and aggregates the top-ranked snippet similarities for sequence-similarity estimation. With this strategy, the intra-person visual variation of each sample could be minimized for similarity estimation, while the diverse appearance and temporal information are maintained. The snippet similarities are estimated by a deep neural network with a novel temporal co-attention for snippet embedding. The attention weights are obtained based on a query feature, which is learned from the whole probe snippet by an LSTM network, making the resulting embeddings less affected by noisy frames. The gallery snippet shares the same query feature with the probe snippet. Thus the embedding of gallery snippet can present more relevant features to compare with the probe snippet, yielding more accurate snippet similarity. Extensive ablation studies verify the effectiveness of competitive snippet-similarity aggregation as well as the temporal co-attentive embedding. Our method significantly outperforms the current state-of-the-art approaches on multiple datasets.

Video-based person re-identification matches video clips of people across non-overlapping cameras. Most existing methods tackle this problem by encoding each video frame in its entirety and computing an aggregate representation across all frames. In practice, people are often partially occluded, which can corrupt the extracted features. Instead, we propose a new spatiotemporal attention model that automatically discovers a diverse set of distinctive body parts. This allows useful information to be extracted from all frames without succumbing to occlusions and misalignments. The network learns multiple spatial attention models and employs a diversity regularization term to ensure multiple models do not discover the same body part. Features extracted from local image regions are organized by spatial attention model and are combined using temporal attention. As a result, the network learns latent representations of the face, torso and other body parts using the best available image patches from the entire video sequence. Extensive evaluations on three datasets show that our framework outperforms the state-of-the-art approaches by large margins on multiple metrics.

Visual question answering (VQA) and visual question generation (VQG) are two trending topics in the computer vision, but they are usually explored separately despite their intrinsic complementary relationship. In this paper, we propose an end-to-end unified model, the Invertible Question Answering Network (iQAN), to introduce question generation as a dual task of question answering to improve the VQA performance. With our proposed invertible bilinear fusion module and parameter sharing scheme, our iQAN can accomplish VQA and its dual task VQG simultaneously. By jointly trained on two tasks with our proposed dual regularizes (termed as Dual Training), our model has a better understanding of the interactions among images, questions and answers. After training, iQAN can take either question or answer as input, and output the counterpart. Evaluated on the CLEVR and VQA2 datasets, our iQAN improves the top-1 accuracy of the prior art MUTAN VQA method by 1.33% and 0.88% (absolute increase) respectiely. We also show that our proposed dual training framework can consistently improve model performances of many popular VQA architectures1.

Face synthesis has achieved advanced development by using generative adversarial networks (GANs). Existing methods typically formulate GAN as a two-player game, where a discriminator distinguishes face images from the real and synthesized domains, while a generator reduces its discriminativeness by synthesizing a face of photorealistic quality. Their competition converges when the discriminator is unable to differentiate these two domains. Unlike two-player GANs, this work generates identity-preserving faces by proposing FaceID-GAN, which treats a classifier of face identity as the third player, competing with the generator by distinguishing the identities of the real and synthesized faces (see Fig.1). A stationary point is reached when the generator produces faces that have high quality as well as preserve identity. Instead of simply modeling the identity classifier as an additional discriminator, FaceID-GAN is formulated by satisfying information symmetry, which ensures that the real and synthesized images are projected into the same feature space. In other words, the identity classifier is used to extract identity features from both input (real) and output (synthesized) face images of the generator, substantially alleviating training difficulty of GAN. Extensive experiments show that FaceID-GAN is able to generate faces of arbitrary viewpoint while preserve identity, outperforming recent advanced approaches.

Person re-identification aims at finding a person of interest in an image gallery by comparing the probe image of this person with all the gallery images. It is generally treated as a retrieval problem, where the affinities between the probe image and gallery images (P2G affinities) are used to rank the retrieved gallery images. However, most existing methods only consider P2G affinities but ignore the affinities between all the gallery images (G2G affinity). Some frameworks incorporated G2G affinities into the testing process, which is not end-to-end trainable for deep neural networks. In this paper, we propose a novel group-shuffling random walk network for fully utilizing the affinity information between gallery images in both the training and testing processes. The proposed approach aims at end-to-end refining the P2G affinities based on G2G affinity information with a simple yet effective matrix operation, which can be integrated into deep neural networks. Feature grouping and group shuffle are also proposed to apply rich supervisions for learning better person features. The proposed approach outperforms state-of-the-art methods on the Market-1501, CUHK03, and DukeMTMC datasets by large margins, which demonstrate the effectiveness of our approach.

Person re-identification aims to robustly measure similarities between person images. The significant variation of person poses and viewing angles challenges for accurate person re-identification. The spatial layout and correspondences between query person images are vital information for tackling this problem but are ignored by most state-of-the-art methods. In this paper, we propose a novel Kronecker Product Matching module to match feature maps of different persons in an end-to-end trainable deep neural network. A novel feature soft warping scheme is designed for aligning the feature maps based on matching results, which is shown to be crucial for achieving superior accuracy. The multi-scale features based on hourglass-like networks and self residual attention are also exploited to further boost the re-identification performance. The proposed approach outperforms state-of-the-art methods on the Market-1501, CUHK03, and DukeMTMC datasets, which demonstrates the effectiveness and generalization ability of our proposed approach.

Zero-shot artistic style transfer is an important image synthesis problem aiming at transferring arbitrary style into content images. However, the trade-off between the generalization and efficiency in existing methods impedes a high quality zero-shot style transfer in real-time. In this paper, we resolve this dilemma and propose an efficient yet effective Avatar-Net that enables visually plausible multi-scale transfer for arbitrary style. The key ingredient of our method is a style decorator that makes up the content features by semantically aligned style features from an arbitrary style image, which does not only holistically match their feature distributions but also preserve detailed style patterns in the decorated features. By embedding this module into an image reconstruction network that fuses multi-scale style abstractions, the Avatar-Net renders multi-scale stylization for any style image in one feed-forward pass. We demonstrate the state-of-the-art effectiveness and efficiency of the proposed method in generating high-quality stylized images, with a series of successive applications include multiple style integration, video stylization and etc.

Person re-identification is an important topic in intelligent surveillance and computer vision. It aims to accurately measure visual similarities between person images for determining whether two images correspond to the same person. State-of-the-art methods mainly utilize deep learning based approaches for learning visual features for describing person appearances. However, we observe that existing deep learning models are biased to capture too much relevance between background appearances of person images. We design a series of experiments with newly created datasets to validate the influence of background information. To solve the background bias problem, we propose a person-region guided pooling deep neural network based on human parsing maps to learn more discriminative person-part features, and propose to augment training data with person images with random background. Extensive experiments demonstrate the robustness and effectiveness of our proposed method.

Recently, remarkable advances have been achieved in 3D human pose estimation from monocular images because of the powerful Deep Convolutional Neural Networks (DCNNs). Despite their success on large-scale datasets collected in the constrained lab environment, it is difficult to obtain the 3D pose annotations for in-the-wild images. Therefore, 3D human pose estimation in the wild is still a challenge. In this paper, we propose an adversarial learning framework, which distills the 3D human pose structures learned from the fully annotated dataset to in-the-wild images with only 2D pose annotations. Instead of defining hard-coded rules to constrain the pose estimation results, we design a novel multi-source discriminator to distinguish the predicted 3D poses from the ground-truth, which helps to enforce the pose estimator to generate anthropometrically valid poses even with images in the wild. We also observe that a carefully designed information source for the discriminator is essential to boost the performance. Thus, we design a geometric descriptor, which computes the pairwise relative locations and distances between body joints, as a new information source for the discriminator. The efficacy of our adversarial learning framework with the new geometric descriptor has been demonstrated through extensive experiments on widely used public benchmarks. Our approach significantly improves the performance compared with previous state-of-the-art approaches.

Person re-identification (reID) is an important task that requires to retrieve a person's images from an image dataset, given one image of the person of interest. For learning robust person features, the pose variation of person images is one of the key challenges. Existing works targeting the problem either perform human alignment, or learn human-region-based representations. Extra pose information and computational cost is generally required for inference. To solve this issue, a Feature Distilling Generative Adversarial Network (FD-GAN) is proposed for learning identity-related and pose-unrelated representations. It is a novel framework based on a Siamese structure with multiple novel discriminators on human poses and identities. In addition to the discriminators, a novel same-pose loss is also integrated, which requires appearance of a same person's generated images to be similar. After learning pose-unrelated person features with pose guidance, no auxiliary pose information and additional computational cost is required during testing. Our proposed FD-GAN achieves state-of-the-art performance on three person reID datasets, which demonstrates that the effectiveness and robust feature distilling capability of the proposed FD-GAN.

Feature extraction, deformation handling, occlusion handling, and classification are four important components in pedestrian detection. Existing methods learn or design these components either individually or sequentially. The interaction among these components is not yet well explored. This paper proposes that they should be jointly learned in order to maximize their strengths through cooperation. We formulate these four components into a joint deep learning framework and propose a new deep network architecture (Code available on www.ee.cuhk.edu.hk/wlouyang/projects/ouyangWiccv13Joint/index.html). By establishing automatic, mutual interaction among components, the deep model has average miss rate 8.57 percent/11.71 percent on the Caltech benchmark dataset with new/original annotations.

The visual cues from multiple support regions of different sizes and resolutions are complementary in classifying a candidate box in object detection. Effective integration of local and contextual visual cues from these regions has become a fundamental problem in object detection. In this paper, we propose a gated bi-directional CNN (GBD-Net) to pass messages among features from different support regions during both feature learning and feature extraction. Such message passing can be implemented through convolution between neighboring support regions in two directions and can be conducted in various layers. Therefore, local and contextual visual patterns can validate the existence of each other by learning their nonlinear relationships and their close interactions are modeled in a more complex way. It is also shown that message passing is not always helpful but dependent on individual samples. Gated functions are therefore needed to control message transmission, whose on-or-offs are controlled by extra visual evidence from the input sample. The effectiveness of GBD-Net is shown through experiments on three object detection datasets, ImageNet, Pascal VOC2007 and Microsoft COCO. Besides the GBD-Net, this paper also shows the details of our approach in winning the ImageNet object detection challenge of 2016, with source code provided on https://github.com/craftGBD/craftGBD. In this winning system, the modified GBD-Net, new pretraining scheme and better region proposal designs are provided. We also show the effectiveness of different network structures and existing techniques for object detection, such as multi-scale testing, left-right flip, bounding box voting, NMS, and context.

The state-of-the-art performance for object detection has been significantly improved over the past two years. Besides the introduction of powerful deep neural networks, such as GoogleNet and VGG, novel object detection frameworks, such as R-CNN and its successors, Fast R-CNN, and Faster R-CNN, play an essential role in improving the state of the art. Despite their effectiveness on still images, those frameworks are not specifically designed for object detection from videos. Temporal and contextual information of videos are not fully investigated and utilized. In this paper, we propose a deep learning framework that incorporates temporal and contextual information from tubelets obtained in videos, which dramatically improves the baseline performance of existing still-image detection frameworks when they are applied to videos. It is called T-CNN, i.e., tubelets with convolutional neueral networks. The proposed framework won newly introduced an object-detection-from-video task with provided data in the ImageNet Large-Scale Visual Recognition Challenge 2015. Code is publicly available athttps://github.com/myfavouritekk/T-CNN.

We propose a new model-free approach for crowd tracking that integrates low-level keypoint tracking, midlevel patch tracking, and high-level group evolution in one unified framework. Instead of computing optical flows, tracking keypoints, or pedestrians, we propose to represent the crowd as a set of distinctive and stable midlevel patches. These patches are tracked together through occlusions, background clutter, and appearance variations, with spatial relations modeled by the proposed hierarchical tree structure. In the low level, keypoint tracking provides accurate local motions, which guides the detection of midlevel patches with stable internal motions, and also organizes patches into hierarchical groups with collective motions. In the high level, group evolution guides updating of the proposed hierarchical tree structure through merge and split events. The dynamically structured patches not only substantially improve their own tracking, but also act as assistant patches that can help track given targets more accurately in a crowd. Extensive experiments on both ours and publicly available data sets show that our proposed approach significantly outperforms current state-of-the-art trackers.

This paper focuses on the connecting structure of deep neural networks and proposes a layerwise structure learning method based on multiobjective optimization. A model with better generalization can be obtained by reducing the connecting parameters in deep networks. The aim is to find the optimal structure with high representation ability and better generalization for each layer. Then, the visible data are modeled with respect to structure based on the products of experts. In order to mitigate the difficulty of estimating the denominator in PoE, the denominator is simplified and taken as another objective, i.e., the connecting sparsity. Moreover, for the consideration of the contradictory nature between the representation ability and the network connecting sparsity, the multiobjective model is established. An improved multiobjective evolutionary algorithm is used to solve this model. Two tricks are designed to decrease the computational cost according to the properties of input data. The experiments on single-layer level, hierarchical level, and application level demonstrate the effectiveness of the proposed algorithm, and the learned structures can improve the performance of deep neural networks.

In this paper, we propose to incorporate convolutional neural networks with a multi-context attention mechanism into an end-to-end framework for human pose estimation. We adopt stacked hourglass networks to generate attention maps from features at multiple resolutions with various semantics. The Conditional Random Field (CRF) is utilized to model the correlations among neighboring regions in the attention map. We further combine the holistic attention model, which focuses on the global consistency of the full human body, and the body part attention model, which focuses on detailed descriptions for different body parts. Hence our model has the ability to focus on different granularity from local salient regions to global semantic consistent spaces. Additionally, we design novel Hourglass Residual Units (HRUs) to increase the receptive field of the network. These units are extensions of residual units with a side branch incorporating filters with larger receptive field, hence features with various scales are learned and combined within the HRUs. The effectiveness of the proposed multi-context attention mechanism and the hourglass residual units is evaluated on two widely used human pose estimation benchmarks. Our approach outperforms all existing methods on both benchmarks over all the body parts. Code has been made publicly available.

Object detection in videos has drawn increasing attention recently with the introduction of the large-scale ImageNet VID dataset. Different from object detection in static images, temporal information in videos is vital for object detection. To fully utilize temporal information, state-of-the-art methods [15, 14] are based on spatiotemporal tubelets, which are essentially sequences of associated bounding boxes across time. However, the existing methods have major limitations in generating tubelets in terms of quality and efficiency. Motion-based [14] methods are able to obtain dense tubelets efficiently, but the lengths are generally only several frames, which is not optimal for incorporating long-term temporal information. Appearance-based [15] methods, usually involving generic object tracking, could generate long tubelets, but are usually computationally expensive. In this work, we propose a framework for object detection in videos, which consists of a novel tubelet proposal network to efficiently generate spatiotemporal proposals, and a Long Short-term Memory (LSTM) network that incorporates temporal information from tubelet proposals for achieving high object detection accuracy in videos. Experiments on the large-scale ImageNet VID dataset demonstrate the effectiveness of the proposed framework for object detection in videos.

As the intermediate level task connecting image captioning and object detection, visual relationship detection started to catch researchers attention because of its descriptive power and clear structure. It detects the objects and captures their pair-wise interactions with a subject-predicate-object triplet, e.g. person-ride-horse. In this paper, each visual relationship is considered as a phrase with three components. We formulate the visual relationship detection as three inter-connected recognition problems and propose a Visual Phrase guided Convolutional Neural Network (ViP-CNN) to address them simultaneously. In ViP-CNN, we present a Phrase-guided Message Passing Structure (PMPS) to establish the connection among relationship components and help the model consider the three problems jointly. Corresponding non-maximum suppression method and model training strategy are also proposed. Experimental results show that our ViP-CNN outperforms the state-of-art method both in speed and accuracy. We further pretrain ViP-CNN on our cleansed Visual Genome Relationship dataset, which is found to perform better than the pretraining on the ImageNet for this task.

Searching persons in large-scale image databases with the query of natural language description has important applications in video surveillance. Existing methods mainly focused on searching persons with image-based or attribute-based queries, which have major limitations for a practical usage. In this paper, we study the problem of person search with natural language description. Given the textual description of a person, the algorithm of the person search is required to rank all the samples in the person database then retrieve the most relevant sample corresponding to the queried description. Since there is no person dataset or benchmark with textual description available, we collect a large-scale person description dataset with detailed natural language annotations and person samples from various sources, termed as CUHK Person Description Dataset (CUHK-PEDES). A wide range of possible models and baselines have been evaluated and compared on the person search benchmark. An Recurrent Neural Network with Gated Neural Attention mechanism (GNA-RNN) is proposed to establish the state-of-the art performance on person search.

In this work, we propose Residual Attention Network, a convolutional neural network using attention mechanism which can incorporate with state-of-art feed forward network architecture in an end-to-end training fashion. Our Residual Attention Network is built by stacking Attention Modules which generate attention-aware features. The attention-aware features from different modules change adaptively as layers going deeper. Inside each Attention Module, bottom-up top-down feedforward structure is used to unfold the feedforward and feedback attention process into a single feedforward process. Importantly, we propose attention residual learning to train very deep Residual Attention Networks which can be easily scaled up to hundreds of layers. Extensive analyses are conducted on CIFAR-10 and CIFAR-100 datasets to verify the effectiveness of every module mentioned above. Our Residual Attention Network achieves state-of-the-art object recognition performance on three benchmark datasets including CIFAR-10 (3.90% error), CIFAR-100 (20.45% error) and ImageNet (4.8% single model and single crop, top-5 error). Note that, our method achieves 0.6% top-1 accuracy improvement with 46% trunk depth and 69% forward FLOPs comparing to ResNet-200. The experiment also demonstrates that our network is robust against noisy labels.

Recent advanced deep convolutional networks (CNNs) achieved great successes in many computer vision tasks, because of their compelling learning complexity and the presences of large-scale labeled data. However, as obtaining per-pixel annotations is expensive, performances of CNNs in semantic image segmentation are not fully exploited. This work significantly increases segmentation accuracy of CNNs by learning from an Image Descriptions in the Wild (IDW) dataset. Unlike previous image captioning datasets, where captions were manually and densely annotated, images and their descriptions in IDW are automatically downloaded from Internet without any manual cleaning and refinement. An IDW-CNN is proposed to jointly train IDW and existing image segmentation dataset such as Pascal VOC 2012 (VOC). It has two appealing properties. First, knowledge from different datasets can be fully explored and transferred from each other to improve performance. Second, segmentation accuracy in VOC can be constantly increased when selecting more data from IDW. Extensive experiments demonstrate the effectiveness and scalability of IDW-CNN, which outperforms existing best-performing system by 12% on VOC12 test set.

Existing person re-identification benchmarks and methods mainly focus on matching cropped pedestrian images between queries and candidates. However, it is different from real-world scenarios where the annotations of pedestrian bounding boxes are unavailable and the target person needs to be searched from a gallery of whole scene images. To close the gap, we propose a new deep learning framework for person search. Instead of breaking it down into two separate tasks-pedestrian detection and person re-identification, we jointly handle both aspects in a single convolutional neural network. An Online Instance Matching (OIM) loss function is proposed to train the network effectively, which is scalable to datasets with numerous identities. To validate our approach, we collect and annotate a large-scale benchmark dataset for person search. It contains 18,184 images, 8,432 identities, and 96,143 pedestrian bounding boxes. Experiments show that our framework outperforms other separate approaches, and the proposed OIM loss function converges much faster and better than the conventional Softmax loss.

This paper addresses the problem of depth estimation from a single still image. Inspired by recent works on multi-scale convolutional neural networks (CNN), we propose a deep model which fuses complementary information derived from multiple CNN side outputs. Different from previous methods, the integration is obtained by means of continuous Conditional Random Fields (CRFs). In particular, we propose two different variations, one based on a cascade of multiple CRFs, the other on a unified graphical model. By designing a novel CNN implementation of mean-field updates for continuous CRFs, we show that both proposed models can be regarded as sequential deep networks and that training can be performed end-to-end. Through extensive experimental evaluation we demonstrate the effectiveness of the proposed approach and establish new state of the art results on publicly available datasets.

Scene parsing is challenging for unrestricted open vocabulary and diverse scenes. In this paper, we exploit the capability of global context information by different-region-based context aggregation through our pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet). Our global prior representation is effective to produce good quality results on the scene parsing task, while PSPNet provides a superior framework for pixel-level prediction. The proposed approach achieves state-of-the-art performance on various datasets. It came first in ImageNet scene parsing challenge 2016, PASCAL VOC 2012 benchmark and Cityscapes benchmark. A single PSPNet yields the new record of mIoU accuracy 85.4% on PASCAL VOC 2012 and accuracy 80.2% on Cityscapes.

Person re-identification (ReID) is an important task in video surveillance and has various applications. It is non-trivial due to complex background clutters, varying illumination conditions, and uncontrollable camera settings. Moreover, the person body misalignment caused by detectors or pose variations is sometimes too severe for feature matching across images. In this study, we propose a novel Convolutional Neural Network (CNN), called Spindle Net, based on human body region guided multi-stage feature decomposition and tree-structured competitive feature fusion. It is the first time human body structure information is considered in a CNN framework to facilitate feature learning. The proposed Spindle Net brings unique advantages: 1) it separately captures semantic features from different body regions thus the macro-and micro-body features can be well aligned across images, 2) the learned region features from different semantic regions are merged with a competitive scheme and discriminative features can be well preserved. State of the art performance can be achieved on multiple datasets by large margins. We further demonstrate the robustness and effectiveness of the proposed Spindle Net on our proposed dataset SenseReID without fine-tuning.

Multi-label image classification is a fundamental but challenging task in computer vision. Great progress has been achieved by exploiting semantic relations between labels in recent years. However, conventional approaches are unable to model the underlying spatial relations between labels in multi-label images, because spatial annotations of the labels are generally not provided. In this paper, we propose a unified deep neural network that exploits both semantic and spatial relations between labels with only image-level supervisions. Given a multi-label image, our proposed Spatial Regularization Network (SRN) generates attention maps for all labels and captures the underlying relations between them via learnable convolutions. By aggregating the regularized classification results with original results by a ResNet-101 network, the classification performance can be consistently improved. The whole deep neural network is trained end-to-end with only image-level annotations, thus requires no additional efforts on image annotations. Extensive evaluations on 3 public datasets with different types of labels show that our approach significantly outperforms state-of-the-arts and has strong generalization capability. Analysis of the learned SRN model demonstrates that it can effectively capture both semantic and spatial relations of labels for improving classification performance.

In this paper, we propose a CNN-based framework for online MOT. This framework utilizes the merits of single object trackers in adapting appearance models and searching for target in the next frame. Simply applying single object tracker for MOT will encounter the problem in computational efficiency and drifted results caused by occlusion. Our framework achieves computational efficiency by sharing features and using ROI-Pooling to obtain individual features for each target. Some online learned target-specific CNN layers are used for adapting the appearance model for each target. In the framework, we introduce spatial-temporal attention mechanism (STAM) to handle the drift caused by occlusion and interaction among targets. The visibility map of the target is learned and used for inferring the spatial attention map. The spatial attention map is then applied to weight the features. Besides, the occlusion status can be estimated from the visibility map, which controls the online updating process via weighted loss on training samples with different occlusion statuses in different frames. It can be considered as temporal attention mechanism. The proposed algorithm achieves 34.3% and 46.0% in MOTA on challenging MOT15 and MOT16 benchmark dataset respectively.

Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise relationship predicted, while region captioning gives a language description of the objects, their attributes, relations and other context information. In this work, to leverage the mutual connections across semantic levels, we propose a novel neural network model, termed as Multi-level Scene Description Network (denoted as MSDN), to solve the three vision tasks jointly in an end-to-end manner. Object, phrase, and caption regions are first aligned with a dynamic graph based on their spatial and semantic connections. Then a feature refining structure is used to pass messages across the three levels of semantic tasks through the graph. We benchmark the learned model on three tasks, and show the joint learning across three tasks with our proposed method can bring mutual improvements over previous models. Particularly, on the scene graph generation task, our proposed method outperforms the stateof- art method with more than 3% margin. Code has been made publicly available.

Textual-visual matching aims at measuring similarities between sentence descriptions and images. Most existing methods tackle this problem without effectively utilizing identity-level annotations. In this paper, we propose an identity-aware two-stage framework for the textual-visual matching problem. Our stage-1 CNN-LSTM network learns to embed cross-modal features with a novel Cross-Modal Cross-Entropy (CMCE) loss. The stage-1 network is able to efficiently screen easy incorrect matchings and also provide initial training point for the stage-2 training. The stage-2 CNN-LSTM network refines the matching results with a latent co-attention mechanism. The spatial attention relates each word with corresponding image regions while the latent semantic attention aligns different sentence structures to make the matching results more robust to sentence structure variations. Extensive experiments on three datasets with identity-level annotations show that our framework outperforms state-of-the-art approaches by large margins.

Since convolutional neural network (CNN) lacks an inherent mechanism to handle large scale variations, we always need to compute feature maps multiple times for multiscale object detection, which has the bottleneck of computational cost in practice. To address this, we devise a recurrent scale approximation (RSA) to compute feature map once only, and only through this map can we approximate the rest maps on other levels. At the core of RSA is the recursive rolling out mechanism: given an initial map on a particular scale, it generates the prediction on a smaller scale that is half the size of input. To further increase efficiency and accuracy, we (a): design a scale-forecast network to globally predict potential scales in the image since there is no need to compute maps on all levels of the pyramid. (b): propose a landmark retracing network (LRN) to retrace back locations of the regressed landmarks and generate a confidence score for each landmark; LRN can effectively alleviate false positives due to the accumulated error in RSA. The whole system could be trained end-to-end in a unified CNN framework. Experiments demonstrate that our proposed algorithm is superior against state-of-the-arts on face detection benchmarks and achieves comparable results for generic proposal generation. The source code of our system is available.

Pedestrian analysis plays a vital role in intelligent video surveillance and is a key component for security-centric computer vision systems. Despite that the convolutional neural networks are remarkable in learning discriminative features from images, the learning of comprehensive features of pedestrians for fine-grained tasks remains an open problem. In this study, we propose a new attentionbased deep neural network, named as HydraPlus-Net (HPnet), that multi-directionally feeds the multi-level attention maps to different feature layers. The attentive deep features learned from the proposed HP-net bring unique advantages: (1) the model is capable of capturing multiple attentions from low-level to semantic-level, and (2) it explores the multi-scale selectiveness of attentive features to enrich the final feature representations for a pedestrian image. We demonstrate the effectiveness and generality of the proposed HP-net for pedestrian analysis on two tasks, i.e. pedestrian attribute recognition and person reidentification. Intensive experimental results have been provided to prove that the HP-net outperforms the state-of-theart methods on various datasets.

Deep neural networks have advanced many computer vision tasks, because of their compelling capacities to learn from large amount of labeled data. However, their performances are not fully exploited in semantic image segmentation as the scale of training set is limited, where per-pixel labelmaps are expensive to obtain. To reduce labeling efforts, a natural solution is to collect additional images from Internet that are associated with image-level tags. Unlike existing works that treated labelmaps and tags as independent supervisions, we present a novel learning setting, namely dual image segmentation (DIS), which consists of two complementary learning problems that are jointly solved. One predicts labelmaps and tags from images, and the other reconstructs the images using the predicted labelmaps. DIS has three appealing properties. 1) Given an image with tags only, its labelmap can be inferred by leveraging the images and tags as constraints. The estimated labelmaps that capture accurate object classes and boundaries are used as ground truths in training to boost performance. 2) DIS is able to clean tags that have noises. 3) DIS significantly reduces the number of per-pixel annotations in training, while still achieves state-of-the-art performance. Extensive experiments demonstrate the effectiveness of DIS, which outperforms an existing best-performing baseline by 12.6% on Pascal VOC 2012 test set, without any post-processing such as CRF/MRF smoothing.

Cascade is a widely used approach that rejects obvious negative samples at early stages for learning better classifier and faster inference. This paper presents chained cascade network (CC-Net). In this CC-Net, there are many cascade stages. Preceding cascade stages are placed at shallow layers. Easy hard examples are rejected at shallow layers so that the computation for deeper or wider layers is not required. In this way, features and classifiers at latter stages handle more difficult samples with the help of features and classifiers in previous stages. It yields consistent boost in detection performance on PASCAL VOC 2007 and ImageNet for both fast RCNN and Faster RCNN. CC-Net saves computation for both training and testing. Code is available on https://github.com/wk910930/ccnn.

Vehicle re-identification is an important problem and has many applications in video surveillance and intelligent transportation. It gains increasing attention because of the recent advances of person re-identification techniques. However, unlike person re-identification, the visual differences between pairs of vehicle images are usually subtle and even challenging for humans to distinguish. Incorporating additional spatio-temporal information is vital for solving the challenging re-identification task. Existing vehicle re-identification methods ignored or used oversimplified models for the spatio-temporal relations between vehicle images. In this paper, we propose a two-stage framework that incorporates complex spatio-temporal information for effectively regularizing the re-identification results. Given a pair of vehicle images with their spatiotemporal information, a candidate visual-spatio-temporal path is first generated by a chain MRF model with a deeply learned potential function, where each visual-spatiotemporal state corresponds to an actual vehicle image with its spatio-temporal information. A Siamese-CNN+Path- LSTM model takes the candidate path as well as the pairwise queries to generate their similarity score. Extensive experiments and analysis show the effectiveness of our proposed method and individual components.

In this paper, we tackle the vehicle Re-identification (ReID) problem which is of great importance in urban surveillance and can be used for multiple applications. In our vehicle ReID framework, an orientation invariant feature embedding module and a spatial-temporal regularization module are proposed. With orientation invariant feature embedding, local region features of different orientations can be extracted based on 20 key point locations and can be well aligned and combined. With spatial-temporal regularization, the log-normal distribution is adopted to model the spatial-temporal constraints and the retrieval results can be refined. Experiments are conducted on public vehicle ReID datasets and our proposed method achieves state-of-the-art performance. Investigations of the proposed framework is conducted, including the landmark regressor and comparisons with attention mechanism. Both the orientation invariant feature embedding and the spatio-temporal regularization achieve considerable improvements.

Articulated human pose estimation is a fundamental yet challenging task in computer vision. The difficulty is particularly pronounced in scale variations of human body parts when camera view changes or severe foreshortening happens. Although pyramid methods are widely used to handle scale changes at inference time, learning feature pyramids in deep convolutional neural networks (DCNNs) is still not well explored. In this work, we design a Pyramid Residual Module (PRMs) to enhance the invariance in scales of DCNNs. Given input features, the PRMs learn convolutional filters on various scales of input features, which are obtained with different subsampling ratios in a multibranch network. Moreover, we observe that it is inappropriate to adopt existing methods to initialize the weights of multi-branch networks, which achieve superior performance than plain networks in many tasks recently. Therefore, we provide theoretic derivation to extend the current weight initialization scheme to multi-branch network structures. We investigate our method on two standard benchmarks for human pose estimation. Our approach obtains state-of-the-art results on both benchmarks. Code is available at https://github.com/bearpaw/PyraNet.

Fashion landmarks are functional key points defined on clothes, such as corners of neckline, hemline, and cuff. They have been recently introduced [18]as an effective visual representation for fashion image understanding. However, detecting fashion landmarks are challenging due to background clutters, human poses, and scales. To remove the above variations, previous works usually assumed bounding boxes of clothes are provided in training and test as additional annotations, which are expensive to obtain and inapplicable in practice. This work addresses unconstrained fashion landmark detection, where clothing bounding boxes are not provided in both training and test. To this end, we present a novel Deep LAndmark Network (DLAN), where bounding boxes and landmarks are jointly estimated and trained iteratively in an end-to-end manner. DLAN contains two dedicated modules, including a Selective Dilated Convolution for handling scale discrepancies, and a Hierarchical Recurrent Spatial Transformer for handling background clutters. To evaluate DLAN, we present a large-scale fashion landmark dataset, namely Unconstrained Landmark Database (ULD), consisting of 30K images. Statistics show that ULD is more challenging than existing datasets in terms of image scales, background clutters, and human poses. Extensive experiments demonstrate the effectiveness of DLAN over the state-of-the-art methods. DLAN also exhibits excellent generalization across different clothing categories and modalities, making it extremely suitable for real-world fashion analysis.

Recent works have shown that exploiting multi-scale representations deeply learned via convolutional neural networks (CNN) is of tremendous importance for accurate contour detection. This paper presents a novel approach for predicting contours which advances the state of the art in two fundamental aspects, i.e. multi-scale feature generation and fusion. Different from previous works directly considering multi-scale feature maps obtained from the inner layers of a primary CNN architecture, we introduce a hierarchical deep model which produces more rich and complementary representations. Furthermore, to refine and robustly fuse the representations learned at different scales, the novel Attention-Gated Conditional Random Fields (AG-CRFs) are proposed. The experiments ran on two publicly available datasets (BSDS500 and NYUDv2) demonstrate the effectiveness of the latent AG-CRF model and of the overall hierarchical framework.

In this paper, we propose deformable deep convolutional neural networks for generic object detection. This new deep learning object detection framework has innovations in multiple aspects. In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty. A new pre-training strategy is proposed to learn feature representations more suitable for the object detection task and with good generalization capability. By changing the net structures, training strategies, adding and removing some key components in the detection pipeline, a set of models with large diversity are obtained, which significantly improves the effectiveness of model averaging. The proposed approach improves the mean averaged precision obtained by RCNN [16], which was the state-of-the-art, from 31% to 50.3% on the ILSVRC2014 detection test set. It also outperforms the winner of ILSVRC2014, GoogLeNet, by 6.1%. Detailed component-wise analysis is also provided through extensive experimental evaluation, which provides a global view for people to understand the deep learning object detection pipeline.

This paper studies an approach to gait based human identification via similarity learning by deep convolutional neural networks (CNNs). With a pretty small group of labeled multi-view human walking videos, we can train deep networks to recognize the most discriminative changes of gait patterns which suggest the change of human identity. To the best of our knowledge, this is the first work based on deep CNNs for gait recognition in the literature. Here, we provide an extensive empirical evaluation in terms of various scenarios, namely, cross-view and cross-walking-condition, with different preprocessing approaches and network architectures. The method is first evaluated on the challenging CASIA-B dataset in terms of cross-view gait recognition. Experimental results show that it outperforms the previous state-of-the-art methods by a significant margin. In particular, our method shows advantages when the cross-view angle is large, i.e., no less than 36 degree. And the average recognition rate can reach 94 percent, much better than the previous best result (less than 65 percent). The method is further evaluated on the OU-ISIR gait dataset to test its generalization ability to larger data. OU-ISIR is currently the largest dataset available in the literature for gait recognition, with 4,007 subjects. On this dataset, the average accuracy of our method under identical view conditions is above 98 percent, and the one for cross-view scenarios is above 91 percent. Finally, the method also performs the best on the USF gait dataset, whose gait sequences are imaged in a real outdoor scene. These results show great potential of this method for practical applications.

In this paper, we tackle the problem of stationary crowd analysis which is as important as modeling mobile groups in crowd scenes and finds many important applications in crowd surveillance. Our key contribution is to propose a robust algorithm for estimating how long a foreground pixel becomes stationary. It is much more challenging than only subtracting background because failure at a single frame due to local movement of objects, lighting variation, and occlusion could lead to large errors on stationary-time estimation. To achieve robust and accurate estimation, sparse constraints along spatial and temporal dimensions are jointly added by mixed partials (which are second-order gradients) to shape a 3D stationary-time map. It is formulated as an L0optimization problem. Besides background subtraction, it distinguishes among different foreground objects, which are close or overlapped in the spatio-temporal space by using a locally shared foreground codebook. The proposed technologies are further demonstrated through three applications. 1) Based on the results of stationary-time estimation, 12 descriptors are proposed to detect four types of stationary crowd activities. 2) The averaged stationary-time map is estimated to analyze crowd scene structures. 3) The result of stationary-time estimation is also used to study the influence of stationary crowd groups to traffic patterns.

Human eyes can recognize person identities based on small salient regions, i.e., person saliency is distinctive and reliable in pedestrian matching across disjoint camera views. However, such valuable information is often hidden when computing similarities of pedestrian images with existing approaches. Inspired by our user study result of human perception on person saliency, we propose a novel perspective for person re-identification based on learning person saliency and matching saliency distribution. The proposed saliency learning and matching framework consists of four steps: (1) To handle misalignment caused by drastic viewpoint change and pose variations, we apply adjacency constrained patch matching to build dense correspondence between image pairs. (2) We propose two alternative methods, i.e., K-Nearest Neighbors and One-class SVM, to estimate a saliency score for each image patch, through which distinctive features stand out without using identity labels in the training procedure. (3) saliency matching is proposed based on patch matching. Matching patches with inconsistent saliency brings penalty, and images of the same identity are recognized by minimizing the saliency matching cost. (4) Furthermore, saliency matching is tightly integrated with patch matching in a unified structural RankSVM learning framework. The effectiveness of our approach is validated on the four public datasets. Our approach outperforms the state-of-the-art person re-identification methods on all these datasets.

Crowd video analysis is one of the hallmark tasks of crowded scene understanding. While we observe a tremendous progress in image-based tasks with the rise of convolutional neural networks (CNNs), performance on video analysis has not (yet) attained the same level of success. In this paper, we introduce intuitive but effective temporal-aware crowd motion channels by uniformly slicing the video volume from different dimensions. Multiple CNN structures with different data-fusion strategies and weight-sharing schemes are proposed to learn the connectivity both spatially and temporally from these motion channels. To well demonstrate our deep model, we construct a new large-scale Who do What at someWhere crowd data set with 10 000 videos from 8257 crowded scenes, and build an attribute set with 94 attributes. Extensive experiments on crowd video attribute prediction demonstrate the effectiveness of our novel method over the state-of-the-art.

Groups are the primary entities that make up a crowd. Understanding group-level dynamics and properties is thus scientifically important and practically useful in a wide range of applications, especially for crowd understanding. In this paper, we show that fundamental group-level properties, such as intra-group stability and inter-group conflict, can be systematically quantified by visual descriptors. This is made possible through learning a novel collective transition prior, which leads to a robust approach for group segregation in public spaces. From the former, we further devise a rich set of group-property visual descriptors. These descriptors are scene-independent and can be effectively applied to public scenes with a variety of crowd densities and distributions. Extensive experiments on hundreds of public scene video clips demonstrate that such property descriptors are complementary to each other, scene-independent, and they convey critical information on physical states of a crowd. The proposed group-level descriptors show promising results and potentials in multiple applications, including crowd dynamic monitoring, crowd video classification, and crowd video retrieval.

In this paper, we tackle the problem of no-reference image quality assessment (IQA). A learning-based IQA framework “VIDGIQA” is proposed, which extracts quality features from the input image and regresses the visual quality on these features. Since different distortions lead to different visual perceptions in the human visual system, distortion information is adopted to guide the feature learning process together with the human quality scores. Besides, a regression method is proposed to model and estimate the visual importance weights of all local regions, which can effectively improve the performance. More importantly, all these operations are integrated into one deep neural network, so that they can be jointly optimized and well cooperate with each other. Experiments were conducted to demonstrate the power of the proposed method on several datasets, including the LIVE dataset [1], the TID 2013 dataset [2], the LIVE multiply distorted IQA dataset [3], CSIQ [4] , and the LIVE in the wild image quality database [5]. The proposed method achieves 0.969 and 0.973 on the LIVE dataset [1] in terms of the spearman rank-order correlation coefficient and the Pearson linear correlation coefficient, respectively, which outperforms the state-of-the-art methods.

The recent advanced face recognition systems werebuilt on large Deep Neural Networks (DNNs) or theirensembles, which have millions of parameters. However, the expensive computation of DNNs make theirdeployment difficult on mobile and embedded devices. This work addresses model compression for face recognition,where the learned knowledge of a large teachernetwork or its ensemble is utilized as supervisionto train a compact student network. Unlike previousworks that represent the knowledge by the soften labelprobabilities, which are difficult to fit, we represent theknowledge by using the neurons at the higher hiddenlayer, which preserve as much information as the label probabilities, but are more compact. By leveragingthe essential characteristics (domain knowledge) of thelearned face representation, a neuron selection methodis proposed to choose neurons that are most relevant toface recognition. Using the selected neurons as supervisionto mimic the single networks of DeepID2+ andDeepID3, which are the state-of-the-art face recognition systems, a compact student with simple network structure achieves better verification accuracy on LFW than its teachers, respectively. When using an ensemble of DeepID2+ as teacher, a mimicked student is able to outperform it and achieves 51.6 times compression ratio and 90 times speed-up in inference, making this cumbersome model applicable on portable devices.

In this paper, we propose a structured feature learning framework to reason the correlations among body joints at the feature level in human pose estimation. Different from existing approaches of modeling structures on score maps or predicted labels, feature maps preserve substantially richer descriptions of body joints. The relationships between feature maps of joints are captured with the introduced geometrical transform kernels, which can be easily implemented with a convolution layer. Features and their relationships are jointly learned in an end-to-end learning system. A bi-directional tree structured model is proposed, so that the feature channels at a body joint can well receive information from other joints. The proposed framework improves feature learning substantially. With very simple post processing, it reaches the best mean PCP on the LSP and FLIC datasets. Compared with the baseline of learning features at each joint separately with ConvNet, the mean PCP has been improved by 18% on FLIC. The code is released to the public.

Deep Convolution Neural Networks (CNNs) have shown impressive performance in various vision tasks such as image classification, object detection and semantic segmentation. For object detection, particularly in still images, the performance has been significantly increased last year thanks to powerful deep networks (e.g. GoogleNet) and detection frameworks (e.g. Regions with CNN features (RCNN)). The lately introduced ImageNet [6] task on object detection from video (VID) brings the object detection task into the video domain, in which objects' locations at each frame are required to be annotated with bounding boxes. In this work, we introduce a complete framework for the VID task based on still-image object detection and general object tracking. Their relations and contributions in the VID task are thoroughly studied and evaluated. In addition, a temporal convolution network is proposed to incorporate temporal information to regularize the detection results and shows its effectiveness for the task. Code is available at https://github.com/ myfavouritekk/vdetlib.

Recent advances in clothes recognition have been driven by the construction of clothes datasets. Existing datasets are limited in the amount of annotations and are difficult to cope with the various challenges in real-world applications. In this work, we introduce DeepFashion1, a large-scale clothes dataset with comprehensive annotations. It contains over 800,000 images, which are richly annotated with massive attributes, clothing landmarks, and correspondence of images taken under different scenarios including store, street snapshot, and consumer. Such rich annotations enable the development of powerful algorithms in clothes recognition and facilitating future researches. To demonstrate the advantages of DeepFashion, we propose a new deep model, namely FashionNet, which learns clothing features by jointly predicting clothing attributes and landmarks. The estimated landmarks are then employed to pool or gate the learned features. It is optimized in an iterative manner. Extensive experiments demonstrate the effectiveness of FashionNet and the usefulness of DeepFashion.

Finetuning from a pretrained deep model is found to yield state-of-the-art performance for many vision tasks. This paper investigates many factors that influence the performance in finetuning for object detection. There is a longtailed distribution of sample numbers for classes in object detection. Our analysis and empirical results show that classes with more samples have higher impact on the feature learning. And it is better to make the sample number more uniform across classes. Generic object detection can be considered as multiple equally important tasks. Detection of each class is a task. These classes/tasks have their individuality in discriminative visual appearance representation. Taking this individuality into account, we cluster objects into visually similar class groups and learn deep representations for these groups separately. A hierarchical feature learning scheme is proposed. In this scheme, the knowledge from the group with large number of classes is transferred for learning features in its subgroups. Finetuned on the GoogLeNet model, experimental results show 4.7% absolute mAP improvement of our approach on the ImageNet object detection dataset without increasing much computational cost at the testing stage. Code is available on www.ee.cuhk.edu.hk/ wlouyang/ projects/ImageNetFactors/CVPR16.html.

Learning and capturing both appearance and dynamic representations are pivotal for crowd video understanding. Convolutional Neural Networks (CNNs) have shown its remarkable potential in learning appearance representations from images. However, the learning of dynamic representation, and how it can be effectively combined with appearance features for video analysis, remains an open problem. In this study, we propose a novel spatio-temporal CNN, named Slicing CNN (S-CNN), based on the decomposition of 3D feature maps into 2D spatio-and 2D temporal-slices representations. The decomposition brings unique advantages: (1) the model is capable of capturing dynamics of different semantic units such as groups and objects, (2) it learns separated appearance and dynamic representations while keeping proper interactions between them, and (3) it exploits the selectiveness of spatial filters to discard irrelevant background clutter for crowd understanding. We demonstrate the effectiveness of the proposed S-CNN model on the WWW crowd video dataset for attribute recognition and observe significant performance improvements to the state-of-the-art methods (62.55% from 51.84% [21]).

This paper proposes to learn high-performance deep ConvNets with sparse neural connections, referred to as sparse ConvNets, for face recognition. The sparse ConvNets are learned in an iterative way, each time one additional layer is sparsified and the entire model is re-trained given the initial weights learned in previous iterations. One important finding is that directly training the sparse ConvNet from scratch failed to find good solutions for face recognition, while using a previously learned denser model to properly initialize a sparser model is critical to continue learning effective features for face recognition. This paper also proposes a new neural correlation-based weight selection criterion and empirically verifies its effectiveness in selecting informative connections from previously learned models in each iteration. When taking a moderately sparse structure (26%-76% of weights in the dense model), the proposed sparse ConvNet model significantly improves the face recognition performance of the previous state-of-the-art DeepID2+ models given the same training data, while it keeps the performance of the baseline model with only 12% of the original parameters.

Due to the limited amount of training samples, finetuning pre-trained deep models online is prone to overfitting. In this paper, we propose a sequential training method for convolutional neural networks (CNNs) to effectively transfer pre-trained deep features for online applications. We regard a CNN as an ensemble with each channel of the output feature map as an individual base learner. Each base learner is trained using different loss criterions to reduce correlation and avoid over-training. To achieve the best ensemble online, all the base learners are sequentially sampled into the ensemble via important sampling. To further improve the robustness of each base learner, we propose to train the convolutional layers with random binary masks, which serves as a regularization to enforce each base learner to focus on different input features. The proposed online training method is applied to visual tracking problem by transferring deep features trained on massive annotated visual data and is shown to significantly improve tracking performance. Extensive experiments are conducted on two challenging benchmark data set and demonstrate that our tracking algorithm can outperform state-of-the-art methods with a considerable margin.

Learning generic and robust feature representations with data from multiple domains for the same problem is of great value, especially for the problems that have multiple datasets but none of them are large enough to provide abundant data variations. In this work, we present a pipeline for learning deep feature representations from multiple domains with Convolutional Neural Networks (CNNs). When training a CNN with data from all the domains, some neurons learn representations shared across several domains, while some others are effective only for a specific one. Based on this important observation, we propose a Domain Guided Dropout algorithm to improve the feature learning procedure. Experiments show the effectiveness of our pipeline and the proposed algorithm. Our methods on the person re-identification problem outperform stateof-the-art methods on multiple datasets by large margins.

Recently, Deep Convolutional Neural Networks (DCNNs) have been applied to the task of human pose estimation, and have shown its potential of learning better feature representations and capturing contextual relationships. However, it is difficult to incorporate domain prior knowledge such as geometric relationships among body parts into DCNNs. In addition, training DCNN-based body part detectors without consideration of global body joint consistency introduces ambiguities, which increases the complexity of training. In this paper, we propose a novel end-to-end framework for human pose estimation that combines DCNNs with the expressive deformable mixture of parts. We explicitly incorporate domain prior knowledge into the framework, which greatly regularizes the learning process and enables the flexibility of our framework for loopy models or tree-structured models. The effectiveness of jointly learning a DCNN with a deformable mixture of parts model is evaluated through intensive experiments on several widely used benchmarks. The proposed approach significantly improves the performance compared with state-of-the-art approaches, especially on benchmarks with challenging articulations.

As a widely used non-linear activation, Rectified Linear Unit (ReLU) separates noise and signal in a feature map by learning a threshold or bias. However, we argue that the classification of noise and signal not only depends on the magnitude of responses, but also the context of how the feature responses would be used to detect more abstract patterns in higher layers. In order to output multiple response maps with magnitude in different ranges for a particular visual pattern, existing networks employing ReLU and its variants have to learn a large number of redundant filters. In this paper, we propose a multi-bias non-linear activation (MBA) layer to explore the information hidden in the magnitudes of responses. It is placed after the convolution layer to decouple the responses to a convolution kernel into multiple maps by multi-thresholding magnitudes, thus generating more patterns in the feature space at a low computational cost. It provides great flexibility of selecting responses to different visual patterns in different magnitude ranges to form rich representations in higher layers. Such a simple and yet effective scheme achieves the state-of-the-art performance on several benchmarks.

While vital for handling most multimedia and computer vision problems, collecting large scale fully annotated datasets is a resource-consuming, often unaffordable task. Indeed, on the one hand datasets need to be large and variate enough so that learning strategies can successfully exploit the variability inherently present in real data, but on the other hand they should be small enough so that they can be fully annotated at a reasonable cost. With the overwhelming success of (deep) learning methods, the traditional problem of balancing between dataset dimensions and resources needed for annotations became a full-fledged dilemma. In this context, methodological approaches able to deal with partially described data sets represent a one-of-a-kind opportunity to find the right balance between data variability and resource-consumption in annotation. These include methods able to deal with noisy, weak or partial annotations. In this tutorial we will present several recent methodologies addressing different visual tasks under the assumption of noisy, weakly annotated data sets.

Deep convolutional neural networks (CNN) have achieved great success. On the other hand, modeling structural information has been proved critical in many vision problems. It is of great interest to integrate them effectively. In a classical neural network, there is no message passing between neurons in the same layer. In this paper, we propose a CRF-CNN framework which can simultaneously model structural information in both output and hidden feature layers in a probabilistic way, and it is applied to human pose estimation. A message passing scheme is proposed, so that in various layers each body joint receives messages from all the others in an efficient way. Such message passing can be implemented with convolution between features maps in the same layer, and it is also integrated with feedforward propagation in neural networks. Finally, a neural network implementation of end-to-end learning CRF-CNN is provided. Its effectiveness is demonstrated through experiments on two benchmark datasets.

This paper proposes a hybrid convolutional network (ConvNet)-Restricted Boltzmann Machine (RBM) model for face verification. A key contribution of this work is to learn high-level relational visual features with rich identity similarity information. The deep ConvNets in our model start by extracting local relational visual features from two face images in comparison, which are further processed through multiple layers to extract high-level and global relational features. To keep enough discriminative information, we use the last hidden layer neuron activations of the ConvNet as features for face verification instead of those of the output layer. To characterize face similarities from different aspects, we concatenate the features extracted from different face region pairs by different deep ConvNets. The resulting high-dimensional relational features are classified by an RBM for face verification. After pre-training each ConvNet and the RBM separately, the entire hybrid network is jointly optimized to further improve the accuracy. Various aspects of the ConvNet structures, relational features, and face verification classifiers are investigated. Our model achieves the state-of-the-art face verification performance on the challenging LFW dataset under both the unrestricted protocol and the setting when outside data is allowed to be used for training.

Part-based models have demonstrated their merit in object detection. However, there is a key issue to be solved on how to integrate the inaccurate scores of part detectors when there are occlusions, abnormal deformations, appearances, or illuminations. To handle the imperfection of part detectors, this paper presents a probabilistic pedestrian detection framework. In this framework, a deformable part-based model is used to obtain the scores of part detectors and the visibilities of parts are modeled as hidden variables. Once the occluded parts are identified, their effects are properly removed from the final detection score. Unlike previous occlusion handling approaches that assumed independence among the visibility probabilities of parts or manually defined rules for the visibility relationship, a deep model is proposed in this paper for learning the visibility relationship among overlapping parts at multiple layers. The proposed approach can be viewed as a general postprocessing of part-detection results and can take detection scores of existing part-based models as input. The experimental results on three public datasets (Caltech, ETH, and Daimler) and a new CUHK occlusion dataset (http://www.ee.cuhk.edu.hk/~xgwang/CUHK_pedestrian.html), which is specially designed for the evaluation of occlusion handling approaches, show the effectiveness of the proposed approach.

Local binary patterns (LBP) are considered among the most computationally efficient high-performance texture features. However, the LBP method is very sensitive to image noise and is unable to capture macrostructure information. To best address these disadvantages, in this paper, we introduce a novel descriptor for texture classification, the median robust extended LBP (MRELBP). Different from the traditional LBP and many LBP variants, MRELBP compares regional image medians rather than raw image intensities. A multiscale LBP type descriptor is computed by efficiently comparing image medians over a novel sampling scheme, which can capture both microstructure and macrostructure texture information. A comprehensive evaluation on benchmark data sets reveals MRELBP's high performance-robust to gray scale variations, rotation changes and noise-but at a low computational cost. MRELBP produces the best classification scores of 99.82%, 99.38%, and 99.77% on three popular Outex test suites. More importantly, MRELBP is shown to be highly robust to image noise, including Gaussian noise, Gaussian blur, salt-and-pepper noise, and random pixel corruption.

Pedestrian behavior modeling and analysis is important for crowd scene understanding and has various applications in video surveillance. Stationary crowd groups are a key factor influencing pedestrian walking patterns but was mostly ignored in the literature. It plays different roles for different pedestrians in a crowded scene and can change over time. In this paper, a novel model is proposed to model pedestrian behaviors by incorporating stationary crowd groups as a key component. Through inference on the interactions between stationary crowd groups and pedestrians, our model can be used to investigate pedestrian behaviors. The effectiveness of the proposed model is demonstrated through multiple applications, including walking path prediction, destination prediction, personality attribute classification, and abnormal event detection. To evaluate our model, two large pedestrian walking route datasets are built. The walking routes of around 15 000 pedestrians from two crowd surveillance videos are manually annotated. The datasets will be released to the public and benefit future research on pedestrian behavior analysis and crowd scene understanding.

In this paper, we present a novel method to recognize the types of crowd movement from crowd trajectories using agent-based motion models (AMMs). Our idea is to apply a number of AMMs, referred to as exemplar-AMMs, to describe the crowd movement. Specifically, we propose an optimization framework that filters out the unknown noise in the crowd trajectories and measures their similarity to the exemplar-AMMs to produce a crowd motion feature. We then address our real-world crowd movement recognition problem as a multilabel classification problem. Our experiments show that the proposed feature outperforms the state-of-the-art methods in recognizing both simulated and real-world crowd movements from their trajectories. Finally, we have created a synthetic dataset, SynCrowd, which contains two-dimensional (2D) crowd trajectories in various scenarios, generated by various crowd simulators. This dataset can serve as a training set or benchmark for crowd analysis work.

Human perceptions of music and image are closely related to each other, since both can inspire similar human sensations, such as emotion, motion, and power. This paper aims to explore whether and how music and image can be automatically matched by machines. The main contributions are three aspects. First, we construct a benchmark dataset composed of more than 45 000 music-image pairs. Human labelers are recruited to annotate whether these pairs are well-matched or not. The results show that they generally agree with each other on the matching degree of music-image pairs. Secondly, we investigate suitable semantic representations of music and image for this cross-modal matching task. In particular, we adopt lyrics as a middle-media to connect music and image, and design a set of lyric-based attributes for image representation. Thirdly, we propose cross-modal ranking analysis (CMRA) to learn the semantic similarity between music and image with ranking labeling information. CMRA aims to find the optimal embedding spaces for both music and image in the sense of maximizing the ordinal margin between music-image pairs. The proposed method is able to learn the non-linear relationship between music and image, and to integrate heterogeneous ranking data from different modalities into a unified space. Experimental results demonstrate that the proposed method outperforms state-of-the-art cross-modal methods in the music-image matching task, and achieves a consistency rate of 91.5% with human labelers.

Crowd understanding has drawn increasing attention from the computer vision community, and its progress is driven by the availability of public crowd datasets. In this paper, we contribute a large-scale benchmark dataset collected from the Shanghai 2010 World Expo. It includes 2630 annotated video sequences captured by 245 surveillance cameras, far larger than any public dataset. It covers a large number of different scenes and is suitable for evaluating the performance of crowd segmentation and estimation of crowd density, collectiveness, and cohesiveness, all of which are universal properties of crowd systems. In total, 53 637 crowd segments are manually annotated with the three crowd properties. This dataset is released to the public to advance research on crowd understanding. The largescale annotated dataset enables using data-driven approaches for crowd understanding. In this paper, a data-driven approach is proposed as a baseline of crowd segmentation and estimation of crowd properties for the proposed dataset. Novel global and local crowd features are designed to retrieve similar training scenes and to match spatio-temporal crowd patches so that the labels of the training scenes can be accurately transferred to the query image. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art approaches for crowd understanding.

In this paper, we propose deformable deep convolutional neural networks for generic object detection. This new deep learning object detection framework has innovations in multiple aspects. In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty. A new pre-training strategy is proposed to learn feature representations more suitable for the object detection task and with good generalization capability. By changing the net structures, training strategies, adding and removing some key components in the detection pipeline, a set of models with large diversity are obtained, which significantly improves the effectiveness of model averaging. The proposed approach improves the mean averaged precision obtained by RCNN [14], which was the state-of-the-art, from 31% to 50.3% on the ILSVRC2014 detection test set. It also outperforms the winner of ILSVRC2014, GoogLeNet, by 6.1%. Detailed component-wise analysis is also provided through extensive experimental evaluation, which provide a global view for people to understand the deep learning object detection pipeline.

Crowded scene understanding is a fundamental problem in computer vision. In this study, we develop a multi-task deep model to jointly learn and combine appearance and motion features for crowd understanding. We propose crowd motion channels as the input of the deep model and the channel design is inspired by generic properties of crowd systems. To well demonstrate our deep model, we construct a new large-scale WWW Crowd dataset with 10, 000 videos from 8, 257 crowded scenes, and build an attribute set with 94 attributes on WWW. We further measure user study performance on WWW and compare this with the proposed deep models. Extensive experiments show that our deep models display significant performance improvements in cross-scene attribute recognition compared to strong crowd-related feature-based baselines, and the deeply learned features behave a superior performance in multi-task learning.

This paper designs a high-performance deep convolutional network (DeepID2+) for face recognition. It is learned with the identification-verification supervisory signal. By increasing the dimension of hidden representations and adding supervision to early convolutional layers, DeepID2+ achieves new state-of-the-art on LFW and YouTube Faces benchmarks. Through empirical studies, we have discovered three properties of its deep neural activations critical for the high performance: sparsity, selectiveness and robustness. (1) It is observed that neural activations are moderately sparse. Moderate sparsity maximizes the discriminative power of the deep net as well as the distance between images. It is surprising that DeepID2+ still can achieve high recognition accuracy even after the neural responses are binarized. (2) Its neurons in higher layers are highly selective to identities and identity-related attributes. We can identify different subsets of neurons which are either constantly excited or inhibited when different identities or attributes are present. Although DeepID2+ is not taught to distinguish attributes during training, it has implicitly learned such high-level concepts. (3) It is much more robust to occlusions, although occlusion patterns are not included in the training set.

Deep learning methods have achieved great successes in pedestrian detection, owing to its ability to learn discriminative features from raw pixels. However, they treat pedestrian detection as a single binary classification task, which may confuse positive with hard negative samples (Fig.1 (a)). To address this ambiguity, this work jointly optimize pedestrian detection with semantic tasks, including pedestrian attributes (e.g. `carrying backpack') and scene attributes (e.g. `vehicle', `tree', and `horizontal'). Rather than expensively annotating scene attributes, we transfer attributes information from existing scene segmentation datasets to the pedestrian dataset, by proposing a novel deep model to learn high-level features from multiple tasks and multiple data sources. Since distinct tasks have distinct convergence rates and data from different datasets have different distributions, a multi-task deep model is carefully designed to coordinate tasks and reduce discrepancies among datasets. Extensive evaluations show that the proposed approach outperforms the state-of-the-art on the challenging Caltech [9] and ETH [10] datasets where it reduces the miss rates of previous deep models by 17 and 5.5 percent, respectively.

Large-scale supervised datasets are crucial to train convolutional neural networks (CNNs) for various computer vision problems. However, obtaining a massive amount of well-labeled data is usually very expensive and time consuming. In this paper, we introduce a general framework to train CNNs with only a limited number of clean labels and millions of easily obtained noisy labels. We model the relationships between images, class labels and label noises with a probabilistic graphical model and further integrate it into an end-to-end deep learning system. To demonstrate the effectiveness of our approach, we collect a large-scale real-world clothing classification dataset with both noisy and clean labels. Experiments on this dataset indicate that our approach can better correct the noisy labels and improves the performance of trained CNNs.

Pedestrian behavior modeling and analysis is important for crowd scene understanding and has various applications in video surveillance. Stationary crowd groups are a key factor influencing pedestrian walking patterns but was largely ignored in literature. In this paper, a novel model is proposed for pedestrian behavior modeling by including stationary crowd groups as a key component. Through inference on the interactions between stationary crowd groups and pedestrians, our model can be used to investigate pedestrian behaviors. The effectiveness of the proposed model is demonstrated through multiple applications, including walking path prediction, destination prediction, personality classification, and abnormal event detection. To evaluate our model, a large pedestrian walking route dataset1is built. The walking routes of 12, 684 pedestrians from a one-hour crowd surveillance video are manually annotated. It will be released to the public and benefit future research on pedestrian behavior analysis and crowd scene understanding.

Cross-scene crowd counting is a challenging task where no laborious data annotation is required for counting people in new target surveillance crowd scenes unseen in the training set. The performance of most existing crowd counting methods drops significantly when they are applied to an unseen scene. To address this problem, we propose a deep convolutional neural network (CNN) for crowd counting, and it is trained alternatively with two related learning objectives, crowd density and crowd count. This proposed switchable learning approach is able to obtain better local optimum for both objectives. To handle an unseen target crowd scene, we present a data-driven method to fine-tune the trained CNN model for the target scene. A new dataset including 108 crowd scenes with nearly 200,000 head annotations is introduced to better evaluate the accuracy of cross-scene crowd counting methods. Extensive experiments on the proposed and another two existing datasets demonstrate the effectiveness and reliability of our approach.

Low-level saliency cues or priors do not produce good enough saliency detection results especially when the salient object presents in a low-contrast background with confusing visual appearance. This issue raises a serious problem for conventional approaches. In this paper, we tackle this problem by proposing a multi-context deep learning framework for salient object detection. We employ deep Convolutional Neural Networks to model saliency of objects in images. Global context and local context are both taken into account, and are jointly modeled in a unified multi-context deep learning framework. To provide a better initialization for training the deep neural networks, we investigate different pre-training strategies, and a task-specific pre-training scheme is designed to make the multi-context modeling suited for saliency detection. Furthermore, recently proposed contemporary deep models in the ImageNet Image Classification Challenge are tested, and their effectiveness in saliency detection are investigated. Our approach is extensively evaluated on five public datasets, and experimental results show significant and consistent improvements over the state-of-the-art methods.

In this paper, we propose to predict immediacy for interacting persons from still images. A complete immediacy set includes interactions, relative distance, body leaning direction and standing orientation. These measures are found to be related to the attitude, social relationship, social interaction, action, nationality, and religion of the communicators. A large-scale dataset with 10,000 images is constructed, in which all the immediacy measures and the human poses are annotated. We propose a rich set of immediacy representations that help to predict immediacy from imperfect 1-person and 2-person pose estimation results. A multi-task deep recurrent neural network is constructed to take the proposed rich immediacy representation as input and learn the complex relationship among immediacy predictions multiple steps of refinement. The effectiveness of the proposed approach is proved through extensive experiments on the large scale dataset.

Predicting face attributes in the wild is challenging due to complex face variations. We propose a novel deep learning framework for attribute prediction in the wild. It cascades two CNNs, LNet and ANet, which are fine-tuned jointly with attribute tags, but pre-trained differently. LNet is pre-trained by massive general object categories for face localization, while ANet is pre-trained by massive face identities for attribute prediction. This framework not only outperforms the state-of-the-art with a large margin, but also reveals valuable facts on learning face representation. (1) It shows how the performances of face localization (LNet) and attribute prediction (ANet) can be improved by different pre-training strategies. (2) It reveals that although the filters of LNet are fine-tuned only with image-level attribute tags, their response maps over entire images have strong indication of face locations. This fact enables training LNet for face localization with only image-level annotations, but without face bounding boxes or landmarks, which are required by all attribute recognition works. (3) It also demonstrates that the high-level hidden neurons of ANet automatically discover semantic concepts after pre-training with massive face identities, and such concepts are significantly enriched after fine-tuning with attribute tags. Each attribute can be well explained with a sparse linear combination of these concepts.

Learning strong feature representations from large scale supervision has achieved remarkable success in computer vision as the emergence of deep learning techniques. It is driven by big visual data with rich annotations. This paper contributes a large-scale object attribute database that contains rich attribute annotations (over 300 attributes) for ~180k samples and 494 object classes. Based on the ImageNet object detection dataset, it annotates the rotation, viewpoint, object part location, part occlusion, part existence, common attributes, and class-specific attributes. Then we use this dataset to train deep representations and extensively evaluate how these attributes are useful on the general object detection task. In order to make better use of the attribute annotations, a deep learning scheme is proposed by modeling the relationship of attributes and hierarchically clustering them into semantically meaningful mixture types. Experimental results show that the attributes are helpful in learning better features and improving the object detection accuracy by 2.6% in mAP on the ILSVRC 2014 object detection dataset and 2.4% in mAP on PASCAL VOC 2007 object detection dataset. Such improvement is well generalized across datasets.

Recent advances in pedestrian detection are attained by transferring the learned features of Convolutional Neural Network (ConvNet) to pedestrians. This ConvNet is typically pre-trained with massive general object categories (e.g. ImageNet). Although these features are able to handle variations such as poses, viewpoints, and lightings, they may fail when pedestrian images with complex occlusions are present. Occlusion handling is one of the most important problem in pedestrian detection. Unlike previous deep models that directly learned a single detector for pedestrian detection, we propose DeepParts, which consists of extensive part detectors. DeepParts has several appealing properties. First, DeepParts can be trained on weakly labeled data, i.e. only pedestrian bounding boxes without part annotations are provided. Second, DeepParts is able to handle low IoU positive proposals that shift away from ground truth. Third, each part detector in DeepParts is a strong detector that can detect pedestrian by observing only a part of a proposal. Extensive experiments in Caltech dataset demonstrate the effectiveness of DeepParts, which yields a new state-of-the-art miss rate of 11:89%, outperforming the second best method by 10%.

We propose a new approach for general object tracking with fully convolutional neural network. Instead of treating convolutional neural network (CNN) as a black-box feature extractor, we conduct in-depth study on the properties of CNN features offline pre-trained on massive image data and classification task on ImageNet. The discoveries motivate the design of our tracking system. It is found that convolutional layers in different levels characterize the target from different perspectives. A top layer encodes more semantic features and serves as a category detector, while a lower layer carries more discriminative information and can better separate the target from distracters with similar appearance. Both layers are jointly used with a switch mechanism during tracking. It is also found that for a tracking target, only a subset of neurons are relevant. A feature map selection method is developed to remove noisy and irrelevant feature maps, which can reduce computation redundancy and improve tracking accuracy. Extensive evaluation on the widely used tracking benchmark [36] shows that the proposed tacker outperforms the state-of-the-art significantly.

In this paper, we target on the problem of estimating the statistic of pedestrian travel time within a period from an entrance to a destination in a crowded scene. Such estimation is based on the global distributions of crowd densities and velocities instead of complete trajectories of pedestrians, which cannot be obtained in crowded scenes. The proposed method is motivated by our statistical investigation into the correlations between travel time and global properties of crowded scenes. Active regions are created for each source-destination pair to model the probable walking regions over the corresponding source-destination traffic flow. Two sets of scene features are specially designed for modeling moving and stationary persons inside the active regions and their influences on pedestrian travel time. The estimation of pedestrian travel time provides valuable information for both crowd scene understanding and pedestrian behavior analysis, but was not sufficiently studied in literature. The effectiveness of the proposed pedestrian travel time estimation model is demonstrated through several surveillance applications, including dynamic scene monitoring, localization of regions blocking traffics, and detection of abnormal pedestrian behaviors. Many more valuable applications based on our method are to be explored in the future.

In this paper, we address the challenging problem of detecting pedestrians who appear in groups. A new approach is proposed for single-pedestrian detection aided by two-pedestrian detection. A mixture model of two-pedestrian detectors is designed to capture the unique visual cues which are formed by nearby pedestrians but cannot be captured by single-pedestrian detectors. A probabilistic framework is proposed to model the relationship between the configurations estimated by single- and two-pedestrian detectors, and to refine the single-pedestrian detection result using two-pedestrian detection. The two-pedestrian detector can integrate with any single-pedestrian detector. Twenty-five state-of-the-art single-pedestrian detection approaches are combined with the two-pedestrian detector on three widely used public datasets: Caltech, TUD-Brussels, and ETH. Experimental results show that our framework improves all these approaches. The average improvement is 9 percent on the Caltech-Test dataset, 11 percent on the TUD-Brussels dataset and 17 percent on the ETH dataset in terms of average miss rate. The lowest average miss rate is reduced from 37 to percent on the Caltech-Test dataset, from 55 to 50 percent on the TUD-Brussels dataset and from 43 to 38 percent on the ETH dataset.

Person re-identification is to match pedestrian images from disjoint camera views detected by pedestrian detectors. Challenges are presented in the form of complex variations of lightings, poses, viewpoints, blurring effects, image resolutions, camera settings, occlusions and background clutter across camera views. In addition, misalignment introduced by the pedestrian detector will affect most existing person re-identification methods that use manually cropped pedestrian images and assume perfect detection. In this paper, we propose a novel filter pairing neural network (FPNN) to jointly handle misalignment, photometric and geometric transforms, occlusions and background clutter. All the key components are jointly optimized to maximize the strength of each component when cooperating with others. In contrast to existing works that use handcrafted features, our method automatically learns features optimal for the re-identification task from data. The learned filter pairs encode photometric transforms. Its deep architecture makes it possible to model a mixture of complex photometric and geometric transforms. We build the largest benchmark re-id dataset with 13, 164 images of 1, 360 pedestrians. Unlike existing datasets, which only provide manually cropped pedestrian images, our dataset provides automatically detected bounding boxes for evaluation close to practical applications. Our neural network significantly outperforms state-of-the-art methods on this dataset.

In this paper, we propose a Switchable Deep Network (SDN) for pedestrian detection. The SDN automatically learns hierarchical features, salience maps, and mixture representations of different body parts. Pedestrian detection faces the challenges of background clutter and large variations of pedestrian appearance due to pose and viewpoint changes and other factors. One of our key contributions is to propose a Switchable Restricted Boltzmann Machine (SRBM) to explicitly model the complex mixture of visual variations at multiple levels. At the feature levels, it automatically estimates saliency maps for each test sample in order to separate background clutters from discriminative regions for pedestrian detection. At the part and body levels, it is able to infer the most appropriate template for the mixture models of each part and the whole body. We have devised a new generative algorithm to effectively pretrain the SDN and then fine-tune it with back-propagation. Our approach is evaluated on the Caltech and ETH datasets and achieves the state-of-the-art detection performance.

Visual appearance score, appearance mixture type and deformation are three important information sources for human pose estimation. This paper proposes to build a multi-source deep model in order to extract non-linear representation from these different aspects of information sources. With the deep model, the global, high-order human body articulation patterns in these information sources are extracted for pose estimation. The task for estimating body locations and the task for human detection are jointly learned using a unified deep model. The proposed approach can be viewed as a post-processing of pose estimation results and can flexibly integrate with existing methods by taking their information sources as input. By extracting the non-linear representation from multiple information sources, the deep model outperforms state-of-the-art by up to 8.6 percent on three public benchmark datasets.

Groups are the primary entities that make up a crowd. Understanding group-level dynamics and properties is thus scientifically important and practically useful in a wide range of applications, especially for crowd understanding. In this study we show that fundamental group-level properties, such as intra-group stability and inter-group conflict, can be systematically quantified by visual descriptors. This is made possible through learning a novel Collective Transition prior, which leads to a robust approach for group segregation in public spaces. From the prior, we further devise a rich set of group property visual descriptors. These descriptors are scene-independent, and can be effectively applied to public-scene with variety of crowd densities and distributions. Extensive experiments on hundreds of public scene video clips demonstrate that such property descriptors are not only useful but also necessary for group state analysis and crowd scene understanding.

This paper proposes to learn a set of high-level feature representations through deep learning, referred to as Deep hidden IDentity features (DeepID), for face verification. We argue that DeepID can be effectively learned through challenging multi-class face identification tasks, whilst they can be generalized to other tasks (such as verification) and new identities unseen in the training set. Moreover, the generalization capability of DeepID increases as more face classes are to be predicted at training. DeepID features are taken from the last hidden layer neuron activations of deep convolutional networks (ConvNets). When learned as classifiers to recognize about 10, 000 face identities in the training set and configured to keep reducing the neuron numbers along the feature extraction hierarchy, these deep ConvNets gradually form compact identity-related features in the top layers with only a small number of hidden neurons. The proposed features are extracted from various face regions to form complementary and over-complete representations. Any state-of-the-art classifiers can be learned based on these high-level representations for face verification. 97:45% verification accuracy on LFW is achieved with only weakly aligned faces.

We tackle stationary crowd analysis in this paper, which is similarly important as modeling mobile groups in crowd scenes and finds many applications in surveillance. Our key contribution is to propose a robust algorithm of estimating how long a foreground pixel becomes stationary. It is much more challenging than only subtracting background because failure at a single frame due to local movement of objects, lighting variation, and occlusion could lead to large errors on stationary time estimation. To accomplish decent results, sparse constraints along spatial and temporal dimensions are jointly added by mixed partials to shape a 3D stationary time map. It is formulated as a L0optimization problem. Besides background subtraction, it distinguishes among different foreground objects, which are close or overlapped in the spatio-temporal space by using a locally shared foreground codebook. The proposed technologies are used to detect four types of stationary group activities and analyze crowd scene structures. We provide the first public benchmark dataset for stationary time estimation and stationary group analysis.

In this paper, we propose a novel approach of learning mid-level filters from automatically discovered patch clusters for person re-identification. It is well motivated by our study on what are good filters for person re-identification. Our mid-level filters are discriminatively learned for identifying specific visual patterns and distinguishing persons, and have good cross-view invariance. First, local patches are qualitatively measured and classified with their discriminative power. Discriminative and representative patches are collected for filter learning. Second, patch clusters with coherent appearance are obtained by pruning hierarchical clustering trees, and a simple but effective cross-view training strategy is proposed to learn filters that are view-invariant and discriminative. Third, filter responses are integrated with patch matching scores in RankSVM training. The effectiveness of our approach is validated on the VIPeR dataset and the CUHK01 dataset. The learned mid-level features are complementary to existing handcrafted low-level features, and improve the best Rank-1 matching rate on the VIPeR dataset by 14%.

Image patch classification is an important task in many different medical imaging applications. In this work, we have designed a customized Convolutional Neural Networks (CNN) with shallow convolution layer to classify lung image patches with interstitial lung disease (ILD). While many feature descriptors have been proposed over the past years, they can be quite complicated and domain-specific. Our customized CNN framework can, on the other hand, automatically and efficiently learn the intrinsic image features from lung image patches that are most suitable for the classification purpose. The same architecture can be generalized to perform other medical image or texture classification tasks.

Detecting stationary crowd groups and analyzing their behaviors have important applications in crowd video surveillance, but have rarely been studied. The contributions of this paper are in two aspects. First, a stationary crowd detection algorithm is proposed to estimate the stationary time of foreground pixels. It employs spatial-temporal filtering and motion filtering in order to be robust to noise caused by occlusions and crowd clutters. Second, in order to characterize the emergence and dispersal processes of stationary crowds and their behaviors during the stationary periods, three attributes are proposed for quantitative analysis. These attributes are recognized with a set of proposed crowd descriptors which extract visual features from the results of stationary crowd detection. The effectiveness of the proposed algorithms is shown through experiments on a benchmark dataset.

We propose a deep learning architecture to solve the problem of multimodal fusion of multi-timescale temporal data, using music and video parts extracted from Music Videos (MVs) in particular. We capture the correlations between music and video at multiple levels by learning shared feature representations with Deep Belief Networks (DBN). The shared representations combine information from multiple modalities for decision making tasks, and are used to evaluate matching degrees between modalities and to retrieve matched modalities using single or multiple modalities as input. Moreover, we propose a novel deep architecture to handle temporal data at multiple timescales. When processing long sequences with varying length, we propose to extract hierarchical shared representations by concatenating deep representations at different levels, and to perform decision fusion with a feed forward neural network, which takes input from predictions of local and global classifiers trained with shared representations at each level. The effectiveness of our method is demonstrated through MV classification and retrieval.

Image re-ranking, as an effective way to improve the results of web-based image search, has been adopted by current commercial search engines such as Bing and Google. Given a query keyword, a pool of images are first retrieved based on textual information. By asking the user to select a query image from the pool, the remaining images are re-ranked based on their visual similarities with the query image. A major challenge is that the similarities of visual features do not well correlate with images' semantic meanings which interpret users' search intention. Recently people proposed to match images in a semantic space which used attributes or reference classes closely related to the semantic meanings of images as basis. However, learning a universal visual semantic space to characterize highly diverse images from the web is difficult and inefficient. In this paper, we propose a novel image re-ranking framework, which automatically offline learns different semantic spaces for different query keywords. The visual features of images are projected into their related semantic spaces to get semantic signatures. At the online stage, images are re-ranked by comparing their semantic signatures obtained from the semantic space specified by the query keyword. The proposed query-specific semantic signatures significantly improve both the accuracy and efficiency of image re-ranking. The original visual features of thousands of dimensions can be projected to the semantic signatures as short as 25 dimensions. Experimental results show that 25-40 percent relative improvement has been achieved on re-ranking precisions compared with the state-of-the-art methods.

The performance of a generic pedestrian detector may drop significantly when it is applied to a specific scene due to the mismatch between the source training set and samples from the target scene. We propose a new approach of automatically transferring a generic pedestrian detector to a scene-specific detector in static video surveillance without manually labeling samples from the target scene. The proposed transfer learning framework consists of four steps. 1) Through exploring the indegrees from target samples to source samples on a visual affinity graph, the source samples are weighted to match the distribution of target samples. 2) It explores a set of context cues to automatically select samples from the target scene, predicts their labels, and computes confidence scores to guide transfer learning. 3) The confidence scores propagate among target samples according to their underlying visual structures. 4) Target samples with higher confidence scores have larger influence on training scene-specific detectors. All these considerations are formulated under a single objective function called confidence-encoded SVM, which avoids hard thresholding on confidence scores. During test, only the appearance-based detector is used without context cues. The effectiveness is demonstrated through experiments on two video surveillance data sets. Compared with a generic detector, it improves the detection rates by 48 and 36 percent at one false positive per image (FPPI) on the two data sets, respectively. The training process converges after one or two iterations on the data sets in experiments.

Collective motions of crowds are common in nature and have attracted a great deal of attention in a variety of multidisciplinary fields. Collectiveness, which indicates the degree of individuals acting as a union, is a fundamental and universal measurement for various crowd systems. By quantifying the topological structures of collective manifolds of crowd, this paper proposes a descriptor of collectiveness and its efficient computation for the crowd and its constituent individuals. The Collective Merging algorithm is then proposed to detect collective motions from random motions. We validate the effectiveness and robustness of the proposed collectiveness on the system of self-driven particles as well as other real crowd systems such as pedestrian crowds and bacteria colony. We compare the collectiveness descriptor with human perception for collective motion and show their high consistency. As a universal descriptor, the proposed crowd collectiveness can be used to compare different crowd systems. It has a wide range of applications, such as detecting collective motions from crowd clutters, monitoring crowd dynamics, and generating maps of collectiveness for crowded scenes. A new Collective Motion Database, which consists of 413 video clips from 62 crowded scenes, is released to the public.

We present a lesion detection and characterization method for (18)F-fluorodeoxyglucose positron emission tomography-computed tomography (FDG PET-CT) images of the thorax in the evaluation of patients with primary nonsmall cell lung cancer (NSCLC) with regional nodal disease. Lesion detection can be difficult due to low contrast between lesions and normal anatomical structures. Lesion characterization is also challenging due to similar spatial characteristics between the lung tumors and abnormal lymph nodes. To tackle these problems, we propose a context driven approximation (CDA) method. There are two main components of our method. First, a sparse representation technique with region-level contexts was designed for lesion detection. To discriminate low-contrast data with sparse representation, we propose a reference consistency constraint and a spatial consistent constraint. Second, a multi-atlas technique with image-level contexts was designed to represent the spatial characteristics for lesion characterization. To accommodate inter-subject variation in a multi-atlas model, we propose an appearance constraint and a similarity constraint. The CDA method is effective with a simple feature set, and does not require parametric modeling of feature space separation. The experiments on a clinical FDG PET-CT dataset show promising performance improvement over the state-of-the-art.

In this paper, we propose a new approach for matching images observed in different camera views with complex cross-view transforms and apply it to person re-identification. It jointly partitions the image spaces of two camera views into different configurations according to the similarity of cross-view transforms. The visual features of an image pair from different views are first locally aligned by being projected to a common feature space and then matched with softly assigned metrics which are locally optimized. The features optimal for recognizing identities are different from those for clustering cross-view transforms. They are jointly learned by utilizing sparsity-inducing norm and information theoretical regularization. This approach can be generalized to the settings where test images are from new camera views, not the same as those in the training set. Extensive experiments are conducted on public datasets and our own dataset. Comparisons with the state-of-the-art metric learning and person re-identification methods show the superior performance of our approach.

In this paper, we address the challenging problem of detecting pedestrians who appear in groups and have interaction. A new approach is proposed for single-pedestrian detection aided by multi-pedestrian detection. A mixture model of multi-pedestrian detectors is designed to capture the unique visual cues which are formed by nearby multiple pedestrians but cannot be captured by single-pedestrian detectors. A probabilistic framework is proposed to model the relationship between the configurations estimated by single-and multi-pedestrian detectors, and to refine the single-pedestrian detection result with multi-pedestrian detection. It can integrate with any single-pedestrian detector without significantly increasing the computation load. 15 state-of-the-art single-pedestrian detection approaches are investigated on three widely used public datasets: Caltech, TUD-Brussels and ETH. Experimental results show that our framework significantly improves all these approaches. The average improvement is 9% on the Caltech-Test dataset, 11% on the TUD-Brussels dataset and 17% on the ETH dataset in terms of average miss rate. The lowest average miss rate is reduced from 48% to 43% on the Caltech-Test dataset, from 55% to 50% on the TUD-Brussels dataset and from 51% to 41% on the ETH dataset.

Detecting pedestrians in cluttered scenes is a challenging problem in computer vision. The difficulty is added when several pedestrians overlap in images and occlude each other. We observe, however, that the occlusion/visibility statuses of overlapping pedestrians provide useful mutual relationship for visibility estimation - the visibility estimation of one pedestrian facilitates the visibility estimation of another. In this paper, we propose a mutual visibility deep model that jointly estimates the visibility statuses of overlapping pedestrians. The visibility relationship among pedestrians is learned from the deep model for recognizing co-existing pedestrians. Experimental results show that the mutual visibility deep model effectively improves the pedestrian detection results. Compared with existing image-based pedestrian detection approaches, our approach has the lowest average miss rate on the Caltech-Train dataset, the Caltech-Test dataset and the ETH dataset. Including mutual visibility leads to 4% - 8% improvements on multiple benchmark datasets.

We propose a new approach for estimation of the positions of facial key points with three-level carefully designed convolutional networks. At each level, the outputs of multiple networks are fused for robust and accurate estimation. Thanks to the deep structures of convolutional networks, global high-level features are extracted over the whole face region at the initialization stage, which help to locate high accuracy key points. There are two folds of advantage for this. First, the texture context information over the entire face is utilized to locate each key point. Second, since the networks are trained to predict all the key points simultaneously, the geometric constraints among key points are implicitly encoded. The method therefore can avoid local minimum caused by ambiguity and data corruption in difficult image samples due to occlusions, large pose variations, and extreme lightings. The networks at the following two levels are trained to locally refine initial predictions and their inputs are limited to small regions around the initial predictions. Several network structures critical for accurate and robust facial point detection are investigated. Extensive experiments show that our approach outperforms state-of-the-art methods in both detection accuracy and reliability.

Human eyes can recognize person identities based on some small salient regions. However, such valuable salient information is often hidden when computing similarities of images with existing approaches. Moreover, many existing approaches learn discriminative features and handle drastic viewpoint change in a supervised way and require labeling new training data for a different pair of camera views. In this paper, we propose a novel perspective for person re-identification based on unsupervised salience learning. Distinctive features are extracted without requiring identity labels in the training procedure. First, we apply adjacency constrained patch matching to build dense correspondence between image pairs, which shows effectiveness in handling misalignment caused by large viewpoint and pose variations. Second, we learn human salience in an unsupervised manner. To improve the performance of person re-identification, human salience is incorporated in patch matching to find reliable and discriminative matched patches. The effectiveness of our approach is validated on the widely used VIPeR dataset and ETHZ dataset.

Collective motions are common in crowd systems and have attracted a great deal of attention in a variety of multidisciplinary fields. Collectiveness, which indicates the degree of individuals acting as a union in collective motion, is a fundamental and universal measurement for various crowd systems. By integrating path similarities among crowds on collective manifold, this paper proposes a descriptor of collectiveness and an efficient computation for the crowd and its constituent individuals. The algorithm of the Collective Merging is then proposed to detect collective motions from random motions. We validate the effectiveness and robustness of the proposed collectiveness descriptor on the system of self-driven particles. We then compare the collectiveness descriptor to human perception for collective motion and show high consistency. Our experiments regarding the detection of collective motions and the measurement of collectiveness in videos of pedestrian crowds and bacteria colony demonstrate a wide range of applications of the collectiveness descriptor.

We propose a new Deep Decompositional Network (DDN) for parsing pedestrian images into semantic regions, such as hair, head, body, arms, and legs, where the pedestrians can be heavily occluded. Unlike existing methods based on template matching or Bayesian inference, our approach directly maps low-level visual features to the label maps of body parts with DDN, which is able to accurately estimate complex pose variations with good robustness to occlusions and background clutters. DDN jointly estimates occluded regions and segments body parts by stacking three types of hidden layers: occlusion estimation layers, completion layers, and decomposition layers. The occlusion estimation layers estimate a binary mask, indicating which part of a pedestrian is invisible. The completion layers synthesize low-level features of the invisible part from the original features and the occlusion mask. The decomposition layers directly transform the synthesized visual features to label maps. We devise a new strategy to pre-train these hidden layers, and then fine-tune the entire network using the stochastic gradient descent. Experimental results show that our approach achieves better segmentation accuracy than the state-of-the-art methods on pedestrian images with or without occlusions. Another important contribution of this paper is that it provides a large scale benchmark human parsing dataset that includes 3,673 annotated samples collected from 171 surveillance videos. It is 20 times larger than existing public datasets.

Recent works have shown that facial attributes are useful in a number of applications such as face recognition and retrieval. However, estimating attributes in images with large variations remains a big challenge. This challenge is addressed in this paper. Unlike existing methods that assume the independence of attributes during their estimation, our approach captures the interdependencies of local regions for each attribute, as well as the high-order correlations between different attributes, which makes it more robust to occlusions and misdetection of face regions. First, we have modeled region interdependencies with a discriminative decision tree, where each node consists of a detector and a classifier trained on a local region. The detector allows us to locate the region, while the classifier determines the presence or absence of an attribute. Second, correlations of attributes and attribute predictors are modeled by organizing all of the decision trees into a large sum-product network (SPN), which is learned by the EM algorithm and yields the most probable explanation (MPE) of the facial attributes in terms of the region's localization and classification. Experimental results on a large data set with 22,400 images show the effectiveness of the proposed approach.

Feature extraction, deformation handling, occlusion handling, and classification are four important components in pedestrian detection. Existing methods learn or design these components either individually or sequentially. The interaction among these components is not yet well explored. This paper proposes that they should be jointly learned in order to maximize their strengths through cooperation. We formulate these four components into a joint deep learning framework and propose a new deep network architecture. By establishing automatic, mutual interaction among components, the deep model achieves a 9% reduction in the average miss rate compared with the current best-performing pedestrian detection approaches on the largest Caltech benchmark dataset.

This paper proposes modeling the complex web image collections with an automatically generated graph structure called visual semantic complex network (VSCN). The nodes on this complex network are clusters of images with both visual and semantic consistency, called semantic concepts. These nodes are connected based on the visual and semantic correlations. Our VSCN with 33,240 concepts is generated from a collection of 10 million web images. A great deal of valuable information on the structures of the web image collections can be revealed by exploring the VSCN, such as the small-world behavior, concept community, in-degree distribution, hubs, and isolated concepts. It not only helps us better understand the web image collections at a macroscopic level, but also has many important practical applications. This paper presents two application examples: content-based image retrieval and image browsing. Experimental results show that the VSCN leads to significant improvement on both the precision of image retrieval (over 200%) and user experience for image browsing.

This paper proposes a hybrid convolutional network (ConvNet)-Restricted Boltzmann Machine (RBM) model for face verification in wild conditions. A key contribution of this work is to directly learn relational visual features, which indicate identity similarities, from raw pixels of face pairs with a hybrid deep network. The deep ConvNets in our model mimic the primary visual cortex to jointly extract local relational visual features from two face images compared with the learned filter pairs. These relational features are further processed through multiple layers to extract high-level and global features. Multiple groups of ConvNets are constructed in order to achieve robustness and characterize face similarities from different aspects. The top-layer RBM performs inference from complementary high-level features extracted from different ConvNet groups with a two-level average pooling hierarchy. The entire hybrid deep network is jointly fine-tuned to optimize for the task of face verification. Our model achieves competitive face verification performance on the LFW dataset.

Cascaded classifiers have been widely used in pedestrian detection and achieved great success. These classifiers are trained sequentially without joint optimization. In this paper, we propose a new deep model that can jointly train multi-stage classifiers through several stages of back propagation. It keeps the score map output by a classifier within a local region and uses it as contextual information to support the decision at the next stage. Through a specific design of the training strategy, this deep architecture is able to simulate the cascaded classifiers by mining hard samples to train the network stage-by-stage. Each classifier handles samples at a different difficulty level. Unsupervised pre-training and specifically designed stage-wise supervised training are used to regularize the optimization problem. Both theoretical analysis and experimental results show that the training strategy helps to avoid over fitting. Experimental results on three datasets (Caltech, ETH and TUD-Brussels) show that our approach outperforms the state-of-the-art approaches.

Human salience is distinctive and reliable information in matching pedestrians across disjoint camera views. In this paper, we exploit the pair wise salience distribution relationship between pedestrian images, and solve the person re-identification problem by proposing a salience matching strategy. To handle the misalignment problem in pedestrian images, patch matching is adopted and patch salience is estimated. Matching patches with inconsistent salience brings penalty. Images of the same person are recognized by minimizing the salience matching cost. Furthermore, our salience matching is tightly integrated with patch matching in a unified structural Rank SVM learning framework. The effectiveness of our approach is validated on the VIPeR dataset and the CUHK Campus dataset. It outperforms the state-of-the-art methods on both datasets.

Face recognition with large pose and illumination variations is a challenging problem in computer vision. This paper addresses this challenge by proposing a new learning based face representation: the face identity-preserving (FIP) features. Unlike conventional face descriptors, the FIP features can significantly reduce intra-identity variances, while maintaining discriminative ness between identities. Moreover, the FIP features extracted from an image under any pose and illumination can be used to reconstruct its face image in the canonical view. This property makes it possible to improve the performance of traditional descriptors, such as LBP [2] and Gabor [31], which can be extracted from our reconstructed images in the canonical view to eliminate variations. In order to learn the FIP features, we carefully design a deep network that combines the feature extraction layers and the reconstruction layer. The former encodes a face image into the FIP features, while the latter transforms them to an image in the canonical view. Extensive experiments on the large MultiPIE face database [7] demonstrate that it significantly outperforms the state-of-the-art face recognition methods.

Web image re-ranking aims to automatically refine the initial text-based image search results by employing visual information. A strong line of work in image re-ranking relies on building image graphs that requires computing distances between image pairs. In this paper, we present Anchor Concept Graph Distance (ACG Distance), a novel distance measure for image re-ranking. For a given textual query, an Anchor Concept Graph (ACG) is automatically learned from the initial text-based search results. The nodes of the ACG (i.e., anchor concepts) and their correlations well model the semantic structure of the images to be re-ranked. Images are projected to the anchor concepts. The projection vectors undergo a diffusion process over the ACG, and then are used to compute the ACG distance. The ACG distance reduces the semantic gap and better represents distances between images. Experiments on the MSRA-MM and INRIA datasets show that the ACG distance consistently outperforms existing distance measures and significantly improves start-of-the-art methods in image re-ranking.

In this paper, we propose a framework of transforming images from a source image space to a target image space, based on learning coupled dictionaries from a training set of paired images. The framework can be used for applications such as image super-resolution and estimation of image intrinsic components (shading and albedo). It is based on a local parametric regression approach, using sparse feature representations over learned coupled dictionaries across the source and target image spaces. After coupled dictionary learning, sparse coefficient vectors of training image patch pairs are partitioned into easily retrievable local clusters. For any test image patch, we can fast index into its closest local cluster and perform a local parametric regression between the learned sparse feature spaces. The obtained sparse representation (together with the learned target space dictionary) provides multiple constraints for each pixel of the target image to be estimated. The final target image is reconstructed based on these constraints. The contributions of our proposed framework are three-fold. 1) We propose a concept of coupled dictionary learning based on coupled sparse coding which requires the sparse coefficient vectors of a pair of corresponding source and target image patches to have the same support, i.e., the same indices of nonzero elements. 2) We devise a space partitioning scheme to divide the high-dimensional but sparse feature space into local clusters. The partitioning facilitates extremely fast retrieval of closest local clusters for query patches. 3) Benefiting from sparse feature-based image transformation, our method is more robust to corrupted input data, and can be considered as a simultaneous image restoration and transformation process. Experiments on intrinsic image estimation and super-resolution demonstrate the effectiveness and efficiency of our proposed method.

Manifold learning concerns the local manifold structure of high dimensional data, and many related algorithms are developed to improve image classification performance. None of them, however, consider both the relationships among pixels in images and the geometrical properties of various images during learning the reduced space. In this paper, we propose a linear approach, called two-dimensional maximum local variation (2DMLV), for face recognition. In 2DMLV, we encode the relationships among pixels in images using the image Euclidean distance instead of conventional Euclidean distance in estimating the variation of values of images, and then incorporate the local variation, which characterizes the diversity of images and discriminating information, into the objective function of dimensionality reduction. Extensive experiments demonstrate the effectiveness of our approach.

Automatically counting vehicles in complex traffic scenes from videos is challenging. Detection and tracking algorithms may fail due to occlusions, scene clutters, and large variations of viewpoints and vehicle types. We propose a new approach of counting vehicles through exploiting contextual regularities from scene structures. It breaks the problem into simpler problems, which count vehicles on each path separately. The model of each path and its source and sink add strong regularization on the motion and the sizes of vehicles and can thus significantly improve the accuracy of vehicle counting. Our approach is based on tracking and clustering feature points and can be summarized in threefold. First, an algorithm is proposed to automatically learn the models of scene structures. A traffic scene is segmented into local semantic regions by exploiting the temporal cooccurrence of local motions. Local semantic regions are connected into global complete paths using the proposed fast marching algorithm. Sources and sinks are estimated from the models of semantic regions. Second, an algorithm is proposed to cluster trajectories of feature points into objects and to estimate average vehicle sizes at different locations from initial clustering results. Third, trajectories of features points are often fragmented due to occlusions. By integrating the spatiotemporal features of trajectory clusters with contextual models of paths and sources and sinks, trajectory clusters are assigned into different paths and connected into complete trajectories. Experimental results on a complex traffic scene show the effectiveness of our approach.

In this paper, we propose two kinds of semantic signatures for 3D object retrieval (3DOR). Humans are capable of describing an object using attribute terms like “symmetric” and “flyable”, or using its similarities to some known object classes. We convert such qualitative descriptions into attribute signature (AS) and reference set signature (RSS), respectively, and use them for 3DOR. We also show that AS and RSS can be understood as two different quantization methods of the same semantic space of human descriptions of objects. The advantages of the semantic signatures are threefold. First, they are much more compact than low-level shape features yet working with comparable retrieval accuracy. Therefore, the proposed semantic signatures require less storage space and computation cost in retrieval. Second, the high-level signatures are a good complement to low-level shape features. As a result, by incorporating the signatures we can improve the performance of state-of-the-art 3DOR methods by a large margin. To the best of our knowledge, we obtain the best results on two popular benchmarks. Third, the AS enables us to build a user-friendly interface, with which the user can trigger a search by simply clicking attribute bars instead of finding a 3D object as the query. This interface is of great significance in 3DOR considering the fact that while searching, the user usually does not have a 3D query at hand that is similar to his/her targeted objects in the database.

Automatically assessing photo quality from the perspective of visual aesthetics is of great interest in high-level vision research and has drawn much attention in recent years. In this paper, we propose content-based photo quality assessment using both regional and global features. Under this framework, subject areas, which draw the most attentions of human eyes, are first extracted. Then regional features extracted from both subject areas and background regions are combined with global features to assess photo quality. Since professional photographers adopt different photographic techniques and have different aesthetic criteria in mind when taking different types of photos (e.g., landscape versus portrait), we propose to segment subject areas and extract visual features in different ways according to the variety of photo content. We divide the photos into seven categories based on their visual content and develop a set of new subject area extraction methods and new visual features specially designed for different categories. The effectiveness of this framework is supported by extensive experimental comparisons of existing photo quality assessment approaches as well as our new features on different categories of photos. In addition, we propose an approach of online training an adaptive classifier to combine the proposed features according to the visual content of a test photo without knowing its category. Another contribution of this work is to construct a large and diversified benchmark dataset for the research of photo quality assessment. It includes 17,673 photos with manually labeled ground truth. This new benchmark dataset can be down loaded at http://mmlab.ie.cuhk.edu.hk/CUHKPQ/Dataset.htm.

We present an approach to synthesize the subtle 3D relief and texture of oil painting brush strokes from a single photograph. This task is unique from traditional synthesize algorithms due to its mixed modality between the input and output; i.e., our goal is to synthesize surface normals given an intensity image input. To accomplish this task, we propose a framework that first applies intrinsic image decomposition to produce a pair of initial normal maps. These maps are combined into a conditional random field (CRF) optimization framework that incorporates additional information derived from a training set consisting of normals captured using photometric stereo on oil paintings with similar brush styles. Additional constraints are incorporated into the CRF framework to further ensures smoothness and preserve brush stroke edges. Our results show that this approach can produce compelling reliefs that are often indistinguishable from results captured using photometric stereo.

This paper investigates how to parse (segment) facial components from face images which may be partially occluded. We propose a novel face parser, which recasts segmentation of face components as a cross-modality data transformation problem, i.e., transforming an image patch to a label map. Specifically, a face is represented hierarchically by parts, components, and pixel-wise labels. With this representation, our approach first detects faces at both the part- and component-levels, and then computes the pixel-wise label maps (Fig.1). Our part-based and component-based detectors are generatively trained with the deep belief network (DBN), and are discriminatively tuned by logistic regression. The segmentators transform the detected face components to label maps, which are obtained by learning a highly nonlinear mapping with the deep autoencoder. The proposed hierarchical face parsing is not only robust to partial occlusions but also provide richer information for face analysis and face synthesis compared with face keypoint detection and face alignment. The effectiveness of our algorithm is shown through several tasks on 2, 239 images selected from three datasets (e.g., LFW [12], BioID [13] and CUFSF [29]).

Part-based models have demonstrated their merit in object detection. However, there is a key issue to be solved on how to integrate the inaccurate scores of part detectors when there are occlusions or large deformations. To handle the imperfectness of part detectors, this paper presents a probabilistic pedestrian detection framework. In this framework, a deformable part-based model is used to obtain the scores of part detectors and the visibilities of parts are modeled as hidden variables. Unlike previous occlusion handling approaches that assume independence among visibility probabilities of parts or manually define rules for the visibility relationship, a discriminative deep model is used in this paper for learning the visibility relationship among overlapping parts at multiple layers. Experimental results on three public datasets (Caltech, ETH and Daimler) and a new CUHK occlusion dataset1specially designed for the evaluation of occlusion handling approaches show the effectiveness of the proposed approach.

The performance of a generic pedestrian detector may drop significantly when it is applied to a specific scene due to mismatch between the source dataset used to train the detector and samples in the target scene. In this paper, we investigate how to automatically train a scene-specific pedestrian detector starting with a generic detector in video surveillance without further manually labeling any samples under a novel transfer learning framework. It tackles the problem from three aspects. (1) With a graphical representation and through exploring the indegrees from target samples to source samples, the source samples are properly re-weighted. The indegrees detect the boundary between the distributions of the source dataset and the target dataset. The re-weighted source dataset better matches the target scene. (2) It takes the context information from motions, scene structures and scene geometry as the confidence scores of samples from the target scene to guide transfer learning. (3) The confidence scores propagate among samples on a graph according to the underlying visual structures of samples. All these considerations are formulated under a single objective function called Confidence-Encoded SVM. At the test stage, only the appearance-based detector is used without the context cues. The effectiveness of the proposed framework is demonstrated through experiments on two video surveillance datasets. Compared with a generic pedestrian detector, it significantly improves the detection rate by 48% and 36% at one false positive per image on the two datasets respectively.

In this paper, a new Mixture model of Dynamic pedestrian-Agents (MDA) is proposed to learn the collective behavior patterns of pedestrians in crowded scenes. Collective behaviors characterize the intrinsic dynamics of the crowd. From the agent-based modeling, each pedestrian in the crowd is driven by a dynamic pedestrian-agent, which is a linear dynamic system with its initial and termination states reflecting a pedestrian's belief of the starting point and the destination. Then the whole crowd is modeled as a mixture of dynamic pedestrian-agents. Once the model is unsupervisedly learned from real data, MDA can simulate the crowd behaviors. Furthermore, MDA can well infer the past behaviors and predict the future behaviors of pedestrians given their trajectories only partially observed, and classify different pedestrian behaviors in the scene. The effectiveness of MDA and its applications are demonstrated by qualitative and quantitative experiments on the video surveillance dataset collected from the New York Grand Central Station.

This paper presents a framework for semantically segmenting a target image without tags by searching for references in an image database, where all the images are unsegmented but annotated with tags. We jointly segment the target image and its references by optimizing both semantic consistencies within individual images and correspondences between the target image and each of its references. In our framework, we first retrieve two types of references with a semantic-driven scheme: i) the compatible references which share similar global appearance with the target image; and ii) the competitive references which have distinct appearance to the target image but similar tags with one of the compatible references. The two types of references have complementary information for assisting the segmentation of the target image. Then we construct a novel graphical representation, in which the vertices are superpixels extracted from the target image and its references. The segmentation problem is posed as labeling all the vertices with the semantic tags obtained from the references. The method is able to label images without the pixel-level annotation and classifier training, and it outperforms the state-of-the-arts approaches on the MSRC-21 database.

Human perception of music and image are highly correlated. Both of them can inspire human sensation like emotion and power. This paper investigates how to model the relationship between music and image using 47,888 music-image pairs extracted from music videos. We have two basic observations for this relationship: 1) music space exhibits simpler cluster structure than image space, and 2) the relationship between the two spaces is complex and nonlinear. Based on these observations, we develop Multiple Ranking Canonical Correlation Analysis (MR-CCA) to learn such relationship. MR-CCA clusters the music-image pairs according to their music parts, and then conducts Ranking CCA (R-CCA) for each cluster. Compared with classical CCA, R-CCA takes account of the pairwise ranking information available in our dataset. MR-CCA improves performance and significantly reduce computational cost. Experiment results show that R-CCA outperforms CCA, and MR-CCA has the best performance with a consistency score of 84.52% with human labeling. The proposed method can be generalized to model cross media relationship and has potential applications in video generation, background music recommendation, and joint retrieval of music and image.

Web-scale image search engines (e.g., Google image search, Bing image search) mostly rely on surrounding text features. It is difficult for them to interpret users' search intention only by query keywords and this leads to ambiguous and noisy search results which are far from satisfactory. It is important to use visual information in order to solve the ambiguity in text-based image retrieval. In this paper, we propose a novel Internet image search approach. It only requires the user to click on one query image with minimum effort and images from a pool retrieved by text-based search are reranked based on both visual and textual content. Our key contribution is to capture the users' search intention from this one-click query image in four steps. 1) The query image is categorized into one of the predefined adaptive weight categories which reflect users' search intention at a coarse level. Inside each category, a specific weight schema is used to combine visual features adaptive to this kind of image to better rerank the text-based search result. 2) Based on the visual content of the query image selected by the user and through image clustering, query keywords are expanded to capture user intention. 3) Expanded keywords are used to enlarge the image pool to contain more relevant images. 4) Expanded keywords are also used to expand the query image to multiple positive visual examples from which new query specific visual and textual similarity metrics are learned to further improve content-based image reranking. All these steps are automatic, without extra effort from the user. This is critically important for any commercial web-based image search engine, where the user interface has to be extremely simple. Besides this key contribution, a set of visual features which are both effective and efficient in Internet image search are designed. Experimental evaluation shows that our approach significantly improves the precision of top-ranked images and also the user experience.

Image re-ranking, as an effective way to improve the results of web-based image search, has been adopted by current commercial search engines. Given a query keyword, a pool of images are first retrieved by the search engine based on textual information. By asking the user to select a query image from the pool, the remaining images are re-ranked based on their visual similarities with the query image. A major challenge is that the similarities of visual features do not well correlate with images' semantic meanings which interpret users' search intention. On the other hand, learning a universal visual semantic space to characterize highly diverse images from the web is difficult and inefficient. In this paper, we propose a novel image re-ranking framework, which automatically offline learns different visual semantic spaces for different query keywords through keyword expansions. The visual features of images are projected into their related visual semantic spaces to get semantic signatures. At the online stage, images are re-ranked by comparing their semantic signatures obtained from the visual semantic space specified by the query keyword. The new approach significantly improves both the accuracy and efficiency of image re-ranking. The original visual features of thousands of dimensions can be projected to the semantic signatures as short as 25 dimensions. Experimental results show that 20% - 35% relative improvement has been achieved on re-ranking precisions compared with the state-of-the-art methods.

Automatic face photo-sketch recognition has important applications for law enforcement. Recent research has focused on transforming photos and sketches into the same modality for matching or developing advanced classification algorithms to reduce the modality gap between features extracted from photos and sketches. In this paper, we propose a new inter-modality face recognition approach by reducing the modality gap at the feature extraction stage. A new face descriptor based on coupled information-theoretic encoding is used to capture discriminative local face structures and to effectively match photos and sketches. Guided by maximizing the mutual information between photos and sketches in the quantized feature spaces, the coupled encoding is achieved by the proposed coupled information-theoretic projection tree, which is extended to the randomized forest to further boost the performance. We create the largest face sketch database including sketches of 1, 194 people from the FERET database. Experiments on this large scale dataset show that our approach significantly outperforms the state-of-the-art methods.

As having multiple images of an object is practically convenient nowadays, to jointly align them is important for subsequent studies and a wide range of applications. In this paper, we propose a model-based approach to jointly align a batch of images of a face undergoing a variety of geometric and appearance variations. The principal idea is to model the non-rigid deformation of a face by means of a learned deformable model. Different from existing model-based methods such as Active Appearance Models, the proposed one does not rely on an accurate appearance model built from a training set. We propose a robust fitting method that simultaneously identifies the appearance space of the input face and brings the images into alignment. The experiments conducted on images in the wild in comparison with competing methods demonstrate the effectiveness of our method in joint alignment of complex objects like human faces.

In this paper, a Random Field Topic (RFT) model is proposed for semantic region analysis from motions of objects in crowded scenes. Different from existing approaches of learning semantic regions either from optical flows or from complete trajectories, our model assumes that fragments of trajectories (called tracklets) are observed in crowded scenes. It advances the existing Latent Dirichlet Allocation topic model, by integrating the Markov random fields (MRF) as prior to enforce the spatial and temporal coherence between tracklets during the learning process. Two kinds of MRF, pairwise MRF and the forest of randomly spanning trees, are defined. Another contribution of this model is to include sources and sinks as high-level semantic prior, which effectively improves the learning of semantic regions and the clustering of tracklets. Experiments on a large scale data set, which includes 40, 000+ tracklets collected from the crowded New York Grand Central station, show that our model outperforms state-of-the-art methods both on qualitative results of learning semantic regions and on quantitative results of clustering tracklets.

Optical flow estimation is a fundamental and ill-posed problem in computer vision. To recover a dense flow field, appropriate spatial constraints have to be enforced. Recent advances exploit higher order spatial regularization, and achieve the top performance on the Middlebury benchmark. In this work, we revisit learning-based approach, and propose a learned sparse model to patch-wisely regularize the flow field. In particular, our method is based on multi-scale spatial regularization, which benefits from first-order spatial regularity and our learned, higher order sparse model. To obtain accurate flow estimation, we propose a sequential optimization scheme to solve the corresponding energy minimization problem. Moreover, as the errors in intermediate flow estimates are usually dense with large variations, we further propose flow-driven and image-driven approaches to address the problem of outliers. Experiments on the Middlebury benchmark show that our method is competitive with the state-of-the-art.

Automatically assessing photo quality from the perspective of visual aesthetics is of great interest in high-level vision research and has drawn much attention in recent years. In this paper, we propose content-based photo quality assessment using regional and global features. Under this framework, subject areas, which draw the most attentions of human eyes, are first extracted. Then regional features extracted from subject areas and the background regions are combined with global features to assess the photo quality. Since professional photographers may adopt different photographic techniques and may have different aesthetic criteria in mind when taking different types of photos (e.g. landscape versus portrait), we propose to segment regions and extract visual features in different ways according to the categorization of photo content. Therefore we divide the photos into seven categories based on their content and develop a set of new subject area extraction methods and new visual features, which are specially designed for different categories. This argument is supported by extensive experimental comparisons of existing photo quality assessment approaches as well as our new regional and global features over different categories of photos. Our new features significantly outperform the state-of-the-art methods. Another contribution of this work is to construct a large and diversified benchmark database for the research of photo quality assessment. It includes 17, 613 photos with manually labeled ground truth.

Humans are capable of describing objects using attributes, such as "the object looks circular and is man-made". Motivated by these high-level descriptions, we build a user-friendly 3D object retrieval system, where the user can browse the database and search for targeted objects using semantic attributes. The main advantage of our system is that it does not require the user to find or sketch a 3D object as the query for 3D object retrieval. Besides, to the best of our knowledge, our system has obtained the best retrieval performance on three popular benchmarks.

We propose a novel approach for activity analysis in multiple synchronized but uncalibrated static camera views. In this paper, we refer to activities as motion patterns of objects, which correspond to paths in far-field scenes. We assume that the topology of cameras is unknown and quite arbitrary, the fields of views covered by these cameras may have no overlap or any amount of overlap, and objects may move on different ground planes. Using low-level cues, objects are first tracked in each camera view independently, and the positions and velocities of objects along trajectories are computed as features. Under a probabilistic model, our approach jointly learns the distribution of an activity in the feature spaces of different camera views. Then, it accomplishes the following tasks: 1) grouping trajectories, which belong to the same activity but may be in different camera views, into one cluster; 2) modeling paths commonly taken by objects across multiple camera views; and 3) detecting abnormal activities. Advantages of this approach are that it does not require first solving the challenging correspondence problem, and that learning is unsupervised. Even though correspondence is not a prerequisite, after the models of activities have been learned, they can help to solve the correspondence problem, since if two trajectories in different camera views belong to the same activity, they are likely to correspond to the same object. Our approach is evaluated on a simulated data set and two very large real data sets, which have 22,951 and 14,985 trajectories, respectively.

We propose a novel unsupervised learning framework to model activities and interactions in crowded and complicated scenes. Hierarchical Bayesian models are used to connect three elements in visual surveillance: low-level visual features, simple "atomic" activities, and interactions. Atomic activities are modeled as distributions over low-level visual features, and multi-agent interactions are modeled as distributions over atomic activities. These models are learnt in an unsupervised way. Given a long video sequence, moving pixels are clustered into different atomic activities and short video clips are clustered into different interactions. In this paper, we propose three hierarchical Bayesian models, Latent Dirichlet Allocation (LDA) mixture model, Hierarchical Dirichlet Process (HDP) mixture model, and Dual Hierarchical Dirichlet Processes (Dual-HDP) model. They advance existing language models, such as LDA [1] and HDP [2]. Our data sets are challenging video sequences from crowded traffic scenes and train station scenes with many kinds of activities co-occurring. Without tracking and human labeling effort, our framework completes many challenging visual surveillance tasks of board interest such as: (1) discovering typical atomic activities and interactions; (2) segmenting long video sequences into different interactions; (3) segmenting motions into different activities; (4) detecting abnormality; and (5) supporting high-level queries on activities and interactions.

In this paper, we propose a novel face photo-sketch synthesis and recognition method using a multiscale Markov Random Fields (MRF) model. Our system has three components: 1) given a face photo, synthesizing a sketch drawing; 2) given a face sketch drawing, synthesizing a photo; and 3) searching for face photos in the database based on a query sketch drawn by an artist. It has useful applications for both digital entertainment and law enforcement. We assume that faces to be studied are in a frontal pose, with normal lighting and neutral expression, and have no occlusions. To synthesize sketch/photo images, the face region is divided into overlapping patches for learning. The size of the patches decides the scale of local face structures to be learned. From a training set which contains photo-sketch pairs, the joint photo-sketch model is learned at multiple scales using a multiscale MRF model. By transforming a face photo to a sketch (or transforming a sketch to a photo), the difference between photos and sketches is significantly reduced, thus allowing effective matching between the two in face sketch recognition. After the photo-sketch transformation, in principle, most of the proposed face photo recognition approaches can be applied to face sketch recognition in a straightforward way. Extensive experiments are conducted on a face sketch database including 606 faces, which can be downloaded from our Web site (http://mmlab.ie.cuhk.edu.hk/facesketch.html).

We propose a novel nonparametric Bayesian model, dual hierarchical Dirichlet processes (Dual-HDP), for trajectory analysis and semantic region modeling in surveillance settings, in an unsupervised way. In our approach, trajectories are treated as documents and observations of an object on a trajectory are treated as words in a document. Trajectories are clustered into different activities. Abnormal trajectories are detected as samples with low likelihoods. The semantic regions, which are intersections of paths commonly taken by objects, related to activities in the scene are also modeled. Dual-HDP advances the existing hierarchical Dirichlet processes (HDP) language model. HDP only clusters co-occurring words from documents into topics and automatically decides the number of topics. Dual-HDP co-clusters both words and documents. It learns both the numbers of word topics and document clusters from data. Under our problem settings, HDP only clusters observations of objects, while Dual-HDP clusters both observations and trajectories. Experiments are evaluated on two data sets, radar tracks collected from a maritime port and visual tracks collected from a parking lot.

We propose a novel approach for activity analysis in multiple synchronized but uncalibrated static camera views. We assume that the topology of camera views is unknown and quite arbitrary, the fields of views covered by these cameras may have no overlap or any amount of overlap, and objects may move on different ground planes. Using low-level cues, objects are tracked in each of the camera views independently, and the positions and velocities of objects along trajectories are computed as features. Under a generative model, our approach jointly learns the distribution of an activity in the feature spaces of different camera views. It accomplishes two tasks: (1) grouping trajectories in different camera views belonging to the same activity into one cluster; (2) modeling paths commonly taken by objects across camera views. To our knowledge, no prior result of co-clustering trajectories in multiple camera views has been published. Advantages of this approach are that it does not require first solving the challenging correspondence problem, and the learning is unsupervised. Our approach is evaluated on two very large data sets with 22, 951 and 14, 985 trajectories.

We propose a framework for detecting and tracking multiple interacting objects, while explicitly handling the dual problems of fragmentation (an object may be broken into several blobs) and grouping (multiple objects may appear as a single blob). We use foreground blobs obtained by background subtraction from a stationary camera as measurements. The main challenge is to associate blob measurements with objects, given the fragment-object-group ambiguity when the number of objects is variable and unknown, and object-class-specific models are not available. We first track foreground blobs till they merge or split. We then build an inference graph representing merge-split relations between the tracked blobs. Using this graph and a generic object model based on spatial connectedness and coherent motion, we label the tracked blobs as whole objects, fragments of objects or groups of interacting objects. The outputs of our algorithm are entire tracks of objects, which may include corresponding tracks from groups during interactions. Experimental results on multiple video sequences are shown.

We propose a novel unsupervised learning framework for activity perception. To understand activities in complicated scenes from visual data, we propose a hierarchical Bayesian model to connect three elements: low-level visual features, simple "atomic" activities, and multi-agent interactions. Atomic activities are modeled as distributions over low-level visual features, and interactions are modeled as distributions over atomic activities. Our models improve existing language models such as Latent Dirichlet Allocation (LDA) and Hierarchical Dirichlet Process (HDP) by modeling interactions without supervision. Our data sets are challenging video sequences from crowded traffic scenes with many kinds of activities co-occurring. Our approach provides a summary of typical atomic activities and interactions in the scene. Unusual activities and interactions are found, with natural probabilistic explanations. Our method supports flexible high-level queries on activities and interactions using atomic activities as components.

In recent years, the language model Latent Dirichlet Allocation (LDA), which clusters co-occurring words into topics, has been widely appled in the computer vision field. However, many of these applications have difficulty with modeling the spatial and temporal structure among visual words, since LDA assumes that a document is a bag-of-words''. It is also critical to properly designwords'' and “documents” when using a language model to solve vision problems. In this paper, we propose a topic model Spatial Latent Dirichlet Allocation (SLDA), which better encodes spatial structure among visual words that are essential for solving many vision problems. The spatial information is not encoded in the value of visual words but in the design of documents. Instead of knowing the partition of words into documents \textit{a priori}, the word-document assignment becomes a random hidden variable in SLDA. There is a generative procedure, where knowledge of spatial structure can be flexibly added as a prior, grouping visual words which are close in space into the same document. We use SLDA to discover objects from a collection of images, and show it achieves better performance than LDA.

In a work by Wang and Tang (2004), three popular subspace face recognition methods, PCA, Bayes, and LDA were analyzed under the same framework and an unified subspace analysis was proposed. However, since they are all based on a single Gaussian model, a global linear subspace often fails to deliver good performance on the data set with complex intrapersonal variation. They also have to face the problem caused by high dimensional face feature vector and the difficulty in finding optimal parameters for subspace analysis. In this paper, we develop a random mixture model to improve Bayes and LDA subspace analysis. By clustering the intrapersonal difference, the complex intrapersonal variation manifold is learned by a set of local linear intrapersonal subspaces. To boost the system performance, we construct multiple low dimensional subspaces by randomly sampling on the high dimensional feature vector and randomly selecting the parameters for subspace analysis. The effectiveness of our method is demonstrated by experiments on the AR face database containing 2340 face images.

In video surveillance, the faces of interest are often of small size. Image resolution is an important factor affecting face recognition by human and computer. In this paper, we propose a new face hallucination method using eigentransformation. Different from most of the proposed methods based on probabilistic models, this method views hallucination as a transformation between different image styles. We use Principal Component Analysis (PCA) to fit the input face image as a linear combination of the low-resolution face images in the training set. The high-resolution image is rendered by replacing the low-resolution training images with high-resolution ones, while retaining the same combination coefficients. Experiments show that the hallucinated face images are not only very helpful for recognition by humans, but also make the automatic recognition procedure easier, since they emphasize the face difference by adding more high-frequency details.

PCA, LDA, and Bayesian analysis are the three most representative subspace face recognition approaches. In this paper, we show that they can be unified under the same framework. We first model face difference with three components: intrinsic difference, transformation difference, and noise. A unified framework is then constructed by using this face difference model and a detailed subspace analysis on the three components. We explain the inherent relationship among different subspace methods and their unique contributions to the extraction of discriminating information from the face difference. Based on the framework, a unified subspace analysis method is developed using PCA, Bayes, and LDA as three steps. A 3D parameter space is constructed using the three subspace dimensions as axes. Searching through this parameter space, we achieve better recognition performance than standard subspace methods.

Automatic retrieval of face images from police mug-shot databases is critically important for law enforcement agencies. It can effectively help investigators to locate or narrow down potential suspects. However, in many cases, a photo image of a suspect is not available and the best substitute is often a sketch drawing based on the recollection of an eyewitness. We present a novel photo retrieval system using face sketches. By transforming a photo image into a sketch, we reduce the difference between photo and sketch significantly, thus allowing effective matching between the two. Experiments over a data set containing 188 people clearly demonstrate the efficacy of the algorithm.

Through modeling the difference between two face images by three components, intrinsic difference (I), transformation difference (T), and random noise (N), we show that the Bayesian algorithm can successfully separate the main disturbing component, T, from the discriminating component, I, however, at a cost of magnified noise, N. To control the noise, we apply PCA on the original image, then carry out the Bayesian analysis in the reduced PCA space. The new method is shown to be more effective than the standard Bayesian algorithm in experiments using 2000+ face images from the Feret database.

We propose a novel face photo retrieval system using sketch drawings. By transforming a photo image into a sketch, we reduce the difference between photo and sketch significantly, thus allow effective matching between the two. To improve the synthesis performance, we separate shape and texture information in a face photo, and conduct transformation on them respectively. Finally a Bayesian classifier is used to recognize the probing sketch from the synthesized pseudo-sketches. Experiments on a data set containing 606 people clearly demonstrate the efficacy of the algorithm.

We propose a face difference model that decomposes face difference into three components, intrinsic difference, transformation difference, and noise. Using the face difference model and a detailed subspace analysis on the three components we develop a unified framework for subspace analysis. Using this framework we discover the inherent relationship among different subspace methods and their unique contributions to the extraction of discriminating information from the face difference. This eventually leads to the construction of a 3D parameter space that uses three subspace dimensions as axis. Within this parameter space, we develop a unified subspace analysis method that achieves better recognition performance than the standard subspace methods on over 2000 face images from the FERET database.

Automatic retrieval of face images from police mug-shot databases is critically important for law enforcement agencies. It can help investigators to locate or narrow down potential suspects efficiently. However, in many cases, the photo image of a suspect is not available and the best substitute is often a sketch drawing based on the recollection of an eyewitness. We present a novel photo retrieval system using face sketches. By transforming a photo image into a sketch, we reduce the difference between photo and sketch significantly, thus allowing effective matching between the two. Experiments over a data set containing 188 people clearly demonstrate the efficacy of the algorithm.