This paper investigates the task of unsupervised graph domain adaptation, which facilitates the transfer of knowledge from labeled source graphs to unlabeled target graphs. Recent approaches usually utilize graph contrastive learning and pseudo-labeling to learn from unlabeled target data, which could introduce potential biased representations and supervision of target graphs resulting from serious shifts across two domains. Towards this end, we propose a novel framework named Diffusion-guided Unbiased Discriminative Learning (DisCo) for unsupervised graph domain adaptation. The core of our DisCo is to leverage both feature disentanglement and cross-domain diffusion signals to remove the potential biases for target graphs. In particular, we first utilize adversarial feature disentanglement to extract causal features that are orthogonal to domain biases. More importantly, we retrieve the labels of cross-domain source graphs to generate the conditions, which would be utilized to optimize a diffusion model for label denoising. The consistency between pseudo-labels and denoised labels is measured to reduce the potential biases during domain alignment. Extensive experiments on several real-world benchmarks demonstrate that our proposed DisCo consistently outperforms competing state-of-the-art baselines.

With the burst of big data, 2D-3D cross-modal retrieval has received increasing attention, which aims to retrieve relevant data from one modality given the query from the other modality. In this paper, we study an underexplored yet practical problem of semi-supervised 2D-3D cross-modal retrieval, which could suffer from serious label scarcity in real-world applications. Moreover, the huge heterogeneous gap could deteriorate the process of learning from unlabeled data. In this work, we propose a novel approach named Decoupled Discriminative Learning with Bigraph-aware Alignment (DREAM) for semi-supervised 2D-3D cross-modal retrieval. The core of our DREAM is to decouple the label prediction and reliability measurement processes to reduce overconfident samples in discriminative learning. In particular, we enhance a label prediction module with label propagation from labeled samples and additionally introduce a reliability measurement module to learn the scores of predicted labels. To reduce class-related bias, we compare reliability scores with class-specific adaptive thresholds to identify samples for additional learning. In addition, negative labels are estimated for unselected samples, which guides soft semantic learning to make the best use of all the information. To further minimize the heterogeneous gap, we build a bigraph graph that connects cross-modal similar examples and then conduct learning to cluster with most edges kept for alignment. Extensive experiments on several benchmark datasets validate the superiority of the proposed DREAM.

Graph neural networks (GNNs) have gained superior performance in graph-based prediction tasks with a variety of applications such as social analysis and drug discovery. Despite the remarkable progress, their performance often degrades on test graphs with distribution shifts. Existing domain adaptation methods rely on unlabeled test graphs during optimization, limiting their applicability to graphs in the wild. Towards this end, this paper studies the problem of multi-domain generalization on graphs, which utilizes multiple source graphs to learn a GNN with high performance on unseen target graphs. We propose a new approach named Topological Adversarial Learning with Prototypical Mixup (TRACI) to solve the problem. The fundamental principle behind our TRACI is to produce virtual adversarial and mixed graph samples from a data-centric view. In particular, TRACI enhances GNN generalization by employing a gradient-ascent strategy that considers both label prediction entropy and graph topology to craft challenging adversarial samples. Additionally, it generates domain-agnostic node representations by characterizing class-graph pair prototypes through latent distributions and applying multi-sample prototypical Mixup for distribution alignment across graphs. We further provide theoretical analysis showing that TRACI reduces the model's excess risk. Extensive experiments on various benchmark datasets demonstrate that TRACI outperforms state-of-the-art baselines, validating its effectiveness.

Recent years have seen substantial progress in diffusion-based controllable video generation. However, achieving precise control in complex scenarios, including fine-grained object parts, sophisticated motion trajectories, and coherent background movement, remains a challenge. In this paper, we introduce *TrackGo*, a novel approach that leverages free-form masks and arrows for conditional video generation. This method offers users with a flexible and precise mechanism for manipulating video content. We also propose the *TrackAdapter* for control implementation, an efficient and lightweight adapter designed to be seamlessly integrated into the temporal self-attention layers of a pretrained video generation model. This design leverages our observation that the attention map of these layers can accurately activate regions corresponding to motion in videos. Our experimental results demonstrate that our new approach, enhanced by the TrackAdapter, achieves state-of-the-art performance on key metrics such as FVD, FID, and ObjMC scores.

This paper presents the Large Vision Diffusion Transformer (LaVin-DiT), a scalable and unified foundation model designed to tackle over 20 computer vision tasks in a generative framework. Unlike existing large vision models directly adapted from natural language processing architectures, which rely on less efficient autoregressive techniques and disrupt spatial relationships essential for vision data, LaVin-DiT introduces key innovations to optimize generative performance for vision tasks. First, to address the high dimensionality of visual data, we incorporate a spatial-temporal variational autoencoder that encodes data into a continuous latent space. Second, for generative modeling, we develop a joint diffusion transformer that progressively produces vision outputs. Third, for unified multitask training, in-context learning is implemented. Input-target pairs serve as task context, which guides the diffusion transformer to align outputs with specific tasks within the latent space. During inference, a task-specific context set and test data as queries allow LaVin-DiT to generalize across tasks without fine-tuning. Trained on extensive vision datasets, the model is scaled from 0.1B to 3.4B parameters, demonstrating substantial scalability and state-of-the-art performance across diverse vision tasks. This work introduces a novel pathway for large vision foundation models, underscoring the promising potential of diffusion transformers. The code and models are available at https://derrickwang005.github.io/LaVin-DiT/.

Traditional network inference methods, such as Gaussian Graphical Models, which are built on continuity and homogeneity, face challenges when modeling discrete data and heterogeneous frameworks. Furthermore, under high-dimensionality, the parameter estimation of such models can be hindered by the notorious intractability of high-dimensional integrals. In this paper, we introduce a new and flexible device for graphical models, which accommodates diverse data types, including Gaussian, Poisson log-normal, and latent Gaussian copula models. The new device is driven by a new marginally recoverable parametric family, which can be effectively estimated without evaluating the high-dimensional integration in high-dimensional settings thanks to the marginal recoverability. We further introduce a mixture of marginally recoverable models to capture ubiquitous heterogeneous structures. We show the validity of the desirable properties of the models and the effective estimation methods, and demonstrate their advantages over the state-of-the-art network inference methods via extensive simulation studies and a gene regulatory network analysis of real single-cell RNA sequencing data.

This paper studies the problem of graph out-of-distribution generalization, which aims to enhance the performance of graph neural networks (GNNs) under distribution shifts. Existing approaches usually learn graph representations from a casual graph, which may not explicitly utilize environment information explicitly. Furthermore, they could suffer from performance degradation when confusing semantics related to target labels and environments. In this paper, we propose a novel approach named Dual Prompt Learning with Information Bottleneck (DATE) for graph out-of-distribution generalization. The core of our DATE is to utilize dual prompts to extract task-oriented semantics and model distribution shifts, respectively. In particular, we first pre-train a GNN using contrastive learning with pretext tokens introduced. More importantly, we not only introduce a task-oriented prompt based on LLMs to generate environment-invariant representations, but also learn the environment-oriented prompts to simulate subgraphs in different environments. To optimize our prompts, we introduce a graph information bottleneck framework, which minimizes the mutual information between environment-invariant representations and environment semantics with the most semantics preserved. Extensive experiments on various benchmark datasets validate the effectiveness of our DATE against various state-of-the-art approaches.

This work studies the problem of out-of-distribution fluid dynamics modeling. Previous works usually design effective neural operators to learn from mesh-based data structures. However, in real-world applications, they would suffer from distribution shifts from the variance of system parameters and temporal evolution of the dynamical system. In this paper, we propose a novel approach named \underline{P}rompt Evol\underline{u}tion with G\underline{r}aph OD\underline{E} (\method{}) for out-of-distribution fluid dynamics modeling. The core of our \method{} is to learn time-evolving prompts using a graph ODE to adapt spatio-temporal forecasting models to different scenarios. In particular, our \method{} first learns from historical observations and system parameters in the frequency domain to explore multi-view context information, which could effectively initialize prompt embeddings. More importantly, we incorporate the interpolation of observation sequences into a graph ODE, which can capture the temporal evolution of prompt embeddings for model adaptation. These time-evolving prompt embeddings are then incorporated into basic forecasting models to overcome temporal distribution shifts. We also minimize the mutual information between prompt embeddings and observation embeddings to enhance the robustness of our model to different distributions. Extensive experiments on various benchmark datasets validate the superiority of the proposed \method{} in comparison to various baselines.

Leveraging the advances of natural language processing, most recent scene text recognizers adopt an encoder-decoder architecture where text images are first converted to representative features and then a sequence of characters via 'sequential decoding'. However, scene text images suffer from rich noises of different sources such as complex background and geometric distortions which often confuse the decoder and lead to incorrect alignment of visual features at noisy decoding time steps. This paper presents I2C2W, a novel scene text recognition technique that is tolerant to geometric and photometric degradation by decomposing scene text recognition into two inter-connected tasks. The first task focuses on image-to-character (I2C) mapping which detects a set of character candidates from images based on different alignments of visual features in an non-sequential way. The second task tackles character-to-word (C2W) mapping which recognizes scene text by decoding words from the detected character candidates. The direct learning from character semantics (instead of noisy image features) corrects falsely detected character candidates effectively which improves the final text recognition accuracy greatly. Extensive experiments over nine public datasets show that the proposed I2C2W outperforms the state-of-the-art by large margins for challenging scene text datasets with various curvature and perspective distortions. It also achieves very competitive recognition performance over multiple normal scene text datasets.

Fine-grained visual classification (FGVC) which aims at recognizing objects from subcategories is a very challenging task due to the inherently subtle inter-class differences. Most existing works mainly tackle this problem by reusing the backbone network to extract features of detected discriminative regions. However, this strategy inevitably complicates the pipeline and pushes the proposed regions to contain most parts of the objects thus fails to locate the really important parts. Recently, vision transformer (ViT) shows its strong performance in the traditional classification task. The self-attention mechanism of the transformer links every patch token to the classification token. In this work, we first evaluate the effectiveness of the ViT framework in the fine-grained recognition setting. Then motivated by the strength of the attention link can be intuitively considered as an indicator of the importance of tokens, we further propose a novel Part Selection Module that can be applied to most of the transformer architectures where we integrate all raw attention weights of the transformer into an attention map for guiding the network to effectively and accurately select discriminative image patches and compute their relations. A contrastive loss is applied to enlarge the distance between feature representations of confusing classes. We name the augmented transformer-based model TransFG and demonstrate the value of it by conducting experiments on five popular fine-grained benchmarks where we achieve state-of-the-art performance. Qualitative results are presented for better understanding of our model.

Generally, humans are more skilled at perceiving differences between high-quality (HQ) and low-quality (LQ) images than directly judging the quality of a single LQ image. This situation also applies to image quality assessment (IQA). Although recent no-reference (NR-IQA) methods have made great progress to predict image quality free from the reference image, they still have the potential to achieve better performance since HQ image information is not fully exploited. In contrast, full-reference (FR-IQA) methods tend to provide more reliable quality evaluation, but its practicability is affected by the requirement for pixel-level aligned reference images. To address this, we firstly propose the content-variant reference method via knowledge distillation (CVRKD-IQA). Specifically, we use non-aligned reference (NAR) images to introduce various prior distributions of high-quality images. The comparisons of distribution differences between HQ and LQ images can help our model better assess the image quality. Further, the knowledge distillation transfers more HQ-LQ distribution difference information from the FR-teacher to the NAR-student and stabilizing CVRKD-IQA performance. Moreover, to fully mine the local-global combined information, while achieving faster inference speed, our model directly processes multiple image patches from the input with the MLP-mixer. Cross-dataset experiments verify that our model can outperform all NAR/NR-IQA SOTAs, even reach comparable performance than FR-IQA methods on some occasions. Since the content-variant and non-aligned reference HQ images are easy to obtain, our model can support more IQA applications with its robustness to content variations. Our code is available: https://github.com/guanghaoyin/CVRKD-IQA.

We present a new neighbor sampling method on temporal graphs. In a temporal graph, predicting different nodes' time-varying properties can require the receptive neigh-borhood of various temporal scales. In this work, we propose the TNS (Time-aware Neighbor Sampling) method: TNS learns from temporal information to provide an adaptive receptive neighborhood for every node at any time. Learning how to sample neighbors is non-trivial, since the neighbor indices in time order are discrete and not differentiable. To address this challenge, we transform neighbor indices from discrete values to continuous ones by interpolating the neighbors' messages. TNS can be flexibly incorporated into popular temporal graph networks to improve their effectiveness without increasing their time complexity. TNS can be trained in an end-to-end manner. It requires no extra supervision and is automatically and implicitly guided to sample the neighbors that are most beneficial for prediction. Empirical results on multiple standard datasets show that TNS yields significant gains on edge prediction and node classification.

In this paper, we target at the Fine-grAined human-Centric Tracklet Segmentation (FACTS) problem, where 12 human parts, e.g., face, pants, left-leg, are segmented. To reduce the heavy and tedious labeling efforts, FACTS requires only one labeled frame per video during training. The small size of human parts and the labeling scarcity makes FACTS very challenging. Considering adjacent frames of videos are continuous and human usually do not change clothes in a short time, we explicitly consider the pixel-level and frame-level context in the proposed Temporal Context segmentation Network (TCNet). On the one hand, optical flow is on-line calculated to propagate the pixel-level segmentation results to neighboring frames. On the other hand, frame-level classification likelihood vectors are also propagated to nearby frames. By fully exploiting the pixel-level and frame-level context, TCNet indirectly uses the large amount of unlabeled frames during training and produces smooth segmentation results during inference. Experimental results on four video datasets show the superiority of TCNet over the state-of-the-arts. The newly annotated datasets can be downloaded via http://liusi-group.com/projects/FACTS for the further studies.

Although the single-image super-resolution (SISR) methods have achieved great success on the single degradation, they still suffer performance drop with multiple degrading effects in real scenarios. Recently, some blind and non-blind models for multiple degradations have been explored. However, these methods usually degrade significantly for distribution shifts between the training and test data. Towards this end, we propose a novel conditional hyper-network framework for super-resolution with multiple degradations (named CMDSR), which helps the SR framework learn how to adapt to changes in the degradation distribution of input. We extract degradation prior at the task-level with the proposed ConditionNet, which will be used to adapt the parameters of the basic SR network (BaseNet). Specifically, the ConditionNet of our framework first learns the degradation prior from a support set, which is composed of a series of degraded image patches from the same task. Then the adaptive BaseNet rapidly shifts its parameters according to the conditional features. Moreover, in order to better extract degradation prior, we propose a task contrastive loss to shorten the inner-task distance and enlarge the cross-task distance between task-level features. Without predefining degradation maps, our blind framework can conduct one single parameter update to yield considerable improvement in SR results. Extensive experiments demonstrate the effectiveness of CMDSR over various blind, and even several non-blind methods. The flexible BaseNet structure also reveals that CMDSR can be a general framework for a large series of SISR models. Our code is available at https://github.com/guanghaoyin/CMDSR.

Unsupervised domain adaptation (UDA) aims to enhance the generalization capability of a certain model from a source domain to a target domain. Present UDA models focus on alleviating the domain shift by minimizing the feature discrepancy between the source domain and the target domain but usually ignore the class confusion problem. In this work, we propose an Inter-class Separation and Intra-class Aggregation (ISIA) mechanism. It encourages the cross-domain representative consistency between the same categories and differentiation among diverse categories. In this way, the features belonging to the same categories are aligned together and the confusable categories are separated. By measuring the align complexity of each category, we design an Adaptive-weighted Instance Matching (AIM) strategy to further optimize the instance-level adaptation. Based on our proposed methods, we also raise a hierarchical unsupervised domain adaptation framework for cross-domain semantic segmentation task. Through performing the image-level, feature-level, category-level and instance-level alignment, our method achieves a stronger generalization performance of the model from the source domain to the target domain. In two typical cross-domain semantic segmentation tasks, i.e., GTA 5→ Cityscapes and SYNTHIA → Cityscapes, our method achieves the state-of-the-art segmentation accuracy. We also build two cross-domain semantic segmentation datasets based on the publicly available data, i.e., remote sensing building segmentation and road segmentation, for domain adaptive segmentation. Our code, models and datasets are available at https://github.com/HibiscusYB/BAFFT.

Generative adversarial networks (GANs) have achieved remarkable progress in recent years, but the continuously growing scale of models make them challenging to deploy widely in practical applications. In particular, for real-time generation tasks, different devices require generators of different sizes due to varying computing power. In this paper, we introduce slimmable GANs (SlimGANs), which can flexibly switch the width of the generator to accommodate various quality-efficiency trade-offs at runtime. Specifically, we leverage multiple discriminators that share partial parameters to train the slimmable generator. To facilitate the consistency between generators of different widths, we present a stepwise inplace distillation technique that encourages narrow generators to learn from wide ones. As for class-conditional generation, we propose a sliceable conditional batch normalization that incorporates the label information into different widths. Our methods are validated, both quantitatively and qualitatively, by extensive experiments and a detailed ablation study.

Although deep learning based methods have achieved great progress in unsupervised video object segmentation, difficult scenarios (e.g., visual similarity, occlusions, and appearance changing) are still no well-handled. To alleviate these issues, we propose a novel Focus on Foreground Network (F2Net), which delves into the intra-inter frame details for the foreground objects and thus effectively improve the segmentation performance. Specifically, our proposed network consists of three main parts: Siamese Encoder Module, Center Guiding Appearance Diffusion Module, and Dynamic Information Fusion Module. Firstly, we take a siamese encoder to extract the feature representations of paired frames (reference frame and current frame). Then, a Center Guiding Appearance Diffusion Module is designed to capture the inter-frame feature (dense correspondences between reference frame and current frame), intra-frame feature (dense correspondences in current frame), and original semantic feature of current frame. Different from the Anchor Diffusion Network, we establish a Center Prediction Branch to predict the center location of the foreground object in current frame and leverage the center point information as spatial guidance prior to enhance the inter-frame and intra-frame feature extraction, and thus the feature representation considerably focus on the foreground objects. Finally, we propose a Dynamic Information Fusion Module to automatically select relatively important features through three aforementioned different level features. Extensive experiments on DAVIS, Youtube-object, and FBMS datasets show that our proposed F2Net achieves the state-of-the-art performance with significant improvement.

Visual Semantic Embedding (VSE) is a dominant approach for vision-language retrieval, which aims at learning a deep embedding space such that visual data are embedded close to their semantic text labels or descriptions. Recent VSE models use complex methods to better contextualize and aggregate multi-modal features into holistic embeddings. However, we discover that surprisingly simple (but carefully selected) global pooling functions (e.g., max pooling) outperform those complex models, across different feature extractors. Despite its simplicity and effectiveness, seeking the best pooling function for different data modality and feature extractor is costly and tedious, especially when the size of features varies (e.g., text, video). Therefore, we propose a Generalized Pooling Operator (GPO), which learns to automatically adapt itself to the best pooling strategy for different features, requiring no manual tuning while staying effective and efficient. We extend the VSE model using this proposed GPO and denote it as VSE∞.Without bells and whistles, VSE∞ outperforms previous VSE methods significantly on image-text retrieval benchmarks across popular feature extractors. With a simple adaptation, variants of VSE∞ further demonstrate its strength by achieving the new state of the art on two video-text retrieval datasets. Comprehensive experiments and visualizations confirm that GPO always discovers the best pooling strategy and can be a plug-and-play feature aggregation module for standard VSE models. Code and pre-trained models are available at http://jcchen.me/vse_infty/

Convolution has been the core ingredient of modern neural networks, triggering the surge of deep learning in vision. In this work, we rethink the inherent principles of standard convolution for vision tasks, specifically spatial-agnostic and channel-specific. Instead, we present a novel atomic operation for deep neural networks by inverting the aforementioned design principles of convolution, coined as involution. We additionally demystify the recent popular self-attention operator and subsume it into our involution family as an over-complicated instantiation. The proposed involution operator could be leveraged as fundamental bricks to build the new generation of neural networks for visual recognition, powering different deep learning models on several prevalent benchmarks, including ImageNet classification, COCO detection and segmentation, together with Cityscapes segmentation. Our involution-based models improve the performance of convolutional baselines using ResNet-50 by up to 1.6% top-1 accuracy, 2.5% and 2.4% bounding box AP, and 4.7% mean IoU absolutely while compressing the computational cost to 66%, 65%, 72%, and 57% on the above benchmarks, respectively. Code and pre-trained models for all the tasks are available at https://github.com/d-li14/involution.

We present Sparse R-CNN, a purely sparse method for object detection in images. Existing works on object detection heavily rely on dense object candidates, such as k anchor boxes pre-defined on all grids of image feature map of size H × W. In our method, however, a fixed sparse set of learned object proposals, total length of N, are provided to object recognition head to perform classification and location. By eliminating HWk (up to hundreds of thousands) hand-designed object candidates to N (e.g. 100) learnable proposals, Sparse R-CNN completely avoids all efforts related to object candidates design and many-to-one label assignment. More importantly, final predictions are directly output without non-maximum suppression post-procedure. Sparse R-CNN demonstrates accuracy, run-time and training convergence performance on par with the well-established detector baselines on the challenging COCO dataset, e.g., achieving 45.0 AP in standard 3× training schedule and running at 22 fps using ResNet-50 FPN model. We hope our work could inspire re-thinking the convention of dense prior in object detectors. The code is available at: https://github.com/PeizeSun/SparseR-CNN.

Few-shot learning aims to adapt knowledge learned from previous tasks to novel tasks with only a limited amount of labeled data. Research literature on few-shot learning exhibits great diversity, while different algorithms often excel at different few-shot learning scenarios. It is therefore tricky to decide which learning strategies to use under different task conditions. Inspired by the recent success in Automated Machine Learning literature (AutoML), in this paper, we present Meta Navigator, a framework that attempts to solve the aforementioned limitation in few-shot learning by seeking a higher-level strategy and proffer to automate the selection from various few-shot learning designs. The goal of our work is to search for good parameter adaptation policies that are applied to different stages in the network for few-shot classification. We present a search space that covers many popular few-shot learning algorithms in the literature, and develop a differentiable searching and decoding algorithm based on meta-learning that supports gradient-based optimization. We demonstrate the effectiveness of our searching-based method on multiple benchmark datasets. Extensive experiments show that our approach significantly outperforms baselines and demonstrates performance advantages over many state-of-the-art methods.

Retrieving occlusion relation among objects in a single image is challenging due to sparsity of boundaries in image. We observe two key issues in existing works: firstly, lack of an architecture which can exploit the limited amount of coupling in the decoder stage between the two subtasks, namely occlusion boundary extraction and occlusion orientation prediction, and secondly, improper representation of occlusion orientation. In this paper, we propose a novel architecture called Occlusion-shared and Path-separated Network (OPNet), which solves the first issue by exploiting rich occlusion cues in shared high-level features and structured spatial information in task-specific low-level features. We then design a simple but effective orthogonal occlusion representation (OOR) to tackle the second issue. Our method surpasses the state-of-the-art methods by 6.1%/8.3% Boundary-AP and 6.5%/10% Orientation-AP on standard PIOD/BSDS ownership datasets. Code is available at https://github.com/fengpanhe/MT-ORL.

Supervised learning is dominant in person search, but it requires elaborate labeling of bounding boxes and identities. Large-scale labeled training data is often difficult to collect, especially for person identities. A natural question is whether a good person search model can be trained without the need of identity supervision. In this paper, we present a weakly supervised setting where only bounding box annotations are available. Based on this new setting, we provide an effective baseline model termed Region Siamese Networks (R-SiamNets). Towards learning useful representations for recognition in the absence of identity labels, we supervise the R-SiamNet with instance-level consistency loss and cluster-level contrastive loss. For instance-level consistency learning, the R-SiamNet is constrained to extract consistent features from each person region with or without out-of-region context. For cluster-level contrastive learning, we enforce the aggregation of closest instances and the separation of dissimilar ones in feature space. Extensive experiments validate the utility of our weakly supervised method. Our model achieves the rank-1 of 87.1% and mAP of 86.0% on CUHK-SYSU benchmark, which surpasses several fully supervised methods, such as OIM [36] and MGTS [4], by a clear margin. More promising performance can be reached by incorporating extra training data. We hope this work could encourage the future research in this field.

This paper studies the context aggregation problem in semantic image segmentation. The existing researches focus on improving the pixel representations by aggregating the contextual information within individual images. Though impressive, these methods neglect the significance of the representations of the pixels of the corresponding class beyond the input image. To address this, this paper proposes to mine the contextual information beyond individual images to further augment the pixel representations. We first set up a feature memory module, which is updated dynamically during training, to store the dataset-level representations of various categories. Then, we learn class probability distribution of each pixel representation under the supervision of the ground-truth segmentation. At last, the representation of each pixel is augmented by aggregating the dataset-level representations based on the corresponding class probability distribution. Furthermore, by utilizing the stored dataset-level representations, we also propose a representation consistent learning strategy to make the classification head better address intra-class compactness and inter-class dispersion. The proposed method could be effortlessly incorporated into existing segmentation frameworks (e.g., FCN, PSPNet, OCRNet and DeepLabV3) and brings consistent performance improvements. Mining contextual information beyond image allows us to report state-of-the-art performance on various benchmarks: ADE20K, LIP, Cityscapes and COCO-Stuff1.

In this paper, we propose MINE to perform novel view synthesis and depth estimation via dense 3D reconstruction from a single image. Our approach is a continuous depth generalization of the Multiplane Images (MPI) by introducing the NEural radiance fields (NeRF). Given a single image as input, MINE predicts a 4-channel image (RGB and volume density) at arbitrary depth values to jointly reconstruct the camera frustum and fill in occluded contents. The reconstructed and inpainted frustum can then be easily rendered into novel RGB or depth views using differentiable rendering. Extensive experiments on RealEstate10K, KITTI and Flowers Light Fields show that our MINE outperforms state-of-the-art by a large margin in novel view synthesis. We also achieve competitive results in depth estimation on iBims-1 and NYU-v2 without annotated depth supervision. Our source code is available at https://github.com/vincentfung13/MINE.

We address the problem of domain generalizable object detection, which aims to learn a domain-invariant detector from multiple "seen" domains so that it can generalize well to other "unseen" domains. The generalization ability is crucial in practical scenarios especially when it is difficult to collect data. Compared to image classification, domain generalization in object detection has seldom been explored with more challenges brought by domain gaps on both image and instance levels. In this paper, we propose a novel generalizable object detection model, termed Domain-Invariant Disentangled Network (DIDN). In contrast to directly aligning multiple sources, we integrate a disentangled network into Faster R-CNN. By disentangling representations on both image and instance levels, DIDN is able to learn domain-invariant representations that are suitable for generalized object detection. Furthermore, we design a cross-level representation reconstruction to complement this two-level disentanglement so that informative object representations could be preserved. Extensive experiments are conducted on five benchmark datasets and the results demonstrate that our model achieves state-of-the-art performances on domain generalization for object detection.

Most existing convolution neural network (CNN) based super-resolution (SR) methods generate their paired training dataset by artificially synthesizing low-resolution (LR) images from the high-resolution (HR) ones. However, this dataset preparation strategy harms the application of these CNNs in real-world scenarios due to the inherent domain gap between the training and testing data. A popular attempts towards the challenge is unpaired generative adversarial networks, which generate "real" LR counterparts from real HR images using image-to-image translation and then perform super-resolution from "real" LR→SR. Despite great progress, it is still difficult to synthesize perfect "real" LR images for super-resolution. In this paper, we firstly consider the real-world SR problem from the traditional domain adaptation perspective. We propose a novel unpaired SR training framework based on feature distribution alignment, with which we can obtain degradation-indistinguishable feature maps and then map them to HR images. In order to generate better SR images for target LR domain, we introduce several regularization losses to force the aligned feature to locate around the target domain. Our experiments indicate that our SR network obtains the state-of-the-art performance over both blind and unpaired SR methods on diverse datasets.

Autonomous highlight detection is crucial for enhancing the efficiency of video browsing on social media platforms. To attain this goal in a data-driven way, one may often face the situation where highlight annotations are not available on the target video category used in practice, while the supervision on another video category (named as source video category) is achievable. In such a situation, one can derive an effective highlight detector on target video category by transferring the highlight knowledge acquired from source video category to the target one. We call this problem cross-category video highlight detection, which has been rarely studied in previous works. For tackling such practical problem, we propose a Dual-Learner-based Video Highlight Detection (DL-VHD) framework. Under this framework, we first design a Set-based Learning module (SL-module) to improve the conventional pair-based learning by assessing the highlight extent of a video segment under a broader context. Based on such learning manner, we introduce two different learners to acquire the basic distinction of target category videos and the characteristics of highlight moments on source video category, respectively. These two types of highlight knowledge are further consolidated via knowledge distillation. Extensive experiments on three benchmark datasets demonstrate the superiority of the proposed SL-module, and the DL-VHD method outperforms five typical Unsupervised Domain Adaptation (UDA) algorithms on various cross-category highlight detection tasks. Our code is available at https://github.com/ChrisAllenMing/Cross_Category_Video_Highlight.

The nonlocal-based blocks are designed for capturing long-range spatial-temporal dependencies in computer vision tasks. Although having shown excellent performance, they still lack the mechanism to encode the rich, structured information among elements in an image or video. In this paper, to theoretically analyze the property of these nonlocal-based blocks, we provide a new perspective to interpret them, where we view them as a set of graph filters generated on a fully-connected graph. Specifically, when choosing the Chebyshev graph filter, a unified formulation can be derived for explaining and analyzing the existing nonlocal-based blocks (e.g., nonlocal block, nonlocal stage, double attention block). Furthermore, by concerning the property of spectral, we propose an efficient and robust spectral nonlocal block, which can be more robust and flexible to catch long-range dependencies when inserted into deep neural networks than the existing nonlocal blocks. Experimental results demonstrate the clear-cut improvements and practical applicabilities of our method on image classification, action recognition, semantic segmentation, and person re-identification tasks. Code are available at https://github.com/zh460045050/SNL_ICCV2021.

Object detection has recently achieved a breakthrough for removing the last one non-differentiable component in the pipeline, Non-Maximum Suppression (NMS), and building up an end-to-end system. However, what makes for its one-to-one prediction has not been well understood. In this paper, we first point out that one-to-one positive sample assignment is the key factor, while, one-to-many assignment in previous detectors causes redundant predictions in inference. Second, we surprisingly find that even training with one-to-one assignment, previous detectors still produce redundant predictions. We identify that classification cost in matching cost is the main ingredient: (1) previous detectors only consider location cost, (2) by additionally introducing classification cost, previous detectors immediately produce one-to-one prediction during inference. We introduce the concept of score gap to explore the effect of matching cost. Classification cost enlarges the score gap by choosing positive samples as those of highest score in the training iteration and reducing noisy positive samples brought by only location cost. Finally, we demonstrate the advantages of end-to-end object detection on crowded scenes.

Given input images, scene graph generation (SGG) aims to produce comprehensive, graphical representations describing visual relationships among salient objects. Recently, more efforts have been paid to the long tail problem in SGG; however, the imbalance in the fraction of missing labels of different classes, or reporting bias, exacerbating the long tail is rarely considered and cannot be solved by the existing debiasing methods. In this paper we show that, due to the missing labels, SGG can be viewed as a "Learning from Positive and Unlabeled data" (PU learning) problem, where the reporting bias can be removed by recovering the unbiased probabilities from the biased ones by utilizing label frequencies, i.e., the per-class fraction of labeled, positive examples in all the positive examples. To obtain accurate label frequency estimates, we propose Dynamic Label Frequency Estimation (DLFE) to take advantage of training-time data augmentation and average over multiple training iterations to introduce more valid examples. Extensive experiments show that DLFE is more effective in estimating label frequencies than a naive variant of the traditional estimate, and DLFE significantly alleviates the long tail and achieves state-of-the-art debiasing performance on the VG dataset. We also show qualitatively that SGG models with DLFE produce prominently more balanced and unbiased scene graphs. The source code is publicly available.

With the growing number of videos in video sharing platforms, how to facilitate the searching and browsing of the user-generated video has attracted intense attention by multimedia community. To help people efficiently search and browse relevant videos, summaries of videos become important. The prior works in multimodal video summarization mainly explore visual and ASR tokens as two separate sources and struggle to fuse the multimodal information for generating the summaries. However, the time information inside videos is commonly ignored. In this paper, we find that it is important to leverage the timestamps to accurately incorporate multimodal signals for the task. We propose a Time-Aware Multimodal Transformer (TAMT) with a novel short-term order-sensitive attention mechanism. The attention mechanism can attend the inputs differently based on time difference to explore the time information inherent inside video more thoroughly. As such, TAMT can fuse the different modalities better for summarizing the videos. Experiments show that our proposed approach is effective and achieves the state-of-the-art performances on both YouCookII and open-domain How2 datasets.

Graph Contrastive Learning (GCL) has emerged to learn generalizable representations from contrastive views. However, it is still in its infancy with two concerns: 1) changing the graph structure through data augmentation to generate contrastive views may mislead the message passing scheme, as such graph changing action deprives the intrinsic graph structural information, especially the directional structure in directed graphs; 2) since GCL usually uses predefined contrastive views with hand-picking parameters, it does not take full advantage of the contrastive information provided by data augmentation, resulting in incomplete structure information for models learning. In this paper, we design a directed graph data augmentation method called Laplacian perturbation and theoretically analyze how it provides contrastive information without changing the directed graph structure. Moreover, we present a directed graph contrastive learning framework, which dynamically learns from all possible contrastive views generated by Laplacian perturbation. Then we train it using multi-task curriculum learning to progressively learn from multiple easy-to-difficult contrastive views. We empirically show that our model can retain more structural features of directed graphs than other GCL models because of its ability to provide complete contrastive information. Experiments on various benchmarks reveal our dominance over the state-of-the-art approaches.

Temporal Graph Networks (TGNs) are powerful on modeling temporal graph data based on their increased complexity. Higher complexity carries with it a higher risk of overfitting, which makes TGNs capture random noise instead of essential semantic information. To address this issue, our idea is to transform the temporal graphs using data augmentation (DA) with adaptive magnitudes, so as to effectively augment the input features and preserve the essential semantic information. Based on this idea, we present the MeTA (Memory Tower Augmentation) module: a multi-level module that processes the augmented graphs of different magnitudes on separate levels, and performs message passing across levels to provide adaptively augmented inputs for every prediction. MeTA can be flexibly applied to the training of popular TGNs to improve their effectiveness without increasing their time complexity. To complement MeTA, we propose three DA strategies to realistically model noise by modifying both the temporal and topological features. Empirical results on standard datasets show that MeTA yields significant gains for the popular TGN models on edge prediction and node classification in an efficient manner.

Network morphism is an effective learning scheme to morph a well-trained neural network to a new one with the network function completely preserved. However, existing network morphism scheme addresses only basic morphing types on the layer level. In this research, we address the central problem of network morphism at a higher level, i.e., how a convolutional layer can be morphed into an arbitrary module of a neural network. To simplify the representation of a network, we abstract a module as a graph with blobs as vertices and convolutional layers as edges. Based on this graph, the morphing process can be formulated as a graph transformation problem. Two atomic morphing operations are introduced to construct the graphs, based on which modules are classified into two families, i.e., simple morphable modules and complex modules. We present practical morphing solutions for both families, and prove that any module can be morphed from a single convolutional layer. Extensive experiments have been conducted based on the state-of-the-art ResNet on benchmarks to verify the effectiveness of the proposed solution.

Modeling spatial or temporal long-range dependency plays a key role in deep neural networks. Conventional dominant solutions include recurrent operations on sequential data or deeply stacking convolutional layers with small kernel size. Recently, a number of non-local operators (such as self-attention based) have been devised. They are typically generic and can be plugged into many existing network pipelines for globally computing among any two neurons in a feature map. This work proposes a novel non-local operator. It is inspired by the attention mechanism of human visual system, which can quickly attend to important local parts in sight and suppress other less-relevant information. The core of our method is learnable and data-adaptive bilinear attentional transform (BA-Transform), whose merits are three-folds: first, BA-Transform is versatile to model a wide spectrum of local or global attentional operations, such as emphasizing specific local regions. Each BA-Transform is learned in a data-adaptive way; Secondly, to address the discrepancy among features, we further design grouped BA-Transforms, which essentially apply different attentional operations to different groups of feature channels; Thirdly, many existing non-local operators are computation-intensive. The proposed BA-Transform is implemented by simple matrix multiplication and admits better efficacy. For empirical evaluation, we perform comprehensive experiments on two large-scale benchmarks, ImageNet and Kinetics, for image / video classification respectively. The achieved accuracies and various ablation experiments consistently demonstrate significant improvement by large margins.

Recent advances on CNNs are mostly devoted to designing more complex architectures to enhance their representation learning capacity. In this paper, we consider how to improve the basic convolutional feature transformation process of CNNs without tuning the model architectures. To this end, we present a novel self-calibrated convolutions that explicitly expand fields-of-view of each convolutional layers through internal communications and hence enrich the output features. In particular, unlike the standard convolutions that fuse spatial and channel-wise information using small kernels (e.g., 3×3), self-calibrated convolutions adaptively build long-range spatial and inter-channel dependencies around each spatial location through a novel self-calibration operation. Thus, it can help CNNs generate more discriminative representations by explicitly incorporating richer information. Our self-calibrated convolution design is simple and generic, and can be easily applied to augment standard convolutional layers without introducing extra parameters and complexity. Extensive experiments demonstrate that when applying self-calibrated convolutions into different backbones, our networks can significantly improve the baseline models in a variety of vision tasks, including image recognition, object detection, instance segmentation, and keypoint detection, with no need to change the network architectures. We hope this work could provide a promising way for future research in designing novel convolutional feature transformations for improving convolutional networks. Code is available on the project page.

In recent years, video generation has attracted a lot of attention in the computer vision community. Unlike image generation which only focuses on appearance, video generation requires modeling both content information and motion dynamics. In this work, we propose MoFlowGAN, which explicitly models motion dynamics by a content-motion decomposition architecture with an additional flow generator. The decomposition architecture models content and motion separately and is instantiated by a compact variant of BigGAN [1]. Besides, the flow generator generates optical flow directly based on high-level feature maps of adjacent frames as a strong supervision, hence the searching space of motion patterns is highly reduced. Our proposed MoFlowGAN achieves the state-of-the-art results on both MUG facial expression and UCF-101 datasets.

Trajectory similarity computation is a core problem in the field of trajectory data queries. However, the high time complexity of calculating the trajectory similarity has always been a bottleneck in real-world applications. Learning-based methods can map trajectories into a uniform embedding space to calculate the similarity of two trajectories with embeddings in constant time. In this paper, we propose a novel trajectory representation learning framework Traj2SimVec that performs scalable and robust trajectory similarity computation. We use a simple and fast trajectory simplification and indexing approach to obtain triplet training samples efficiently. We make the framework more robust via taking full use of the sub-trajectory similarity information as auxiliary supervision. Furthermore, the framework supports the point matching query by modeling the optimal matching relationship of trajectory points under different distance metrics. The comprehensive experiments on real-world datasets demonstrate that our model substantially outperforms all existing approaches.

Normalization operations are widely used to train deep neural networks, and they can improve both convergence and generalization in most tasks. The theories for normalization's effectiveness and new forms of normalization have always been hot topics in research. To better understand normalization, one question can be whether normalization is indispensable for training deep neural network? In this paper, we study what would happen when normalization layers are removed from the network, and show how to train deep neural networks without normalization layers and without performance degradation. Our proposed method can achieve the same or even slightly better performance in a variety of tasks: image classification in ImageNet, object detection and segmentation in MS-COCO, video classification in Kinetics, and machine translation in WMT English-German, etc. Our study may help better understand the role of normalization layers and can be a competitive alternative to normalization layers. Codes are available.

Weakly supervised object detection has attracted increasing research attention recently. To this end, most existing schemes rely on scoring category-independent region proposals, which is formulated as a multiple instance learning problem. During this process, the proposal scores are aggregated and supervised by only image-level labels, which often fails to locate object boundaries precisely. In this paper, we break through such a restriction by taking a deeper look into the score aggregation stage and propose a Category-aware Spatial Constraint (CSC) scheme for proposals, which is integrated into weakly supervised object detection in an end-to-end learning manner. In particular, we incorporate the global shape information of objects as an unsupervised constraint, which is inferred from build-in foreground-and-background cues, termed Category-specific Pixel Gradient (CPG) maps. Specifically, each region proposal is weighted according to how well it covers the estimated shape of objects. For each category, a multi-center regularization is further introduced to penalize the violations between centers cluster and high-score proposals in a given image. Extensive experiments are done on the most widely-used benchmark Pascal VOC and COCO, which shows that our approach significantly improves weakly supervised object detection without adding new learnable parameters to the existing models nor changing the structures of CNNs.

This paper studies the problem of generalized zero-shot learning which requires the model to train on image-label pairs from some seen classes and test on the task of classifying new images from both seen and unseen classes. In this paper, we propose a novel model that provides a unified framework for three different approaches: visual → semantic mapping, semantic → visual mapping, and metric learning. Specifically, our proposed model consists of a feature generator that can generate various visual features given class embeddings as input, a regressor that maps each visual feature back to its corresponding class embedding, and a discriminator that learns to evaluate the closeness of an image feature and a class embedding. All three components are trained under the combination of cyclic consistency loss and dual adversarial loss. Experimental results show that our model not only preserves higher accuracy in classifying images from seen classes, but also performs better than existing state-of-the-art models in in classifying images from unseen classes.

Multi-person pose estimation is an important but challenging problem in computer vision. Although current approaches have achieved significant progress by fusing the multi-scale feature maps, they pay little attention to enhancing the channel-wise and spatial information of the feature maps. In this paper, we propose two novel modules to perform the enhancement of the information for the multi-person pose estimation. First, a Channel Shuffle Module (CSM) is proposed to adopt the channel shuffle operation on the feature maps with different levels, promoting cross-channel information communication among the pyramid feature maps. Second, a Spatial, Channel-wise Attention Residual Bottleneck (SCARB) is designed to boost the original residual unit with attention mechanism, adaptively highlighting the information of the feature maps both in the spatial and channel-wise context. The effectiveness of our proposed modules is evaluated on the COCO keypoint benchmark, and experimental results show that our approach achieves the state-of-the-art results.

Deep neural networks perform better when they are deeper. Network morphism is one of the paradigms to construct deeper neural networks. It makes developing deeper neural networks building on existing ones possible by morphing a well-trained neural network into a new one with the network function completely preserved. The morphed network also has the potential to continue growing into a more powerful one as it has more parameters. Existing network morphism schemes include Net2Net and NetMorph. However, both of them suffer from significant initial performance drop when the morphed network is continually trained. Such unstability is very much undesired for a continual learning system. In this research, we first identify the reason for the unstability, which is due to the large amount of zeros padded into the parameters. Based on this observation, we propose an algorithm based on modified gradient descent to decompose the network morphism equation. As a result, the morphed parameters are all non-zeros and the continual training process become stable. Experimental results on benchmark datasets demonstrate the effectiveness of the proposed stable network morphism scheme.

Most existing object detection algorithms are trained based upon a set of fully annotated object regions or bounding boxes, which are typically labor-intensive. On the contrary, nowadays there is a significant amount of image-level annotations cheaply available on the Internet. It is hence a natural thought to explore such "weak" supervision to benefit the training of object detectors. In this paper, we propose a novel scheme to perform weakly supervised object localization, termed object-specific pixel gradient (OPG). The OPG is trained by using image-level annotations alone, which performs in an iterative manner to localize potential objects in a given image robustly and efficiently. In particular, we first extract an OPG map to reveal the contributions of individual pixels to a given object category, upon which an iterative mining scheme is further introduced to extract instances or components of this object. Moreover, a novel average and max pooling layer is introduced to improve the localization accuracy. In the task of weakly supervised object localization, the OPG achieves a state-of-the-art 44.5% top-5 error on ILSVRC 2013, which outperforms competing methods, including Oquab et al. and region-based convolutional neural networks on the Pascal VOC 2012, with gains of 2.6% and 2.3%, respectively. In the task of object detection, OPG achieves a comparable performance of 27.0% mean average precision on Pascal VOC 2007. In all experiments, the OPG only adopts the off-the-shelf pretrained CNN model, without using any object proposals. Therefore, it also significantly improves the detection speed, i.e., achieving three times faster compared with the state-of-the-art method.

Surveillance video parsing, which segments the video frames into several labels, e.g., face, pants, left-leg, has wide applications [41, 8]. However, pixel-wisely annotating all frames is tedious and inefficient. In this paper, we develop a Single frame Video Parsing (SVP) method which requires only one labeled frame per video in training stage. To parse one particular frame, the video segment preceding the frame is jointly considered. SVP (i) roughly parses the frames within the video segment, (ii) estimates the optical flow between frames and (iii) fuses the rough parsing results warped by optical flow to produce the refined parsing result. The three components of SVP, namely frame parsing, optical flow estimation and temporal fusion are integrated in an end-to-end manner. Experimental results on two surveillance video datasets show the superiority of SVP over state-of-the-arts. The collected video parsing datasets can be downloaded via http://liusi-group.com/projects/SVP for the further studies.

We target at solving the problem of automatic image segmentation. Although 1D contour and 2D surface cues have been widely utilized in existing work, 3D depth information of an image, a necessary cue according to human visual perception, is however overlooked in automatic image segmentation. In this paper, we study how to fully utilize 1D contour, 2D surface, and 3D depth cues for image segmentation. First, three elementary segmentation modules are developed for these cues respectively. The proposed 3D depth cue is able to segment different textured regions even with similar color, and also merge similar textured areas, which cannot be achieved using state-of-the-art approaches. Then, a content-dependent spectral (CDS) graph is proposed for layered affinity models to produce the final segmentation. CDS is designed to build a more reliable relationship between neighboring surface nodes based on the three elementary cues in the spectral graph. Extensive experiments not only show the superior performance of the proposed algorithm over state-of-the-art approaches, but also verify the necessities of these three cues in image segmentation.

In this work we formulate the problem of image captioning as a multimodal translation task. Analogous to machine translation, we present a sequence-to-sequence recurrent neural networks (RNN) model for image caption generation. Different from most existing work where the whole image is represented by convolutional neural network (CNN) feature, we propose to represent the input image as a sequence of detected objects which feeds as the source sequence of the RNN model. In this way, the sequential representation of an image can be naturally translated to a sequence of words, as the target sequence of the RNN model. To represent the image in a sequential way, we extract the objects features in the image and arrange them in a order using convolutional neural networks. To further leverage the visual information from the encoded objects, a sequential attention layer is introduced to selectively attend to the objects that are related to generate corresponding words in the sentences. Extensive experiments are conducted to validate the proposed approach on popular benchmark dataset, i.e., MS COCO, and the proposed model surpasses the state-of-the-art methods in all metrics following the dataset splits of previous work. The proposed approach is also evaluated by the evaluation server of MS COCO captioning challenge, and achieves very competitive results, e.g., a CIDEr of 1.029 (c5) and 1.064 (c40).

How to effectively connect people with information is a fundamental problem in human society. We are now in the era of mobile first, and everything is digitally connected. With the advent of diverse social contents, information feeds have become a new way to connect people with information. Thus, there is a pretty good opportunity for artificial intelligence (AI) to make innovations in this direction. AI can make more efficient and intelligent the creation, moderation, dissemination, searching, consumption, and interaction of information and contents.

In this demo, we present a real-time surveillance video parsing (RSVP) system to parse surveillance videos. Surveillance video parsing, which aims to segment the video frames into several labels, e.g., face, pants, left-legs, has wide applications, especially in security filed. However, it is very tedious and time-consuming to annotate all the frames in a video. We design a RSVP system to parse the surveillance videos in real-time. The RSVP system requires only one labeled frame in training stage. The RSVP system jointly considers the segmentation of preceding frames when parsing one particular frame within the video. The RSVP system is proved to be effective and efficient in real applications.

We present a systematic study on how to morph a well-trained neural network to a new one so that its network function can be completely preserved. We define this as network morphism in this research. After morphing a parent network, the child network is expected to inherit the knowledge from its parent network and also has the potential to continue growing into a more powerful one with much shortened training time. The first requirement for this network morphism is its ability to handle diverse morphing types of networks, including changes of depth, width, kernel size, and even subnet. To meet this requirement, we first introduce the network morphism equations, and then develop novel morphing algorithms for all these morphing types for both classic and convolutional neural networks. The second requirement is its ability to deal with non-linearity in a network. We propose a family of parametric-activation functions to facilitate the morphing of any continuous non-linear activation neurons. Experimental results on benchmark datasets and typical neural networks demonstrate the effectiveness of the proposed network morphism scheme.

In this work, we showcase the Image2Text system, which is a real-time captioning system that can generate human-level natural language description for any input image. We formulate the problem of image captioning as a multimodal translation task. Analogous to machine translation, we present a sequence-to-sequence recurrent neural networks (RNN) model for image caption generation. Different from most existing work where the whole image is represented by a convolutional neural networks (CNN) feature, we propose to represent the input image as a sequence of detected objects to serve as the source sequence of the RNN model. Based on the captioning framework, we develop a user-friendly system to automatically generated human-level captions for users. The system also enables users to detect salient objects in an image, and retrieve similar images and corresponding descriptions from a database.

In this paper, we study oracle character recognition and general sketch recognition. First, a data set of oracle characters, which are the oldest hieroglyphs in China yet remain a part of modern Chinese characters, is collected for analysis. Second, typical visual representations in shape- and sketch-related works are evaluated. We analyze the problems suffered when addressing these representations and determine several representation design criteria. Based on the analysis, we propose a novel hierarchical representation that combines a Gabor-related low-level representation and a sparse-encoder-related mid-level representation. Extensive experiments show the effectiveness of the proposed representation in both oracle character recognition and general sketch recognition. The proposed representation is also complementary to convolutional neural network (CNN)-based models. We introduce a solution to combine the proposed representation with CNN-based models, and achieve better performances over both approaches. This solution has beaten humans at recognizing general sketches.

As the popularity of touch-screen devices, understanding a user's hand-drawn sketch has become an increasingly important research topic in artificial intelligence and computer vision. However, different from natural images, the hand-drawn sketches are often highly abstract, with sparse visual information and large intra-class variance, making the problem more challenging. In this work, we study how to build effective representations for sketch recognition. First, to capture saliency patterns of different scales and spatial arrangements, a Gabor-based low-level representation is proposed. Then, based on this representation, to discovery more complex patterns in a sketch, a Hybrid Multilayer Sparse Coding (HMSC) model is proposed to learn mid-level representations. An improved dictionary learning algorithm is also leveraged in HMSC to reduce overfitting to common but trivial patterns. Extensive experiments show that the proposed representations are highly discriminative and lead to large improvements over the state of the arts.

In this paper we address the problem of visual instance mining, which is to automatically discover frequently appearing visual instances from a large collection of images. We propose a scalable mining method by leveraging the graph structure with images as vertices. Different from most existing work that focused on either instance-level similarities or image-level context properties, our graph captures both information. The instance-level information is integrated during the construction of a weighted and undirected instance graph based on the similarity between augmented local features, while the image-level context is explored with a greedy breadth-first search algorithm to discover clusters of visual instances from the graph. This method is capable of mining challenging small visual instances with diverse variations. We evaluated our method on two fully annotated datasets and outperformed the state of the arts on both datasets with higher recalls. We also applied our method on a one-million Flickr dataset and proved its scalability.

Exploring image structure is a long-standing yet important research subject in the computer vision community. In this paper, we focus on understanding image structure inspired by the “simple-to-complex” biological evidence. A hierarchical shape parsing strategy is proposed to partition and organize image components into a hierarchical structure in the scale space. To improve the robustness and flexibility of image representation, we further bundle the image appearances into hierarchical parsing trees. Image descriptions are subsequently constructed by performing a structural pooling, facilitating efficient matching between the parsing trees. We leverage the proposed hierarchical shape parsing to study two exemplar applications including edge scale refinement and unsupervised “objectness” detection. We show competitive parsing performance comparing to the state-of-the-arts in above scenarios with far less proposals, which thus demonstrates the advantage of the proposed parsing scheme.

The contour-guided color palette (CCP) is proposed for robust image segmentation. It efficiently integrates contour and color cues of an image. To find representative colors of an image, color samples along long contours between regions, similar in spirit to machine learning methodology that focus on samples near decision boundaries, are collected followed by the mean-shift (MS) algorithm in the sampled color space to achieve an image-dependent color palette. This color palette provides a preliminary segmentation in the spatial domain, which is further fine-tuned by post-processing techniques such as leakage avoidance, fake boundary removal, and small region mergence. Segmentation performances of CCP and MS are compared and analyzed. While CCP offers an acceptable standalone segmentation result, it can be further integrated into the framework of layered spectral segmentation to produce a more robust segmentation. The superior performance of CCP-based segmentation algorithm is demonstrated by experiments on the Berkeley Segmentation Dataset.

The explosive growth of touch screens has provided a good platform for sketch-based image retrieval. However, most previous works focused on low level descriptors of shapes and sketches. In this paper, we try to step forward and propose to leverage shape words descriptor for sketch-based image retrieval. First, the shape words are defined and an efficient algorithm is designed for shape words extraction. Then we generalize the classic Chamfer Matching algorithm to address the shape words matching problem. Finally, a novel inverted index structure is proposed to make shape words representation scalable to large scale image databases. Experimental results show that our method achieves competitive accuracy but requires much less memory, e.g., less than 3% of memory storage of MindFinder. Due to its competitive accuracy and low memory cost, our method can scale up to much larger database.

In this work, we introduce the IdeaPanel system, an interactive sketch-based image search engine with millions of images. IdeaPanel enables users to sketch the target image in their minds and also supports tagging to describe their intentions. After a search is triggered, similar images will be returned in real time, based on which users can interactively refine their query sketches until ideal images are returned. Different from existing work, most of which requires a huge amount of memory for indexing and matching, IdeaPanel can achieve very competitive performance but requires much less memory storage. IdeaPanel needs only about 240MB memory to index 1.3M images (less than 3% of previous MindFinder system). Due to its high accuracy and low memory cost, IdealPanel can scale up to much larger database and thus has larger potential to return the most desired images for users.

In this work, we introduce the PPTLens system to convert sketch images captured by smart phones to digital flowcharts in PowerPoint. Different from existing sketch recognition system, which is based on hand-drawn strokes, PPTLens enables users to use sketch images as inputs directly. It's more challenging since strokes extracted from sketch images might not only be very messy, but also without temporal information of the drawings. To implement the 'Image to Object' (I2O) scenario, we propose a novel sketch image recognition framework, including an effective stroke extraction strategy and a novel offline sketch parsing algorithm. By enabling sketch images as inputs, our system makes flowchart/diagram production much more convenient and easier.

In this paper, we study the problem of discovering visual patterns and partial-duplicate images, which is fundamental to visual concept representation and image parsing, but very challenging when the database is extremely large, such as billions of images indexed by a commercial search engine. Although extensive research with sophisticated algorithms has been conducted for either partial-duplicate clustering or visual pattern discovery, most of them can not be easily extended to this scale, since both are clustering problems in nature and require pairwise comparisons. To tackle this computational challenge, we introduce a novel and highly parallelizable framework to discover partial-duplicate images and visual patterns in a unified way in distributed computing systems. We emphasize the nested property of local features, and propose the generalized nested feature (GNF) as a mid-level representation for regions and local patterns. Initial coarse clusters are then discovered by GNFs, upon which$n$-gram GNF is defined to represent co-occurrent visual patterns. After that, efficient merging and refining algorithms are used to get the partial-duplicate clusters, and logical combinations of probabilistic GNF models are leveraged to represent the visual patterns of partially duplicate images. Extensive experiments show the parallelizable property and effectiveness of the algorithms on both partial-duplicate clustering and visual pattern discovery. With 2000 machines, it costs about eight and 400 minutes to process one million and 40 million images respectively, which is quite efficient compared to previous methods.

In this paper, we target at the problem of sketch recognition. We systematically study how to incorporate users' correction and editing into isolated and full sketch recognition. This is a natural and necessary interaction in real systems such as Visio where very similar shapes exist. First, a novel algorithm is proposed to mine the prior shape knowledge for three editing modes. Second, to differentiate visually similar shapes, a novel symbol recognition algorithm is introduced by leveraging the learnt shape knowledge. Then, a novel editing detection algorithm is proposed to facilitate symbol recognition. Furthermore, both of the symbol recognizer and the editing detector are systematically incorporated into the full sketch recognition. Finally, based on the proposed algorithms, a real-time sketch recognition system is built to recognize hand-drawn flowcharts and diagrams with flexible interactions. Extensive experiments show the effectiveness of the proposed algorithms.

In this work, we introduce the SmartVisio system for interactive hand-drawn shape/diagram recognition. Different from existing work, SmartVisio is a real-time sketch recognition system based on Visio, to recognize hand-drawn flowchart/diagram with flexible interactions. This system enables a user to draw shapes or diagrams on the Visio interface, and then the hand-drawn shapes are automatically converted to formal shapes in real-time. To satisfy the interaction needs from common users, we propose an algorithm to detect a user's correction and editing during drawing, and then recognize in real time. We also propose a novel symbol recognition algorithm to better recognize or differentiate some visually similar shapes. By enabling users' natural correction/editing on various shapes, our system makes flowchart/diagram production much more natural and easier.

We study the problem of sketch-based 3D model retrieval, and propose a solution powered by a new query-to-model distance metric and a powerful feature descriptor based on the bag-of-features framework. The main idea of the proposed query-to-model distance metric is to represent a query sketch using a compact set of sample views (called basic views) of each model, and to rank the models in ascending order of the representation errors. To better differentiate between relevant and irrelevant models, the representation is constrained to be essentially a combination of basic views with similar viewpoints. In another aspect, we propose a mid-level descriptor (called BOF-JESC) which robustly characterizes the edge information within junction-centered patches, to extract the salient shape features from sketches or model views. The combination of the query-to-model distance metric and the BOF-JESC descriptor achieves effective results on two latest benchmark datasets.

An effective and efficient image contour detector is highly desired due to its wide applications in computer vision and multimedia retrieval. However, the state-of-the-art image contour detection algorithms are very computationally intensive, and thus impractical for web-scale applications. In this work, we study the relationship between edge detection and contour detection, based on which an edge-based image contour detection algorithm is proposed. This algorithm fully makes use of cheap edge information for efficiency purpose. The experiments on benchmark data sets show that, the proposed contour detector works much faster than existing state-of-the-art algorithms while maintaining high accuracy, and thus suitable for large-scale applications.

In this paper, we showcase the MagicBrush system, a novel painting-based image search engine. This system enables users to draw a color sketch as a query to find images. Different from existing works on sketch-based image retrieval, most of which focus on matching the shape structure without carefully considering other important visual modalities, MagicBrush takes into account the indispensable value of "color" related to "shape", and explores to make use of both the shape and color expectations that users usually have when they're imaging or searching for an image. To achieve this, we 1) develop a user-friendly interface to allow users to easily "paint out" their colorful visual expectations; 2) design a compact feature "color-edge word" to encode both shape and color information in a organic way; and 3) develop a novel matching and index structure to support a real-time response in 6.4 million images. By taking into account both shape and color information, the MagicBrush system helps users to vividly present what they are imagining, and retrieve images in a more natural way.

Because of the popularity of touch-screen devices, it has become a highly desirable feature to retrieve images from a huge repository by matching with a hand-drawn sketch. Although searching images via keywords or an example image has been successfully launched in some commercial search engines of billions of images, it is still very challenging for both academia and industry to develop a sketch-based image retrieval system on a billion-level database. In this work, we systematically study this problem and try to build a system to support query-by-sketch for two billion images. The raw edge pixel and Chamfer matching are selected as the basic representation and matching in this system, owning to the superior performance compared with other methods in extensive experiments. To get a more compact feature and a faster matching, a vector-like Chamfer feature pair is introduced, based on which the complex matching is reformulated as the crossover dot-product of feature pairs. Based on this new formulation, a compact shape code is developed to represent each image/sketch by projecting the Chamfer features to a linear subspace followed by a non-linear source coding. Finally, the multi-probe Kmedoids-LSH is leveraged to index database images, and the compact shape codes are further used for fast reranking. Extensive experiments show the effectiveness of the proposed features and algorithms in building such a sketch-based image search system.

Although the scale of isotropic visual elements such as blobs and interest points, e.g. SIFT[12], has been well studied and adopted in various applications, how to determine the scale of anisotropic elements such as edges is still an open problem. In this paper, we study the scale of edges, and try to answer two questions: 1) what is the scale of edges, and 2) how to calculate it. From the points of human cognition and physical interpretation, we illustrate the existence of the scale of edges and provide a quantitative definition. Then, an automatic edge scale selection approach is proposed. Finally, a cognitive experiment is conducted to validate the rationality of the detected scales. Moreover, the importance of identifying the scale of edges is also shown in applications such as boundary detection and hierarchical edge parsing.

In this work, we study the problem of hand-drawn sketch recognition. Due to large intra-class variations presented in hand-drawn sketches, most of existing work was limited to a particular domain or limited pre-defined classes. Different from existing work, we target at developing a general sketch recognition system, to recognize any semantically meaningful object that a child can recognize. To increase the recognition coverage, a web-scale clipart image collection is leveraged as the knowledge base of the recognition system. To alleviate the problems of intra-class shape variation and inter-class shape ambiguity in this unconstrained situation, a query-adaptive shape topic model is proposed to mine object topics and shape topics related to the sketch, in which, multiple layers of information such as sketch, object, shape, image, and semantic labels are modeled in a generative process. Besides sketch recognition, the proposed topic model can also be used for related applications such as sketch tagging, image tagging, and sketch-based image search. Extensive experiments on different applications show the effectiveness of the proposed topic model and the recognition system.

In this work, we introduce the Sketch2Tag system for hand-drawn sketch recognition. Due to large variations presented in hand-drawn sketches, most of existing work was limited to a particular domain or limited predefined classes. Different from existing work, Sketch2Tag is a general sketch recognition system, towards recognizing any semantically meaningful object that a child can recognize. This system enables a user to draw a sketch on the query panel, and then provides real-time recognition results. To increase the recognition coverage, a web-scale clipart image collection is leveraged as the knowledge base of the recognition system. Better understanding a user's drawing will be of great value to a variety of applications, such as, improving the sketch-based image search by combining the recognition results as textual queries.

Retrieving images to match with a hand-drawn sketch query is a highly desired feature, especially with the popularity of devices with touch screens. Although query-by-sketch has been extensively studied since 1990s, it is still very challenging to build a real-time sketch-based image search engine on a large-scale database due to the lack of effective and efficient matching/indexing solutions. The explosive growth of web images and the phenomenal success of search techniques have encouraged us to revisit this problem and target at solving the problem of web-scale sketch-based image retrieval. In this work, a novel index structure and the corresponding raw contour-based matching algorithm are proposed to calculate the similarity between a sketch query and natural images, and make sketch-based image retrieval scalable to millions of images. The proposed solution simultaneously considers storage cost, retrieval accuracy, and efficiency, based on which we have developed a real-time sketch-based image search engine by indexing more than 2 million images. Extensive experiments on various retrieval tasks (basic shape search, specific image search, and similar image search) show better accuracy and efficiency than state-of-the-art methods.

Automatic object detection for an arbitrary class is an important but very challenging problem, due to the countless kinds of objects in the world and the large amount of labeling work for each object. In this work, we target at solving the problem of automatic object detection for an arbitrary class without the laborious human effort. Motivated by the explosive growth of Web images and the phenomenal success of search techniques, we develop an unsupervised object detection framework by automatically training the object detector on the top returns of certain image search engine queried by the name of the object class. In order to automatically isolate the objects from the Web images for training, only clipart images with simple background are used, which preserve most of the shape information of the objects. A two-stage shape-based clustering algorithm is proposed to mine typical shapes of the object, in which the inner-class variance of object shapes is considered and undesired images are filtered out. In order to reduce the gap between clipart images and real-world images, we introduce an efficient algorithm to synthesize the real-world images from clipart images, and only shape feature is used in the detector training part. Finally, the synthetic images could be used to train object detectors by an off-the-shelf discriminative algorithm, e.g., boosting or SVM. Extensive experiments show the effectiveness of the proposed framework on objects with simple and representative shapes, and the proposed framework could be considered as a good beginning of solving this challenging problem.

In this paper, we introduce the Sketch2Cartoon system, which is an automatic cartoon making system by leveraging a novel sketch-based clipart image search engine. Different from existing work, most of which either limited users to the pre-prepared characters or only used keyword queries to search materials, Sketch2Cartoon enables users to sketch major curves of characters and props in their mind, and real-time search results from millions of clipart images could be selected to compose the cartoon images. The selected components are vectorized and thus could be further edited. By enabling sketch-based input, the cartoon image making process becomes more natural, and even a child who is too young to read or write can draw whatever he/she imagines and get interesting cartoon images.

In this paper, we study the problem of large scale image retrieval by developing a new class of bag-of-features to encode geometric information of objects within an image. Beyond existing orderless bag-of-features, local features of an image are first projected to different directions or points to generate a series of ordered bag-of-features, based on which different families of spatial bag-of-features are designed to capture the invariance of object translation, rotation, and scaling. Then the most representative features are selected based on a boosting-like method to generate a new bag-of-features-like vector representation of an image. The proposed retrieval framework works well in image retrieval task owing to the following three properties: 1) the encoding of geometric information of objects for capturing objects' spatial transformation, 2) the supervised feature selection and combination strategy for enhancing the discriminative power, and 3) the representation of bag-of-features for effective image matching and indexing for large scale image retrieval. Extensive experiments on 5000 Oxford building images and 1 million Panoramio images show the effectiveness and efficiency of the proposed features as well as the retrieval framework.

Dictionary generation is a core technique of the bag-of-visual-words (BOV) models when applied to image categorization. Most of previous approaches generate dictionaries by unsupervised clustering techniques, e.g. k-means. However, the features obtained by such kind of dictionaries may not be optimal for image classification. In this paper, we propose a probabilistic model for supervised dictionary learning (SDLM) which seamlessly combines an unsuper-vised model (a Gaussian Mixture Model) and a supervised model (a logistic regression model) in a probabilistic framework. In the model, image category information directly affects the generation of a dictionary. A dictionary obtained by this approach is a trade-off between minimization of distortions of clusters and maximization of discriminative power of image-wise representations, i.e. histogram representations of images. We further extend the model to incorporate spatial information during the dictionary learning process in a spatial pyramid matching like manner. We extensively evaluated the two models on various benchmark dataset and obtained promising results.

Specific images refer to images one has a certain episodic memory about, e.g. a picture one has ever seen before. Specific image retrieval is a frequent daily information need and the episodic memory is the key to find a specific image. In this paper, we propose a novel semantic sketch-based interface to incorporate the episodic memory for specific image retrieval. The interface allows a user to specify the semantic category and rough area/color of the objects in his memory. To bridge the semantic gap between the query sketch and database images, in the back end, a sampling method selects exemplars from a reference dataset which contains many object instances with user-provided tags and bounding boxes. After that, an exemplar matching algorithm ranks images to retrieve the target image to match the user's memory. In practice, we have observed that query sketches are usually error prone. That is, the position or the color of an object may not be accurate. Meanwhile, the annotations in the reference dataset are also noisy. Thus, the search algorithm has to handle two kinds of errors: 1) reference dataset label noise; 2) user sketch error such as position or scale. For the former, we propose a robust sampling method. For the latter, we derive an efficient spatial reranking algorithm to tolerate inaccurate user sketches. Detailed experimental results on the LabelMe dataset show that the proposed approach is robust to both kinds of errors.

In this paper, we showcase the MindFinder system, which is an interactive sketch-based image search engine. Different from existing work, most of which is limited to a small scale database or only enables single modality input, MindFinder is a sketch-based multimodal search engine for million-level database. It enables users to sketch major curves of the target image in their mind, and also supports tagging and coloring operations to better express their search intentions. Owning to a friendly interface, our system supports multiple actions, which help users to flexibly design their queries. After each operation, top returned images are updated in real time, based on which users could interactively refine their initial thoughts until ideal images are returned. The novelty of the MindFinder system includes the following two aspects: 1) A multimodal searching scheme is proposed to retrieve images which meet users' requirements not only in structure, but also in semantic meaning and color tone. 2) An indexing framework is designed to make MindFinder scalable in terms of database size, memory cost, and response time. By scaling up the database to more than two million images, MindFinder not only helps users to easily present whatever they are imagining, but also has the potential to retrieve the most desired images in their mind.

Travel route planning is an important step for a tourist to prepare his/her trip. As a common scenario, a tourist usually asks the following questions when he/she is planning his/her trip in an unfamiliar place: 1) Are there any travel route suggestions for a one-day or three-day trip in Beijing? 2) What is the most popular travel path within the Forbidden City? To facilitate a tourist's trip planning, in this paper, we target at solving the problem of automatic travel route planning. We propose to leverage existing travel clues recovered from 20 million geo-tagged photos collected from www.panoramio.com to suggest customized travel route plans according to users' preferences. As the footprints of tourists at memorable destinations, the geo-tagged photos could be naturally used to discover the travel paths within a destination (attractions/landmarks) and travel routes between destinations. Based on the information discovered from geo-tagged photos, we can provide a customized trip plan for a tourist, i.e., the popular destinations to visit, the visiting order of destinations, the time arrangement in each destination, and the typical travel path within each destination. Users are also enabled to specify personal preference such as visiting location, visiting time/season, travel duration, and destination style in an interactive manner to guide the system. Owning to 20 million geo-tagged photos and 200,000 travelogues, an online system has been developed to help users plan travel routes for over 30,000 attractions/landmarks in more than 100 countries and territories. Experimental results show the intelligence and effectiveness of the proposed framework.

In this technical demonstration, we present a novel interactive trip planning system, i.e. Photo2Trip, by leveraging existing travel clues recovered from 20 million geo-tagged photos. Compared with the most common ways of trip planning, such as surveying travelogues and resorting to travel forums, Photo2Trip enables users to plan their trips in a more effective way. To meet users' diverse travel requirements, the system considers the following preferences: travel location (e.g. Beijing, Paris, or New York), travel duration (e.g. a two-day trip or a five-day trip), visiting time (e.g. summer, winter, March, or October), and travel style preference (e.g. prefer historic or prefer scenery sites). According to user requirements, Photo2Trip can automatically recommend popular travel routes among multiple destinations (attractions/ landmarks), and suggest typical internal paths within each destination. Moreover, users are allowed to interactively adjust the suggested plans by adding or removing destinations to get more customized travel routes from the system. Owning to 20 million geo-tagged photos and 200,000 travelogues, Photo2Trip is capable of supporting users plan travel routes for over 30,000 attractions/landmarks in more than 100 countries and territories.

With the prosperity of tourism and Web 2.0 technologies, more and more people have willingness to share their travel experiences on the Web (e.g., weblogs, forums, or Web 2.0 communities). These so-called travelogues contain rich information, particularly including location-representative knowledge such as attractions (e.g., Golden Gate Bridge), styles (e.g., beach, history), and activities (e.g., diving, surfing). The location-representative information in travelogues can greatly facilitate other tourists' trip planning, if it can be correctly extracted and summarized. However, since most travelogues are unstructured and contain much noise, it is difficult for common users to utilize such knowledge effectively. In this paper, to mine location-representative knowledge from a large collection of travelogues, we propose a probabilistic topic model, named as Location-Topic model. This model has the advantages of (1) differentiability between two kinds of topics, i.e., local topics which characterize locations and global topics which represent other common themes shared by various locations, and (2) representation of locations in the local topic space to encode both location-representative knowledge and similarities between locations. Some novel applications are developed based on the proposed model, including (1) destination recommendation for on flexible queries, (2) characteristic summarization for a given destination with representative tags and snippets, and (3) identification of informative parts of a travelogue and enriching such highlights with related images. Based on a large collection of travelogues, the proposed framework is evaluated using both objective and subjective evaluation methods and shows promising results.

In this technical demonstration, we showcase the MindFinder system $-$ a novel image search engine. Different from existing interactive image search engines, most of which only provide image-level relevance feedback, MindFinder enables users to sketch and tag query images at object level. By considering the image database as a huge repository, MindFinder is able to help users present and refine their initial thoughts in their mind, and finally turn thoughts to a beautiful image(s). Multiple actions are enabled for users to flexibly design their queries in a bilateral interactive manner by leveraging the whole image database, including tagging, refining query by dragging and dropping objects from search results, as well as editing objects. After each action, the search results will be updated in real time to provide users up-to-date materials to further formulate the query. By the deliberate but easy design of the query, MindFinder not only tries to enable users to present on the query panel whatever they are imagining, but also returns to users the most similar images to the picture in users' mind. By scaling up the image database to 10 million, MindFinder has the potential to reveal whatever in users' mind, that is where the name MindFinder comes from.

In this paper, we study the problem of nonnegative graph embedding, originally investigated in [14] for reaping the benefits from both nonnegative data factorization and the specific purpose characterized by the intrinsic and penalty graphs [13]. Our contributions are two-fold. On the one hand, we present a multiplicative iterative procedure for nonnegative graph embedding, which significantly reduces the computational cost compared with the iterative procedure in [14] involving the matrix inverse calculation of an M-matrix. On the other hand, the nonnegative graph embedding framework is expressed in a more general way by encoding each datum as a tensor of arbitrary order, which brings a group of byproducts, e.g., nonnegative discriminative tensor factorization algorithm, with admissible time and memory cost. Extensive experiments compared with the state-of-the-art algorithms on nonnegative data factorization, graph embedding, and tensor representation demonstrate the algorithmic properties in computation speed, sparsity, discriminating power, and robustness to realistic image occlusions.

In this paper, we present a multi-label sparse coding framework for feature extraction and classification within the context of automatic image annotation. First, each image is encoded into a so-called supervector, derived from the universal Gaussian Mixture Models on orderless image patches. Then, a label sparse coding based subspace learning algorithm is derived to effectively harness multi-label information for dimensionality reduction. Finally, the sparse coding method for multi-label data is proposed to propagate the multi-labels of the training images to the query image with the sparse ℓ1reconstruction coefficients. Extensive image annotation experiments on the Corel5k and Corel30k databases both show the superior performance of the proposed multi-label sparse coding framework over the state-of-the-art algorithms.

We consider in this paper the problem of large scale natural image classification. As the explosion and popularity of images in the Internet, there are increasing attentions to utilize millions of or even billions of these images for helping image related research. Beyond the opportunities brought by unlimited data, a great challenge is how to design more effective classification methods under these large scale scenarios. Most of existing attempts are based on k-nearest-neighbor method. However, in spite of the optimistic performance in some tasks, this strategy still suffers from that, one single fixed global parameter k is not robust for different object classes from different semantic levels. In this paper, we propose an alternative method, called ℓ1-nearest-neighbor, based on a sparse representation computed by ℓ1-minimization. We first treat a testing sample as a sparse linear combination of all training samples, and then consider the related samples as the nearest neighbors of the testing sample. Finally, we classify the testing sample based on the majority of these neighbors' classes. We conduct extensive experiments on a 1.6 million natural image database on different semantic levels defined based on WordNet, which demonstrate that the proposed ℓ1-nearest-neighbor algorithm outperforms k-nearest-neighbor in two aspects: 1) the robustness of parameter selection for different semantic levels, and 2) the discriminative capability for large scale image classification task.

Defining a lexicon of high-level concepts is the first step for data collection and model construction in concept-based image retrieval. Differences of semantic gaps among concepts are well worth considering. By measuring consistency in visual space and textual space, concepts with small semantic gap can be obtained. Considering so many diverse concepts in large-scale image dataset, we construct a lexica family of high-level concepts with small semantic gap based on different low-level features and different consistency measurements. In this lexica family, the lexica are independent to each other and mutually complementary. It provides helpful suggestions about data collection, feature selection and search model construction for large-scale image retrieval.

We study in this paper the problem of bridging the semantic gap between low-level image features and high-level semantic concepts, which is the key hindrance in content-based image retrieval. Piloted by the rich textual information of Web images, the proposed framework tries to learn a new distance measure in the visual space, which can be used to retrieve more semantically relevant images for any unseen query image. The framework differentiates with traditional distance metric learning methods in the following ways. 1) A ranking-based distance metric learning method is proposed for image retrieval problem, by optimizing the leave-one-out retrieval performance on the training data. 2) To be scalable, millions of images together with rich textual information have been crawled from the Web to learn the similarity measure, and the learning framework particularly considers the indexing problem to ensure the retrieval efficiency. 3) To alleviate the noises in the unbalanced labels of images and fully utilize the textual information, a Latent Dirichlet Allocation based topic-level text model is introduced to define pairwise semantic similarity between any two images. The learnt distance measure can be directly applied to applications such as content-based image retrieval and search-based image annotation. Experimental results on the two applications in a two million Web image database show both the effectiveness and efficiency of the proposed framework.

Query-biased Web page summarization is the summarization of a Web page reflecting the relevance of it to a specific query. It plays an important role in search results representation of Web search engines. In this paper, we propose a learning-based query-biased Web page summarization method. The summarization problem is solved within the typical sentence selection framework. Different from existing Web page summarization methods that use page content or link context alone, both of them are considered as the sources of sentences in this work. Most of existing learning-based summarization methods treat summarization as a sentence classification problem and train a classifier to discriminate between extracted sentences and non-extracted sentences of all training documents. The basic assumption of these methods is that sentences from different documents are comparable with respect to the class information. In contrast to the classification scheme, a ranking scheme is introduced to rank extracted sentences higher than non-extracted sentences of each training document. The underlying assumption that sentences within a document are comparable is weaker and more reasonable than the assumption of classification-based scheme. Extensive results using intrinsic evaluation metrics gauge many aspects of the proposed method.

Automatic image annotation has been an active research topic due to its great importance in image retrieval and management. However, results of the state-of-the-art image annotation methods are often unsatisfactory. Despite continuous efforts in inventing new annotation algorithms, it would be advantageous to develop a dedicated approach that could refine imprecise annotations. In this paper, a novel approach to automatically refining the original annotations of images is proposed. For a query image, an existing image annotation method is first employed to obtain a set of candidate annotations. Then, the candidate annotations are re-ranked and only the top ones are reserved as the final annotations. By formulating the annotation refinement process as a Markov process and defining the candidate annotations as the states of a Markov chain, a content-based image annotation refinement (CIAR) algorithm is proposed to re-rank the candidate annotations. It leverages both corpus information and the content feature of a query image. Experimental results on a typical Corel dataset show not only the validity of the refinement, but also the superiority of the proposed algorithm over existing ones.

In this technical demonstration, we showcase the SBIA system - a search-based image annotation system. At the heart of the system lies a very large-scale image search engine which indexed three million Web images and supports both text and visual queries. Given an image (with initial annotations), SBIA first finds semantically/visually similar images via the search engine, and then mines representative keywords from the retrieved images. These keywords, after annotation rejection and relevance ranking, are finally used to annotate the query image.

In this paper, we propose, IGroup, an efficient and effective algorithm that organizes Web image search results into clusters. IGroup is different from all existing Web image search results clustering algorithms that only cluster the top few images using visual or textual features. Our proposed algorithm first identifies several query-related semantic clusters based on a key phrases extraction algorithm originally proposed for clustering general Web search results. Then, all the resulting images are separated and assigned to corresponding clusters. As a result, all the resulting images are organized into a clustering structure with semantic level. To make the best use of the clustering results, a new user interface (UI) is proposed. Different from existing Web image search interfaces, which show only a limited number of suggested query terms or representative image thumbnails of some clusters, the proposed interface displays both representative thumbnails and appropriate titles of semantically coherent image clusters. Comprehensive user studies have been completed to evaluate both the clustering algorithm and the new UI.

In this demo, we present IGroup, a Web image search engine that organizes the search results into semantic clusters. Different from all existing Web image search results clustering algorithms that only cluster the top few images using visual or textual features, IGroup first identifies several query-related semantic clusters based on a key phrases extraction algorithm originally proposed for clustering general Web search results. Then, all the resulting images are separated and assigned to corresponding clusters. To make the best use of the clustering results, a new user interface is proposed. Please go to http://igroup.msra.cn for real experience.

Image annotation plays an important role in image retrieval and management. However, the results of the state-of-the-art image annotation methods are often unsatisfactory. Therefore, it is necessary to refine the imprecise annotations obtained by existing annotation methods. In this paper, a novel approach to automatically refine the original annotations of images is proposed. On the one hand, for Web images, textual information, e.g. file name and surrounding text, is used to retrieve a set of candidate annotations. On the other hand, for non-Web images that are lack of textual information, a relevance model-based algorithm using visual information is used to decide the candidate annotations. Then, candidate annotations are re-ranked and only the top ones are reserved as the final annotations. To re-rank the annotations, an algorithm using Random Walk with Restarts (RWR) is proposed to leverage both the corpus information and the original confidence information of the annotations. Experimental results on both non-Web images of Corel dataset and Web images of photo forum sites demonstrate the effectiveness of the proposed method.

In this paper, we propose a fully automatic and efficient algorithm for realistic 3D face reconstruction by fusing multiple 2D face images. Firstly, an efficient multi-view 2D face alignment algorithm is utilized to localize the facial points of the face images; and then the intrinsic shape and texture models are inferred by the proposed Syncretized Shape Model (SSM) and Syncretized Texture Model (STM), respectively. Compared with other related works, our proposed algorithm has the following characteristics: 1) the inferred shape and texture are more realistic owing to the constraints and co-enhancement among the multiple images; 2) it is fully automatic, without any user interaction; and 3) the shape and pose parameter estimation is efficient via EM approach and unit quaternion based pose representation, and is also robust as a result of the dynamic correspondence approach. The experimental results show the effectiveness of our proposed algorithm for 3D face reconstruction.