Abstract The potential for higher-resolution image generation using pretrained diffusion models is immense. However, these models often struggle with object repetition and structural artifacts especially when scaling to 4K resolution and beyond. Our analysis reveals that causes the problem, a single prompt for the generation of multiple scales provides insufficient efficacy. To address this, we propose HiPrompt, a new tuning-free solution that tackles the above problems by introducing hierarchical prompts. The hierarchical prompts provide both global and local semantic guidance. Specifically, the global prompt captures overall scene semantics from user input, while local guidance comes from patch-wise descriptions generated by MLLMs to refine regional structures and textures. Furthermore, during inverse denoising, noise is decomposed into low- and high-frequency components, each conditioned on different prompt levels, facilitating prompt-guided denoising under hierarchical semantic guidance. It further allows the generation to focus more on local spatial regions and ensures the generated images maintain coherent local and global semantics, structures, and textures with high definition. Extensive experiments demonstrate that HiPrompt outperforms state-of-the-art works in higher-resolution image generation, significantly reducing object repetition and enhancing structural quality. The demo and code can be found on the project website: https://liuxinyv.github.io/HiPrompt/ .

Xinyu Chen, Yunxin Li, Haoyuan Shi, Baotian Hu, Wenhan Luo, Yaowei Wang, Min Zhang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Photorealistic 3D human modeling is essential for various applications and has seen tremendous progress. However, existing methods for monocular full-body reconstruction, typically relying on front and/or predicted back view, still struggle with satisfactory performance due to the ill-posed nature of the problem and sophisticated self-occlusions. In this paper, we propose PSHuman, a novel framework that explicitly reconstructs human meshes utilizing priors from the multiview diffusion model. It is found that directly applying multiview diffusion on single-view human images leads to severe geometric distortions, especially on generated faces. To address it, we propose a cross-scale diffusion that models the joint probability distribution of global full-body shape and local facial characteristics, enabling identity-preserved novel-view generation without geometric distortion. Moreover, to enhance cross-view body shape consistency of varied human poses, we condition the generative model on parametric models (SMPL-X), which provide body priors and prevent unnatural views inconsistent with human anatomy. Leveraging the generated multiview normal and color images, we present SMPLX-initialized explicit human carving to recover realistic textured human meshes efficiently. Extensive experiments on CAPE and THuman2.1 demonstrate PSHuman’s superiority in geometry details, texture fidelity, and generalization capability.

Video diffusion models have shown great potential in generating high-quality videos, making them an increasingly popular focus. However, their inherent iterative nature leads to substantial computational and time costs. Although techniques such as consistency distillation and adversarial training have been employed to accelerate video diffusion by reducing inference steps, these methods often simply transfer the generation approaches from Image diffusion models to video diffusion models. As a result, these methods frequently fall short in terms of both performance and training stability. In this work, we introduce a two-stage training framework that effectively combines consistency distillation with adversarial training to address these challenges. Additionally, we propose a novel video discriminator design, which eliminates the need for decoding the video latents and improves the final performance. Our model is capable of producing high-quality videos in merely one-step, with the flexibility to perform multi-step refinement for further performance enhancement. Our quantitative evaluation on the OpenVid-1M benchmark shows that our model significantly outperforms existing methods. Notably, our 1-step performance (FVD 171.15) exceeds the 8-step performance of the consistency distillation based method, AnimateLCM (FVD 184.79), and approaches the 25-step performance of advanced Stable Video Diffusion (FVD 156.94).

Style control has been popular in video generation models. Existing methods often generate videos far from the given style, cause content leakage, and struggle to transfer one video to the desired style. Our first observation is that the style extraction stage matters, whereas existing methods emphasize global style but ignore local textures. In order to bring texture features while preventing content leakage, we filter content-related patches while retaining style ones based on prompt-patch similarity; for global style extraction, we generate a paired style dataset through model illusion to facilitate contrastive learning, which greatly enhances the absolute style consistency. Moreover, to fill in the image-to-video gap, we train a lightweight motion adapter on still videos, which implicitly enhances stylization extent, and enables our image-trained model to be seamlessly applied to videos. Benefited from these efforts, our approach, StyleMaster, not only achieves significant improvement in both style resemblance and temporal coherence, but also can easily generalize to video style transfer with a gray tile ControlNet. Extensive experiments and visualizations demonstrate that StyleMaster significantly outperforms competitors, effectively generating high-quality stylized videos that align with textual content and closely resemble the style of reference images.

Controllable character image animation has a wide range of applications. Although existing studies have consistently improved performance, challenges persist in the field of character image animation, particularly concerning stability in complex backgrounds and tasks involving multiple characters. To address these challenges, we propose a novel multi-condition guided framework for character image animation, employing several well-designed input modules to enhance the implicit decoupling capability of the model. First, the optical flow guider calculates the background optical flow map as guidance information, which enables the model to implicitly learn to decouple the background motion into background constants and background momentum during training, and generate a stable background by setting zero background momentum during inference. Second, the depth order guider calculates the order map of the characters, which transforms the depth information into the positional information of multiple characters. This facilitates the implicit learning of decoupling different characters, especially in accurately separating the occluded body parts of multiple characters. Third, the reference pose map is input to enhance the ability to decouple character texture and pose information in the reference image. Furthermore, to fill the gap of fair evaluation of multi-character image animation, we propose a new benchmark comprising about 4,000 frames. Extensive qualitative and quantitative evaluations demonstrate that our method excels in generating high-quality character animations, especially in scenarios of complex backgrounds and multiple characters.

Facial personalization faces challenges to maintain identity fidelity without disrupting the foundation model's prompt consistency. The mainstream personalization models employ identity embedding to integrate identity information within the attention mechanisms. However, our preliminary findings reveal that identity embeddings compromise the effectiveness of other tokens in the prompt, thereby limiting high prompt consistency and attribute-level controllability. Moreover, by deactivating identity embedding, personalization models still demonstrate the underlying foundation models' ability to control facial attributes precisely. It suggests that such foundation models' knowledge can be leveraged to cure the ill-aligned prompt consistency of personalization models. Building upon these insights, we propose FreeCure, a framework that improves the prompt consistency of personalization models with their latent foundation models' knowledge. First, by setting a dual inference paradigm with/without identity embedding, we identify attributes (e.g., hair, accessories, etc.) for enhancements. Second, we introduce a novel foundation-aware self-attention module, coupled with an inversion-based process to bring well-aligned attribute information to the personalization process. Our approach is training-free, and can effectively enhance a wide array of facial attributes; and it can be seamlessly integrated into existing popular personalization models based on both Stable Diffusion and FLUX. FreeCure has consistently shown significant improvements in prompt consistency across these facial personalization models while maintaining the integrity of their original identity fidelity.

Audio-driven human animation methods, such as talking head and talking body generation, have made remarkable progress in generating synchronized facial movements and appealing visual quality videos. However, existing methods primarily focus on single human animation and struggle with multi-stream audio inputs, facing incorrect binding problems between audio and persons. Additionally, they exhibit limitations in instruction-following capabilities. To solve this problem, in this paper, we propose a novel task: Multi-Person Conversational Video Generation, and introduce a new framework, MultiTalk, to address the challenges during multi-person generation. Specifically, for audio injection, we investigate several schemes and propose the Label Rotary Position Embedding (L-RoPE) method to resolve the audio and person binding problem. Furthermore, during training, we observe that partial parameter training and multi-task training are crucial for preserving the instruction-following ability of the base model. MultiTalk achieves superior performance compared to other methods on several datasets, including talking head, talking body, and multi-person datasets, demonstrating the powerful generation capabilities of our approach.

Recently, Transformer networks have demonstrated outstanding performance in the field of image restoration due to the global receptive field and adaptability to input. However, the quadratic computational complexity of Softmax-attention poses a significant limitation on its extensive application in image restoration tasks, particularly for high-resolution images. To tackle this challenge, we propose a novel variant of the Transformer. This variant leverages the Taylor expansion to approximate the Softmax-attention and utilizes the concept of norm-preserving mapping to approximate the remainder of the first-order Taylor expansion, resulting in a linear computational complexity. Moreover, we introduce a multi-branch architecture featuring multi-scale patch embedding into the proposed Transformer, which has four distinct advantages: 1) various sizes of the receptive field; 2) multi-level semantic information; 3) flexible shapes of the receptive field; 4) accelerated training and inference speed. Hence, the proposed model, named the second version of Taylor formula expansion-based Transformer (for short MB-TaylorFormer V2) has the capability to concurrently process coarse-to-fine features, capture long-distance pixel interactions with limited computational cost, and improve the approximation of the Taylor expansion remainder. Experimental results across diverse image restoration benchmarks demonstrate that MB-TaylorFormer V2 achieves state-of-the-art performance in multiple image restoration tasks, such as image dehazing, deraining, desnowing, motion deblurring, and denoising, with very little computational overhead.

Recent advancements in Multimodal Large Language Models (MLLMs) underscore the significance of scalable models and data to boost performance, yet this often incurs substantial computational costs. Although the Mixture of Experts (MoE) architecture has been employed to scale large language or visual-language models efficiently, these efforts typically involve fewer experts and limited modalities. To address this, our work presents the pioneering attempt to develop a unified MLLM with the MoE architecture, named Uni-MoE that can handle a wide array of modalities. Specifically, it features modality-specific encoders with connectors for a unified multimodal representation. We also implement a sparse MoE architecture within the LLMs to enable efficient training and inference through modality-level data parallelism and expert-level model parallelism. To enhance the multi-expert collaboration and generalization, we present a progressive training strategy: 1) Cross-modality alignment using various connectors with different cross-modality data, 2) Training modality-specific experts with cross-modality instruction data to activate experts' preferences, and 3) Tuning the whole Uni-MoE framework utilizing Low-Rank Adaptation (LoRA) on mixed multimodal instruction data. We evaluate the instruction-tuned Uni-MoE on a comprehensive set of multimodal datasets. The extensive experimental results demonstrate Uni-MoE's principal advantage of significantly reducing performance bias in handling mixed multimodal datasets, alongside improved multi-expert collaboration and generalization.

Multi-view clustering (MVC) for remote sensing data has demonstrated significant potential in Earth observation, given its ability to aggregate multi-source information without relying on labels. Despite achieving compelling results through the combination of deep encoders and contrastive learning, existing algorithms still face two limitations: inadequate exploration of diverse spatial relationships and inability to guide the selection of sample pairs leads to blind sampling, both of which lead to suboptimal clustering performance. To tackle these challenges, we propose a sampling enhanced contrastive multi-view clustering method for remote sensing data, namely SEC-LSRM. The proposed method incorporates long- and short-range information mining to enhance clustering performance. By aggregating shortrange information extracted through autoencoders and longrange information obtained via graph autoencoders, our method improves the sampling quality of positive and negative sample pairs. To render the extracted features more compact, a multiview correlation reduction strategy is devised to filter out irrelevant information. With the extracted comprehensive features, an adaptive sampling strategy is designed to obtain high-quality positive and negative samples. Subsequently, we select positive and negative sample pairs based on these affinity matrices with idempotence and block diagonal constraints. Moreover, we integrate the optimization of these sample pairs and contrastive learning within the same framework to achieve iterative updates of both. Experiments conducted on multiple multi-view remote sensing datasets illustrate that our proposed SEC-LSRM method achieves excellent and reliable clustering performance.

Blind face restoration (BFR) aims to recover high-quality (HQ) face images from low-quality (LQ) ones and usually resorts to facial priors for improving restoration performance. However, current methods still suffer from two major difficulties: 1) how to derive a powerful network architecture without extensive hand tuning and 2) how to capture complementary information from multiple facial priors in one network to improve restoration performance. To this end, we propose a face restoration searching network (FRSNet) to adaptively search the suitable feature extraction architecture within our specified search space, which can directly contribute to the restoration quality. On the basis of FRSNet, we further design our multiple facial prior searching network (MFPSNet) with a multiprior learning scheme. MFPSNet optimally extracts information from diverse facial priors and fuses the information into image features, ensuring that both external guidance and internal features are reserved. In this way, MFPSNet takes full advantage of semantic-level (parsing maps), geometric-level (facial heat maps), reference-level (facial dictionaries), and pixel-level (degraded images) information and, thus, generates faithful and realistic images. Quantitative and qualitative experiments show that the MFPSNet performs favorably on both synthetic and real-world datasets against the state-of-the-art (SOTA) BFR methods. The codes are publicly available at: https://github.com/YYJ1anG/MFPSNet.

Despite recent advancements in the Large Reconstruction Model (LRM) demonstrating impressive results, when extending its input from single image to multiple images, it exhibits inefficiencies, subpar geometric and texture quality, as well as slower convergence speed than expected. It is attributed to that, LRM formulates 3D reconstruction as a naive images-to-3D translation problem, ignoring the strong 3D coherence among the input images. In this article, we propose a Multi-view Large Reconstruction Model (M-LRM) designed to reconstruct high-quality 3D shapes from multi-views in a 3D-aware manner. Specifically, we introduce a multi-view consistent cross-attention scheme to enable M-LRM to accurately query information from the input images. Moreover, we employ the 3D priors of the input multi-view images to initialize the triplane tokens. Compared to previous methods, the proposed M-LRM can generate 3D shapes of high fidelity. Experimental studies demonstrate that our model achieves a significant performance gain and faster training convergence.

In this paper, we propose a new setting for generating product descriptions from images, augmented by marketing keywords. It leverages the combined power of visual and textual information to create descriptions that are more tailored to the unique features of products. For this setting, previous methods utilize visual and textual encoders to encode the image and keywords and employ a language model-based decoder to generate the product description. However, the generated description is often inaccurate and generic since same-category products have similar copy-writings, and optimizing the overall framework on large-scale samples makes models concentrate on common words yet ignore the product features. To alleviate the issue, we present a simple and effective Multimodal In-Context Tuning approach, named ModICT, which introduces a similar product sample as the reference and utilizes the in-context learning capability of language models to produce the description. During training, we keep the visual encoder and language model frozen, focusing on optimizing the modules responsible for creating multimodal in-context references and dynamic prompts. This approach preserves the language generation prowess of large language models (LLMs), facilitating a substantial increase in description diversity. To assess the effectiveness of ModICT across various language model scales and types, we collect data from three distinct product categories within the E-commerce domain. Extensive experiments demonstrate that ModICT significantly improves the accuracy (by up to 3.3% on Rouge-L) and diversity (by up to 9.4% on D-5) of generated results compared to conventional methods. Our findings underscore the potential of ModICT as a valuable tool for enhancing the automatic generation of product descriptions in a wide range of applications. Data and code are at https://github.com/HITsz-TMG/Multimodal-In-Context-Tuning

Generating vivid and emotional 3D co-speech gestures is crucial for virtual avatar animation in human-machine interaction applications. While the existing methods enable generating the gestures to follow a single emotion label, they overlook that long gesture sequence modeling with emotion transition is more practical in real scenes. In addition, the lack of large-scale available datasets with emotional transition speech and corresponding 3D human gestures also limits the addressing of this task. To fulfill this goal, we first incorporate the ChatGPT-4 and an audio inpainting approach to construct the high-fidelity emotion transition human speeches. Considering obtaining the realistic 3D pose annotations corresponding to the dynamically inpainted emotion transition audio is extremely difficult, we propose a novel weakly supervised training strategy to encourage authority gesture transitions. Specifically, to enhance the coordination of transition gestures w. r. t. different emotional ones, we model the temporal association representation between two different emotional gesture sequences as style guidance and infuse it into the transition generation. We further devise an emotion mixture mechanism that provides weak supervision based on a learnable mixed emotion label for transition gestures. Last, we present a keyframe sampler to supply effective initial posture cues in long sequences, enabling us to generate diverse gestures. Extensive experiments demonstrate that our method outperforms the state-of-the-art models constructed by adapting single emotion-conditioned counterparts on our newly defined emotion transition task and datasets. Our code and dataset will be released on the project page: https://xingqunqi-lab.github.io/Emo-Transition-Gesture/.

Tracking by natural language specification (TNL) aims to consistently localize a target in a video sequence given a linguistic description in the initial frame. Existing methodologies perform language-based and template-based matching for target reasoning separately and merge the matching results from two sources, which suffer from tracking drift when language and visual templates missalign with the dynamic target state and ambiguity in the later merging stage. To tackle the issues, we propose a joint multi-modal tracking framework with 1) a prompt modulation module to leverage the complementarity between temporal visual templates and language expressions, enabling precise and context-aware appearance and linguistic cues, and 2) a unified target decoding module to integrate the multi-modal reference cues and executes the integrated queries on the search image to predict the target location in an end-to-end manner directly. This design ensures spatio-temporal consistency by leveraging historical visual information and introduces an integrated solution, generating predictions in a single step. Extensive experiments conducted on TNL2K, OTB-Lang, LaSOT, and RefCOCOg validate the efficacy of our proposed approach. The results demonstrate competitive performance against state-of-the-art methods for both tracking and grounding. Code is available at https://github.com/twotw02/QueryNLT

We aim at exploiting additional auxiliary labels from an independent (auxiliary) task to boost the primary task performance which we focus on, while preserving a single task inference cost of the primary task. While most existing auxiliary learning methods are optimization-based relying on loss weights/gradients manipulation, our method is architecture-based with a flexible asymmetric structure for the primary and auxiliary tasks, which produces different networks for training and inference. Specifically, starting from two single task networks/branches (each representing a task), we propose a novel method with evolving networks where only primary-to-auxiliary links exist as the cross-task connections after convergence. These connections can be removed during the primary task inference, resulting in a single-task inference cost. We achieve this by formulating a Neural Architecture Search (NAS) problem, where we initialize bi-directional connections in the search space and guide the NAS optimization converging to an architecture with only the single-side primary-to-auxiliary connections. Moreover, our method can be incorporated with optimization-based auxiliary learning approaches. Extensive experiments with six tasks on NYU v2, CityScapes, and Taskonomy datasets using VGG, ResNet, and ViT backbones validate the promising performance. The codes are available at https://github.com/ethanygao/Aux-NAS.

In this paper, we present DetKDS, the first framework that searches for optimal detection distillation policies. Manual design of detection distillers becomes challenging and time-consuming due to significant disparities in distillation behaviors between detectors with different backbones, paradigms, and label assignments. To tackle these challenges, we leverage search algorithms to discover optimal distillers for homogeneous and heterogeneous student-teacher pairs. Firstly, our search space encompasses global features, foreground-background features, instance features, logits response, and localization response as inputs. Then, we construct omni-directional cascaded transformations and obtain the distiller by selecting the advanced distance function and common weight value options. Finally, we present a divide-and-conquer evolutionary algorithm to handle the explosion of the search space. In this strategy, we first evolve the best distiller formulations of individual knowledge inputs and then optimize the combined weights of these multiple distillation losses. DetKDS automates the distillation process without requiring expert design or additional tuning, effectively reducing the teacher-student gap in various scenarios. Based on the analysis of our search results, we provide valuable guidance that contributes to detection distillation designs. Comprehensive experiments on different detectors demonstrate that DetKDS outperforms state-of-the-art methods in detection and instance segmentation tasks. For instance, DetKDS achieves significant gains than baseline detectors: $+3.7$, $+4.1$, $+4.0$, $+3.7$, and $+3.5$ AP on RetinaNet, Faster-RCNN, FCOS, RepPoints, and GFL, respectively. Code at: https://github.com/lliai/DetKDS.

Within the domain of blind face restoration (BFR), approaches lacking facial priors frequently result in excessively smoothed visual outputs. Exiting BFR methods predominantly utilize generative facial priors to achieve realistic and authentic details. However, these methods, primarily designed for images, encounter challenges in maintaining temporal consistency when applied to face video restoration. To tackle this issue, we introduce StableBFVR, an innovative Blind Face Video Restoration method based on Stable Diffusion that incorporates temporal information into the generative prior. This is achieved through the introduction of temporal layers in the diffusion process. These temporal layers consider both long-term and short-term information aggregation. Moreover, to improve generalizability, BFR methods employ complex, large-scale degradation during training, but it often sacrifices accuracy. Addressing this, StableBFVR features a novel mixed-degradation-aware prompt module, capable of encoding specific degradation information to dynamically steer the restoration process. Comprehensive experiments demonstrate that our proposed StableBFVR outperforms state-of-the-art methods.

In this paper, we present DSA, the first automated framework for discovering sparsity allocation schemes for layer-wise pruning in Large Language Models (LLMs). LLMs have become increasingly powerful, but their large parameter counts make them computationally expensive. Existing pruning methods for compressing LLMs primarily focus on evaluating redundancies and removing element-wise weights. However, these methods fail to allocate adaptive layer-wise sparsities, leading to performance degradation in challenging tasks. We observe that per-layer importance statistics can serve as allocation indications, but their effectiveness depends on the allocation function between layers. To address this issue, we develop an expression discovery framework to explore potential allocation strategies. Our allocation functions involve two steps: reducing element-wise metrics to per-layer importance scores, and modelling layer importance to sparsity ratios. To search for the most effective allocation function, we construct a search space consisting of pre-process, reduction, transform, and post-process operations. We leverage an evolutionary algorithm to perform crossover and mutation on superior candidates within the population, guided by performance evaluation. Finally, we seamlessly integrate our discovered functions into various uniform methods, resulting in significant performance improvements. We conduct extensive experiments on multiple challenging tasks such as arithmetic, knowledge reasoning, and multimodal benchmarks spanning GSM8K, MMLU, SQA, and VQA, demonstrating that our DSA method achieves significant performance gains on the LLaMA-1|2|3, Mistral, and OPT models. Notably, the LLaMA-1|2|3 model pruned by our DSA reaches 4.73\%|6.18\%|10.65\% gain over the state-of-the-art techniques (e.g., Wanda and SparseGPT).

In this paper, we introduce **Era3D**, a novel multiview diffusion method that generates high-resolution multiview images from a single-view image. Despite significant advancements in multiview generation, existing methods still suffer from camera prior mismatch, inefficacy, and low resolution, resulting in poor-quality multiview images. Specifically, these methods assume that the input images should comply with a predefined camera type, e.g. a perspective camera with a fixed focal length, leading to distorted shapes when the assumption fails. Moreover, the full-image or dense multiview attention they employ leads to a dramatic explosion of computational complexity as image resolution increases, resulting in prohibitively expensive training costs. To bridge the gap between assumption and reality, Era3D first proposes a diffusion-based camera prediction module to estimate the focal length and elevation of the input image, which allows our method to generate images without shape distortions. Furthermore, a simple but efficient attention layer, named row-wise attention, is used to enforce epipolar priors in the multiview diffusion, facilitating efficient cross-view information fusion. Consequently, compared with state-of-the-art methods, Era3D generates high-quality multiview images with up to a 512×512 resolution while reducing computation complexity of multiview attention by 12x times. Comprehensive experiments demonstrate the superior generation power of Era3D- it can reconstruct high-quality and detailed 3D meshes from diverse single-view input images, significantly outperforming baseline multiview diffusion methods.

Facial expression is related to facial muscle contractions and different muscle movements correspond to different emotional states. For micro-expression recognition, the muscle movements are usually subtle, which has a negative impact on the performance of current facial emotion recognition algorithms. Most existing methods use self-attention mechanisms to capture relationships between tokens in a sequence, but they do not take into account the inherent spatial relationships between facial landmarks. This can result in sub-optimal performance on micro-expression recognition tasks. Therefore, learning to recognize facial muscle movements is a key challenge in the area of micro-expression recognition. In this paper, we propose a Hierarchical Transformer Network (HTNet) to identify critical areas of facial muscle movement. HTNet includes two major components: a transformer layer that leverages the local temporal features and an aggregation layer that extracts local and global semantical facial features. Specifically, HTNet divides the face into four different facial areas: left lip area, left eye area, right eye area and right lip area. The transformer layer is used to focus on representing local minor muscle movement with local self-attention in each area. The aggregation layer is used to learn the interactions between eye areas and lip areas. The experiments on four publicly available micro-expression datasets show that the proposed approach outperforms previous methods by a large margin. The codes and models are available at: https://github.com/wangzhifengharrison/HTNet.

Blind face restoration is an important task in computer vision and has gained significant attention due to its wide-range applications. Previous works mainly exploit facial priors to restore face images and have demonstrated high-quality results. However, generating faithful facial details remains a challenging problem due to the limited prior knowledge obtained from finite data. In this work, we delve into the potential of leveraging the pretrained Stable Diffusion for blind face restoration. We propose BFRffusion which is thoughtfully designed to effectively extract features from low-quality face images and could restore realistic and faithful facial details with the generative prior of the pretrained Stable Diffusion. In addition, we build a privacy-preserving face dataset called PFHQ with balanced attributes like race, gender, and age. This dataset can serve as a viable alternative for training blind face restoration networks, effectively addressing privacy and bias concerns usually associated with the real face datasets. Through an extensive series of experiments, we demonstrate that our BFRffusion achieves state-of-the-art performance on both synthetic and real-world public testing datasets for blind face restoration and our PFHQ dataset is an available resource for training blind face restoration networks. The codes, pretrained models, and dataset are released at https://github.com/chenxx89/BFRffusion.

Adverse weather conditions, such as rain, raindrop, snow and haze, consistently degrade images in an unpredictable manner, thereby rendering existing task-specific and task-aligned methods inadequate in addressing this formidable problem. To this end, we investigate the application of Transformer in image restoration and introduce an efficient frequency-oriented method called AIRFormer, which is designed to restore weather-degraded images comprehensively and holistically. Specifically, we identify that the initial self-attention mechanism exhibits distinctive properties akin to a low-pass filter. Therefore, we construct a frequency-guided Transformer encoder by incorporating wavelet-based prior information to guide the extraction of image features. Additionally, considering the non-specific frequency characteristics of self-attention in the later stages, we develop a frequency-refined Transformer decoder that incorporates learnable task-specific queries across spatial dimensions, channel dimensions, and wavelet domains. To facilitate the training of our proposed method, we curate a comprehensive benchmark dataset named AIR40K that, encompasses a wide range of challenging scenarios. Extensive experimental evaluations demonstrate the superiority of our AIRFormer over both task-aligned and all-in-one methods across 15 publicly available datasets. Notably, AIRFormer achieves the best trade-off between the inference time and quality of reconstructed image, comparing with existing methods such as TransWeather and Restormer. The source code, dataset and pre-trained models will be available at https://github.com/chdwyb/AIRFormer.

Face recognition systems have raised concerns due to their vulnerability to different presentation attacks, and system security has become an increasingly critical concern. Although many face anti-spoofing (FAS) methods perform well in intra-dataset scenarios, their generalization remains a challenge. To address this issue, some methods adopt domain adversarial training (DAT) to extract domain-invariant features. Differently, in this paper, we propose a domain adversarial attack (DAA) method by adding perturbations to the input images, which makes them indistinguishable across domains and enables domain alignment. Moreover, since models trained on limited data and types of attacks cannot generalize well to unknown attacks, we propose a dual perceptual and generative knowledge distillation framework for face anti-spoofing that utilizes pre-trained face-related models containing rich face priors. Specifically, we adopt two different face-related models as teachers to transfer knowledge to the target student model. The pre-trained teacher models are not from the task of face anti-spoofing but from perceptual and generative tasks, respectively, which implicitly augment the data. By combining both DAA and dual-teacher knowledge distillation, we develop a dual teacher knowledge distillation with domain alignment framework (DTDA) for face anti-spoofing. The advantage of our proposed method has been verified through extensive ablation studies and comparison with state-of-the-art methods on public datasets across multiple protocols.

By hiding the front-facing camera below the display panel, Under-Display Camera (UDC) provides users with a full-screen experience. However, due to the characteristics of the display, images taken by UDC suffer from significant quality degradation. Methods have been proposed to tackle UDC image restoration and advances have been achieved. There are still no specialized methods and datasets for restoring UDC face images, which may be the most common problem in the UDC scene. To this end, considering color filtering, brightness attenuation, and diffraction in the imaging process of UDC, we propose a two-stage network UDC Degradation Model Network named UDC-DMNet to synthesize UDC images by modeling the processes of UDC imaging. Then we use UDC-DMNet and high-quality face images from FFHQ and CelebA-Test to create UDC face training datasets FFHQ-P/T and testing datasets CelebA-Test-P/T for UDC face restoration. We propose a novel dictionary-guided transformer network named DGFormer. Introducing the facial component dictionary and the characteristics of the UDC image in the restoration makes DGFormer capable of addressing blind face restoration in UDC scenarios. Experiments show that our DGFormer and UDC-DMNet achieve state-of-the-art performance.

Blur artifacts can seriously degrade the visual quality of images, and numerous deblurring methods have been proposed for specific scenarios. However, in most real-world images, blur is caused by different factors, e.g., motion, and defocus. In this paper, we address how other deblurring methods perform in the case of multiple types of blur. For in-depth performance evaluation, we construct a new large-scale multi-cause image deblurring dataset (MC-Blur), including real-world and synthesized blurry images with different blur factors. The images in the proposed MC-Blur dataset are collected using other techniques: averaging sharp images captured by a 1000-fps high-speed camera, convolving Ultra-High-Definition (UHD) sharp images with large-size kernels, adding defocus to images, and real-world blurry images captured by various camera models. Based on the MC-Blur dataset, we conduct extensive benchmarking studies to compare SOTA methods in different scenarios, analyze their efficiency, and investigate the buildataset’s capacity. These benchmarking results provide a comprehensive overview of the advantages and limitations of current deblurring methods, revealing our dataset’s advances. The dataset is available to the public athttps://github.com/HDCVLab/MC-Blur-Dataset.

Deep Neural Networks (DNNs) have demonstrated excellent performance in image classification, yet remain vulnerable to adversarial attacks. Generating deployable adversarial patches represents a promising approach to safeguard critical facilities against DNN-based classifiers used for Remote Sensing Images (RSI). While existing adversarial patch attack methods are designed for natural images, they typically generate a single and large patch which is impractically oversize for RSI applications. In this paper, we propose a Deployable Multi-Mini-Patch Adversarial Attack (DeMPAA) method for RSI classification task, which deploys multiple small adversarial patches on key locations considering both the feasibility and the effectiveness. The proposed DeMPAA method formulates the problem as a constrained optimization problem that jointly optimizes patch locations and adversarial patches. The proposed DeMPAA method takes a searching and optimization strategy to tackle it. The DeMPAA framework consists of a Feasible and Effective Map Generation (FEMG) module and a Patch Generation (PG) module. The FEMG module generates a location map to guide the adversarial patch location sampling by excluding the infeasible locations and considering the location effectiveness. In the PG module, a Probability guided Random Sampling based patch location selection (PRSamp) method is used to search better locations, then we optimize the adversarial patches using gradient descent with respect to an adversarial classification loss and an imperceptibility loss. Extensive experimental results conducted on Aerial Image Dataset show that the proposed DeMPAA method achieves 94.80% attacking success rate against ResNet50 using 16 small patches, which significantly outperforms other adversarial patch methods.

Deep learning models are usually black boxes when deployed on machine learning platforms. Prior works have shown that the attributes (e.g., the number of convolutional layers) of a target black-box model can be exposed through a sequence of queries. There is a crucial limitation: these works assume the training dataset of the target model is known beforehand and leverage this dataset for model attribute attack. However, it is difficult to access the training dataset of the target black-box model in reality. Therefore, whether the attributes of a target black-box model could be still revealed in this case is doubtful. In this paper, we investigate a new problem of black-box reverse engineering, without requiring the availability of the target model’s training dataset. We put forward a general and principled framework DREAM, by casting this problem as out-of-distribution (OOD) generalization. In this way, we can learn a domain-agnostic meta-model to infer the attributes of the target black-box model with unknown training data. This makes our method one of the kinds that can gracefully apply to an arbitrary domain for model attribute reverse engineering with strong generalization ability. Extensive experimental results demonstrate the superiority of our proposed method over the baselines.

Biometric systems are vulnerable to presentation attacks (PAs) performed using various PA instruments (PAIs). Even though there are numerous PA detection (PAD) techniques based on both deep learning and hand-crafted features, the generalization of PAD for unknown PAI is still a challenging problem. In this work, we empirically prove that the initialization of the PAD model is a crucial factor for generalization, which is rarely discussed in the community. Based on such observation, we proposed a self-supervised learning-based method, denoted as DF-DM. Specifically, DF-DM is based on a global-local view coupled with de-folding and de-mixing to derive the task-specific representation for PAD. During de-folding, the proposed technique will learn region-specific features to represent samples in a local pattern by explicitly minimizing the generative loss. While de-mixing drives detectors to obtain the instance-specific features with global information for more comprehensive representation by minimizing the interpolation-based consistency. Extensive experimental results show that the proposed method can achieve significant improvements in terms of both face and fingerprint PAD in more complicated and hybrid datasets when compared with the state-of-the-art methods. When training in CASIA-FASD and Idiap Replay-Attack, the proposed method can achieve an 18.60% equal error rate (EER) in OULU-NPU and MSU-MFSD, exceeding the baseline performance by 9.54%. The source code of the proposed technique is available at https://github.com/kongzhecn/dfdm.

As the quality of optical sensors improves, there is a need for processing large-scale images. In particular, the ability of devices to capture ultra-high definition (UHD) images and video places new demands on the image processing pipeline. In this paper, we consider the task of low-light image enhancement (LLIE) and introduce a large-scale database consisting of images at 4K and 8K resolution. We conduct systematic benchmarking studies and provide a comparison of current LLIE algorithms. As a second contribution, we introduce LLFormer, a transformer-based low-light enhancement method. The core components of LLFormer are the axis-based multi-head self-attention and cross-layer attention fusion block, which significantly reduces the linear complexity. Extensive experiments on the new dataset and existing public datasets show that LLFormer outperforms state-of-the-art methods. We also show that employing existing LLIE methods trained on our benchmark as a pre-processing step significantly improves the performance of downstream tasks, e.g., face detection in low-light conditions. The source code and pre-trained models are available at https://github.com/TaoWangzj/LLFormer.

This paper addresses the problem of robust deep single-image reflection removal (SIRR) against adversarial attacks. Current deep learning based SIRR methods have shown significant performance degradation due to unnoticeable distortions and perturbations on input images. For a comprehensive robustness study, we first conduct diverse adversarial attacks specifically for the SIRR problem, i.e. towards different attacking targets and regions. Then we propose a robust SIRR model, which integrates the cross-scale attention module, the multi-scale fusion module, and the adversarial image discriminator. By exploiting the multi-scale mechanism, the model narrows the gap between features from clean and adversarial images. The image discriminator adaptively distinguishes clean or noisy inputs, and thus further gains reliable robustness. Extensive experiments on Nature, SIR2, and Real datasets demonstrate that our model remarkably improves the robustness of SIRR across disparate scenes.

Contrastive learning based vision-language joint pre-training has emerged as a successful representation learning strategy. In this paper, we present a prototype representation learning framework incorporating both global and local alignment between medical images and reports. In contrast to standard global multi-modality alignment methods, we employ a local alignment module for fine-grained representation. Furthermore, a cross-modality conditional reconstruction module is designed to interchange information across modalities in the training phase by reconstructing masked images and reports. For reconstructing long reports, a sentence-wise prototype memory bank is constructed, enabling the network to focus on low-level localized visual and high-level clinical linguistic features. Additionally, a non-auto-regressive generation paradigm is proposed for reconstructing non-sequential reports. Experimental results on five downstream tasks, including supervised classification, zero-shot classification, image-to-text retrieval, semantic segmentation, and object detection, show the proposed method outperforms other state-of-the-art methods across multiple datasets and under different dataset size settings. The code is available at https://github.com/QtacierP/PRIOR.

In recent years, Transformer networks are beginning to replace pure convolutional neural networks (CNNs) in the field of computer vision due to their global receptive field and adaptability to input. However, the quadratic computational complexity of softmax-attention limits the wide application in image dehazing task, especially for high-resolution images. To address this issue, we propose a new Transformer variant, which applies the Taylor expansion to approximate the softmax-attention and achieves linear computational complexity. A multi-scale attention refinement module is proposed as a complement to correct the error of the Taylor expansion. Furthermore, we introduce a multi-branch architecture with multi-scale patch embedding to the proposed Transformer, which embeds features by overlapping deformable convolution of different scales. The design of multi-scale patch embedding is based on three key ideas: 1) various sizes of the receptive field; 2) multi-level semantic information; 3) flexible shapes of the receptive field. Our model, named Multi-branch Transformer expanded by Taylor formula (MB-TaylorFormer), can em-bed coarse to fine features more flexibly at the patch embedding stage and capture long-distance pixel interactions with limited computational cost. Experimental results on several dehazing benchmarks show that MB-TaylorFormer achieves state-of-the-art (SOTA) performance with a light computational burden. The source code and pre-trained models are available at https://github.com/FVL2020/ICCV-2023-MB-TaylorFormer.

Reliable segmentation of road lines and markings is critical to autonomous driving. Our work is motivated by the observations that road lines and markings are (1) frequently occluded in the presence of moving vehicles, shadow, and glare and (2) highly structured with low intra-class shape variance and overall high appearance consistency. To solve these issues, we propose a Homography Guided Fusion (HomoFusion) module to exploit temporally-adjacent video frames for complementary cues facilitating the correct classification of the partially occluded road lines or markings. To reduce computational complexity, a novel surface normal estimator is proposed to establish spatial correspondences between the sampled frames, allowing the HomoFusion module to perform a pixel-to-pixel attention mechanism in updating the representation of the occluded road lines or markings. Experiments on ApolloScape, a large-scale lane mark segmentation dataset, and ApolloScape Night with artificial simulated night-time road conditions, demonstrate that our method outperforms other existing SOTA lane mark segmentation models with less than 9% of their parameters and computational complexity. We show that exploiting available camera intrinsic data and ground plane assumption for cross-frame correspondence can lead to a light-weight network with significantly improved performances in speed and accuracy. We also prove the versatility of our HomoFusion approach by applying it to the problem of water puddle segmentation and achieving SOTA performance1.

Multi-object tracking (MOT) aims to build moving trajectories for number-agnostic objects. Modern multi-object trackers commonly follow the tracking-by-detection strategy. Therefore, fooling detectors can be an effective solution but it usually requires attacks in multiple successive frames, resulting in low efficiency. Attacking association processes improves efficiency but may require model-specific design, leading to poor generalization. In this paper, we propose a novel False negative and False positive attack (F&F attack) mechanism: it perturbs the input image to erase original detections and to inject deceptive false alarms around original ones while integrating the association attack implicitly. The mechanism can produce effective identity switches against multi-object trackers by only fooling detectors in a few frames. To demonstrate the flexibility of the mechanism, we deploy it to three multi-object trackers (ByteTrack, SORT, and CenterTrack) which are enabled by two representative detectors (YOLOX and CenterNet). Comprehensive experiments on MOT17 and MOT20 datasets show that our method significantly outperforms existing attackers, revealing the vulnerability of the tracking-by-detection paradigm to detection attacks.

Understanding human interaction with objects is an important research topic for embodied Artificial Intelligence and identifying the objects that humans are interacting with is a primary problem for interaction understanding. Existing methods rely on frame-based detectors to locate interacting objects. However, this approach is subjected to heavy occlusions, background clutter, and distracting objects. To address the limitations, in this paper, we propose to leverage spatio-temporal information of hand-object interaction to track interactive objects under these challenging cases. Without prior knowledge of the general objects to be tracked like object tracking problems, we first utilize the spatial relation between hands and objects to adaptively discover the interacting objects from the scene. Second, the consistency and continuity of the appearance of objects between successive frames are exploited to track the objects. With this tracking formulation, our method also benefits from training on large-scale general object-tracking datasets. We further curate a video-level hand-object interaction dataset for testing and evaluation from 100DOH. The quantitative results demonstrate that our proposed method outperforms the state-of-the-art methods. Specifically, in scenes with continuous interaction with different objects, we achieve an impressive improvement of about 10% as evaluated using the Average Precision (AP) metric. Our qualitative findings also illustrate that our method can produce more continuous trajectories for interacting objects.

The adversarial attacks have attracted increasing attention in various fields including natural language processing. The current textual attacking models primarily focus on fooling models by adding character-/word-/sentence-level perturbations, ignoring their influence on human perception. In this paper, for the first time in the community, we propose a novel mode of textual attack, punctuation-level attack. With various types of perturbations, including insertion, displacement, deletion, and replacement, the punctuation-level attack achieves promising fooling rates against SOTA models on typical textual tasks and maintains minimal influence on human perception and understanding of the text by mere perturbation of single-shot single punctuation. Furthermore, we propose a search method named Text Position Punctuation Embedding and Paraphrase (TPPEP) to accelerate the pursuit of optimal position to deploy the attack, without exhaustive search, and we present a mathematical interpretation of TPPEP. Thanks to the integrated Text Position Punctuation Embedding (TPPE), the punctuation attack can be applied at a constant cost of time. Experimental results on public datasets and SOTA models demonstrate the effectiveness of the punctuation attack and the proposed TPPE. We additionally apply the single punctuation attack to summarization, semantic-similarity-scoring, and text-to-image tasks, and achieve encouraging results.

This work studies the problem of few-shot object counting, which counts the number of exemplar objects (i.e., described by one or several support images) occurring in the query image. The major challenge lies in that the target objects can be densely packed in the query image, making it hard to recognize every single one. To tackle the obstacle, we propose a novel learning block, equipped with a similarity comparison module and a feature enhancement module. Concretely, given a support image and a query image, we first derive a score map by comparing their projected features at every spatial position. The score maps regarding all support images are collected together and normalized across both the exemplar dimension and the spatial dimensions, producing a reliable similarity map. We then enhance the query feature with the support features by employing the developed point-wise similarities as the weighting coefficients. Such a design encourages the model to inspect the query image by focusing more on the regions akin to the support images, leading to much clearer boundaries between different objects. Extensive experiments on various benchmarks and training setups suggest that we surpass the state-of-the-art methods by a sufficiently large margin. For instance, on a recent large-scale FSC-147 dataset, we surpass the state-of-the-art method by improving the mean absolute error from 22.08 to 14.32 (35%↑). Code has been released in https://github.com/zhiyuanyou/SAFECount.

Recent deep face hallucination methods show stunning performance in super-resolving severely degraded facial images, even surpassing human ability. However, these algorithms are mainly evaluated on non-public synthetic datasets. It is thus unclear how these algorithms perform on public face hallucination datasets. Meanwhile, most of the existing datasets do not well consider the distribution of races, which makes face hallucination methods trained on these datasets biased toward some specific races. To address the above two problems, in this paper, we build a public Ethnically Diverse Face dataset, EDFace-Celeb-1 M, and design a benchmark task for face hallucination. Our dataset includes 1.7 million photos that cover different countries, with relatively balanced race composition. To the best of our knowledge, it is the largest-scale and publicly available face hallucination dataset in the wild. Associated with this dataset, this paper also contributes various evaluation protocols and provides comprehensive analysis to benchmark the existing state-of-the-art methods. The benchmark evaluations demonstrate the performance and limitations of state-of-the-art algorithms. https://github.com/HDCVLab/EDFace-Celeb-1M.

Video deraining is an important task in computer vision as the unwanted rain hampers the visibility of videos and deteriorates the robustness of most outdoor vision systems. Despite the significant success which has been achieved for video deraining recently, two major challenges remain: 1) how to exploit the vast information among successive frames to extract powerful spatio-temporal features across both the spatial and temporal domains, and 2) how to restore high-quality derained videos with a high-speed approach. In this paper, we present a new end-to-end video deraining framework, dubbed Enhanced Spatio-Temporal Interaction Network (ESTINet), which considerably boosts current state-of-the-art video deraining quality and speed. The ESTINet takes the advantage of deep residual networks and convolutional long short-term memory, which can capture the spatial features and temporal correlations among successive frames at the cost of very little computational resource. Extensive experiments on three public datasets show that the proposed ESTINet can achieve faster speed than the competitors, while maintaining superior performance over the state-of-the-art methods. https://github.com/HDCVLab/Enhanced-Spatio-Temporal-Interaction-Learning-for-Video-Deraining.

We present a novel network to transfer the image-language pre-trained model to video-text retrieval in an end-to-end manner. Leading approaches in the domain of video-and-language learning try to distill the spatio-temporal video features and multi-modal interaction between videos and language from a large-scale video-text dataset. Differently, we leverage the pre-trained image-language model, and simplify it as a two-stage framework including co-learning of image and text, and enhancing temporal relations between video frames and video-text respectively. Specifically, based on the spatial semantics captured by Contrastive Language-Image Pre-training (CLIP) model, our model involves a Temporal Difference Block (TDB) to capture motions at fine temporal video frames, and a Temporal Alignment Block (TAB) to re-align the tokens of video clips and phrases and enhance the cross-modal correlation. These two temporal blocks efficiently realize video-language learning and enable the proposed model to scale well on comparatively small datasets. We conduct extensive experimental studies including ablation studies and comparisons with existing SOTA methods, and our proposed approach outperforms them on the popularly-employed text-to-video and video-to-text retrieval benchmarks, including MSR-VTT, MSVD, LSMDC, and VATEX.

Haze reduces the visibility of image content and leads to failure in handling subsequent computer vision tasks. In this paper, we address the problem of single image dehazing by proposing a dehazing network named T-Net, which consists of a backbone network based on the U-Net architecture and a dual attention module. Multi-scale feature fusion can be achieved by using skip connections with a new fusion strategy. Furthermore, by repeatedly unfolding the plain T-Net, Stack T-Net is proposed to take advantage of the dependence of deep features across stages via a recursive strategy. To reduce network parameters, the intra-stage recursive computation of ResNet is adopted in our Stack T-Net. We take both the stage-wise result and the original hazy image as input to each T-Net and finally output the prediction of the clean image. Experimental results on both synthetic and real-world images demonstrate that our plain T-Net and the advanced Stack T-Net perform favorably against state-of-the-art dehazing algorithms and show that our Stack T-Net could further improve the dehazing effect, demonstrating the effectiveness of the recursive strategy.

Text logo design heavily relies on the creativity and expertise of professional designers, in which arranging element layouts is one of the most important procedures. However, few attention has been paid to this task which needs to take many factors (e.g., fonts, linguistics, topics, etc.) into consideration. In this paper, we propose a content-aware layout generation network which takes glyph images and their corresponding text as input and synthesizes aesthetic layouts for them automatically. Specifically, we develop a dual-discriminator module, including a sequence discriminator and an image discriminator, to evaluate both the character placing trajectories and rendered shapes of synthesized text logos, respectively. Furthermore, we fuse the information of linguistics from texts and visual semantics from glyphs to guide layout prediction, which both play important roles in professional layout design. To train and evaluate our approach, we construct a dataset named as TextLogo3K, consisting of about 3,500 text logo images and their pixel-level annotations. Experimental studies on this dataset demonstrate the effectiveness of our approach for synthesizing visually-pleasing text logos and verify its superiority against the state of the art.

Multi-object tracking (MOT) in the scenario of low-frame-rate videos is a promising solution for deploying MOT methods on edge devices with limited computing, storage, power, and transmitting bandwidth. Tracking with a low frame rate poses particular challenges in the association stage as objects in two successive frames typically exhibit much quicker variations in locations, velocities, appearances, and visibilities than those in normal frame rates. In this paper, we observe severe performance degeneration of many existing association strategies caused by such variations. Though optical-flow-based methods like CenterTrack can handle the large displacement to some extent due to their large receptive field, the temporally local nature makes them fail to give correct displacement estimations of objects whose visibility flip within adjacent frames. To overcome the local nature of optical-flow-based methods, we propose an online tracking method by extending the CenterTrack architecture with a new head, named APP, to recognize unreliable displacement estimations. Then we design a two-stage association policy where displacement estimations or historical motion cues are leveraged in the corresponding stage according to APP predictions. Our method, with little additional computational overhead, shows robustness in preserving identities in low-frame-rate video sequences. Experimental results on public datasets in various low-frame-rate settings demonstrate the advantages of the proposed method.

We tackle human image synthesis, including human motion imitation, appearance transfer, and novel view synthesis, within a unified framework. It means that the model, once being trained, can be used to handle all these tasks. The existing task-specific methods mainly use 2D keypoints (pose) to estimate the human body structure. However, they only express the position information with no ability to characterize the personalized shape of the person and model the limb rotations. In this paper, we propose to use a 3D body mesh recovery module to disentangle the pose and shape. It can not only model the joint location and rotation but also characterize the personalized body shape. To preserve the source information, such as texture, style, color, and face identity, we propose an Attentional Liquid Warping GAN with Attentional Liquid Warping Block (AttLWB) that propagates the source information in both image and feature spaces to the synthesized reference. Specifically, the source features are extracted by a denoising convolutional auto-encoder for characterizing the source identity well. Furthermore, our proposed method can support a more flexible warping from multiple sources. To further improve the generalization ability of the unseen source images, a one/few-shot adversarial learning is applied. In detail, it first trains a model in an extensive training set. Then, it finetunes the model by one/few-shot unseen image(s) in a self-supervised way to generate high-resolution ( 512 ×512 and 1024 ×1024) results. Also, we build a new dataset, namely Impersonator (iPER) dataset, for the evaluation of human motion imitation, appearance transfer, and novel view synthesis. Extensive experiments demonstrate the effectiveness of our methods in terms of preserving face identity, shape consistency, and clothes details. All codes and dataset are available on https://impersonator.org/work/impersonator-plus-plus.html.

For the large amount of spatial and spectral information contained in hyperspectral image (HSI), feature description of HSI has attracted widespread concern in recent years. Existing deep learning-based HSI feature description algorithms require a large number of training samples and have poor interpretability. Therefore, it is necessary to develop an efficient HSI features description algorithm with interpretability based on machine learning. Local binary pattern (LBP) is a classical descriptor used to extract the local spatial texture features of images, which has been widely applied to image feature description and matching. However, the existing LBP algorithms for HSI are based on the single-dimensional description, which leads to the limitations on the expression of spatial–spectral information. Therefore, a multidimensional LBP (MDLBP) based on Clifford algebra for HSI is proposed in this article, which is able to extract spatial–spectral feature from multiple dimensions. First, with the theory of the Clifford algebra, a new representation of HSI including spatial and spectral information is built. Second, the geometric relationship between the local geometry of HSI in Clifford algebra space is calculated to realize the local multidimensional description of the local spatial–spectral information. Finally, a novel LBP coding algorithm for HSI is implemented based on the local multidimensional description to calculate the feature descriptor of HSI. The experimental results on HSI classification show that our proposed MDLBP algorithm can achieve higher accuracy than the representative spatial–spectral features and the existing LBP algorithms, especially in the scenery of small-scale training samples.

Skeleton-based action recognition has attracted significant attention and obtained widespread applications due to the robustness of 3D skeleton data. One of the key challenges is how to extract discriminative and robust spatio-temporal features from sparse skeleton data to describe actions and improve recognition accuracy. To address this issue, this paper combines convolutions with attention mechanisms and proposes a deep network for skeleton-based action recognition, termed as local-and-global attention network (LAGA-Net). First, we encode skeleton sequences into joint feature evolution maps to compactly describe the spatial and temporal characteristics of skeleton sequences. Then, a motion guided channel attention module (MGCAM) is proposed to model the interdependencies between feature channels by calculating temporal frame-level motion and enhance motion-salient features in a channel-wise way. Further, a spatio-temporal attention module (STAM) is proposed to model spatio-temporal context-aware collaboration at sequence level and extract spatio-temporal attention features that involve long-range dependencies. Together, MGCAM and STAM are combined to form LAGA-Net, which extracts discriminative features integrating both local and global representations of skeleton sequences. Moreover, a two-stream architecture is proposed to learn complementary features from joint and bone aspects. We conduct extensive experiments to verify the effectiveness and superiority of our proposed method over state-of-the-art approaches on several benchmarks (e.g., NTU RGB+D, Northwestern-UCLA, UTD-MHAD and NTU RGB+D 120).

Facial portrait is an artistic form which draws faces by emphasizing discriminative or prominent parts of faces via various kinds of drawing tools. However, the complex interplay between the different facial factors, such as facial parts, background, and drawing styles, and the significant domain gap between natural facial images and their portrait counterparts makes the task challenging. In this paper, a flexible four-stream Disentangled Feature Networks (DFN) is proposed to learn disentangled feature representation of different facial factors and generate plausible portraits with reasonable exaggerations and richness in style. Four factors are encoded as embedding features, and combined to reconstruct facial portraits. Meanwhile, to make the process fully automatic (without manually specifying either portrait style or exaggerating form), we propose a new Adversarial Portrait Mapping Module (APMM) to map noise to the embedding feature space, as proxies for portrait style and exaggerating. Thanks to the proposedDFNandAPMM, we are able to manipulate the portrait style and facial geometric structures to generate a large number of portraits. Extensive experiments on two public datasets show that our proposed methods can generate a diverse set of artistic portraits.

Increasingly, modern mobile devices allow capturing images at Ultra-High-Definition (UHD) resolution, which includes 4K and 8K images. However, current single image super-resolution (SISR) methods focus on super-resolving images to ones with resolution up to high definition (HD) and ignore higher-resolution UHD images. To explore their performance on UHD images, in this paper, we first introduce two large-scale image datasets, UHDSR4K and UHDSR8K, to benchmark existing SISR methods. With 70,000 V100 GPU hours of training, we benchmark these methods on 4K and 8K resolution images under seven different settings to provide a set of baseline models. Moreover, we propose a baseline model, called Mesh Attention Network (MANet) for SISR. The MANet applies the attention mechanism in both different depths (horizontal) and different levels of receptive field (vertical). In this way, correlations among feature maps are learned, enabling the network to focus on more important features.

In active visual tracking, it is notoriously difficult when distracting objects appear, as distractors often mislead the tracker by occluding the target or bringing a confusing appearance. To address this issue, we propose a mixed cooperative-competitive multi-agent game, where a target and multiple distractors form a collaborative team to play against a tracker and make it fail to follow. Through learning in our game, diverse distracting behaviors of the distractors naturally emerge, thereby exposing the tracker’s weakness, which helps enhance the distraction-robustness of the tracker. For effective learning, we then present a bunch of practical methods, including a reward function for distractors, a cross-modal teacher-student learning strategy, and a recurrent attention mechanism for the tracker. The experimental results show that our tracker performs desired distraction-robust active visual tracking and can be well generalized to unseen environments. We also show that the multi-agent game can be used to adversarially test the robustness of trackers.

Visual Active Tracking (VAT) aims at following a target object by autonomously controlling the motion system of a tracker given visual observations. To learn a robust tracker for VAT, in this article, we propose a novel adversarial reinforcement learning (RL) method which adopts an Asymmetric Dueling mechanism, referred to as AD-VAT. In the mechanism, the tracker and target, viewed as two learnable agents, are opponents and can mutually enhance each other during the dueling/competition: i.e., the tracker intends to lockup the target, while the target tries to escape from the tracker. The dueling is asymmetric in that the target is additionally fed with the tracker's observation and action, and learns to predict the tracker's reward as an auxiliary task. Such an asymmetric dueling mechanism produces a stronger target, which in turn induces a more robust tracker. To improve the performance of the tracker in the case of challenging scenarios such as obstacles, we employ more advanced environment augmentation technique and two-stage training strategies, termed as AD-VAT+. For a better understanding of the asymmetric dueling mechanism, we also analyze the target's behaviors as the training proceeds and visualize the latent space of the tracker. The experimental results, in both 2D and 3D environments, demonstrate that the proposed method leads to a faster convergence in training and yields more robust tracking behaviors in different testing scenarios. The potential of the active tracker is also shown in real-world videos.

In this paper, we tackle the problem of single image dehazing with a convolutional neural network. Within this network, we develop a multi-level fusion module to utilize both low-level and high-level features. The low-level features help to recover finer details, and the high-level features discover abstract semantics. They are complementary in the restoring of clear images. Moreover, a Residual Mixed-convolution Attention Module (RMAM) with an attention block is proposed to guide the network to focus on important features in the learning process. In this RMAM, group convolution, depth-wise convolution, and point-wise convolution are mixed, and thus it is much faster than its counterparts. With these two modules, we thus have an end-to-end network without explicitly estimating the atmospheric light intensity and the transmission map in the classical atmosphere scattering model. Both qualitative and quantitative experimental studies are carried out on public datasets including RESIDE, DCPDN-TestA, and the real-world dataset. The extensive results demonstrate both the effectiveness and efficiency of the proposed solution to single image dehazing.

Pedestrian detection methods have been significantly improved with the development of deep convolutional neural networks. Nevertheless, detecting ismall-scaled pedestrians and occluded pedestrians remains a challenging problem. In this paper, we propose a pedestrian detection method with a couple-network to simultaneously address these two issues. One of the sub-networks, the gated multi-layer feature extraction sub-network, aims to adaptively generate discriminative features for pedestrian candidates in order to robustly detect pedestrians with large variations on scale. The second sub-network targets on handling the occlusion problem of pedestrian detection by using deformable regional region of interest (RoI)-pooling. We investigate two different gate units for the gated sub-network, namely, the channel-wise gate unit and the spatio-wise gate unit, which can enhance the representation ability of the regional convolutional features among the channel dimensions or across the spatial domain, repetitively. Ablation studies have validated the effectiveness of both the proposed gated multi-layer feature extraction sub-network and the deformable occlusion handling sub-network. With the coupled framework, our proposed pedestrian detector achieves promising results on both two pedestrian datasets, especially on detecting small or occluded pedestrians. On the CityPersons dataset, the proposed detector achieves the lowest missing rates (i.e. 40.78% and 34.60%) on detecting small and occluded pedestrians, surpassing the second best comparison method by 6.0% and 5.87%, respectively.

Single-image super-resolution (SR) and multi-frame SR are two ways to super resolve low-resolution images. Single-Image SR generally handles each image independently, but ignores the temporal information implied in continuing frames. Multi-frame SR is able to model the temporal dependency via capturing motion information. However, it relies on neighbouring frames which are not always available in the real world. Meanwhile, slight camera shake easily causes heavy motion blur on long-distance-shot low-resolution images. To address these problems, a Blind Motion Deblurring Super-Reslution Networks, BMDSRNet, is proposed to learn dynamic spatio-temporal information from single static motion-blurred images. Motion-blurred images are the accumulation over time during the exposure of cameras, while the proposed BMDSRNet learns the reverse process and uses three-streams to learn Bidirectional spatio-temporal information based on well designed reconstruction loss functions to recover clean high-resolution images. Extensive experiments demonstrate that the proposed BMDSRNet outperforms recent state-of-the-art methods, and has the ability to simultaneously deal with image deblurring and SR.

An image can be decomposed into two parts: the basic content and details, which usually correspond to the low-frequency and high-frequency information of the image. For a hazy image, these two parts are often affected by haze in different levels, e.g., high-frequency parts are often affected more serious than low-frequency parts. In this paper, we approach the single image dehazing problem as two restoration problems of recovering basic content and image details, and propose a Dual-Path Recurrent Network (DPRN) to simultaneously tackle these two problems. Specifically, the core structure of DPRN is a dual-path block, which uses two parallel branches to learn the characteristics of the basic content and details of hazy images. Each branch consists of several Convolutional LSTM blocks and convolution layers. Moreover, a parallel interaction function is incorporated into the dual-path block, thus enables each branch to dynamically fuse the intermediate features of both the basic content and image details. In this way, both branches can benefit from each other, and recover the basic content and image details alternately, therefore alleviating the color distortion problem in the dehazing process. Experimental results show that the proposed DPRN outperforms state-of-the-art image dehazing methods in terms of both quantitative accuracy and qualitative visual effect.

Rain streaks and raindrops are two natural phenomena, which degrade image capture in different ways. Currently, most existing deep deraining networks take them as two distinct problems and individually address one, and thus cannot deal adequately with both simultaneously. To address this, we propose a Dual Attention-in-Attention Model (DAiAM) which includes two DAMs for removing both rain streaks and raindrops. Inside the DAM, there are two attentive maps - each of which attends to the heavy and light rainy regions, respectively, to guide the deraining process differently for applicable regions. In addition, to further refine the result, a Differential-driven Dual Attention-in-Attention Model (D-DAiAM) is proposed with a "heavy-to-light" scheme to remove rain via addressing the unsatisfying deraining regions. Extensive experiments on one public raindrop dataset, one public rain streak and our synthesized joint rain streak and raindrop (JRSRD) dataset have demonstrated that the proposed method not only is capable of removing rain streaks and raindrops simultaneously, but also achieves the state-of-the-art performance on both tasks.

Images captured in snowy days suffer from noticeable degradation of scene visibility, which degenerates the performance of current vision-based intelligent systems. Removing snow from images thus is an important topic in computer vision. In this paper, we propose a Deep Dense Multi-Scale Network (DDMSNet) for snow removal by exploiting semantic and depth priors. As images captured in outdoor often share similar scenes and their visibility varies with depth from camera, such semantic and depth information provides a strong prior for snowy image restoration. We incorporate the semantic and depth maps as input and learn the semantic-aware and geometry-aware representation to remove snow. In particular, we first create a coarse network to remove snow from the input images. Then, the coarsely desnowed images are fed into another network to obtain the semantic and depth labels. Finally, we design a DDMSNet to learn semantic-aware and geometry-aware representation via a self-attention mechanism to produce the final clean images. Experiments evaluated on public synthetic and real-world snowy images verify the superiority of the proposed method, offering better results both quantitatively and qualitatively. https://github.com/HDCVLab/Deep-Dense-Multi-scale-Network https://github.com/HDCVLab/Deep-Dense-Multi-scale-Network.

Existing image-to-image transformation approaches primarily focus on synthesizing visually pleasing data. Generating images with correct identity labels is challenging yet much less explored. It is even more challenging to deal with image transformation tasks with large deformation in poses, viewpoints, or scales while preserving the identity, such as face rotation and object viewpoint morphing. In this paper, we aim at transforming an image with a fine-grained category to synthesize new images that preserve the identity of the input image, which can thereby benefit the subsequent fine-grained image recognition and few-shot learning tasks. The generated images, transformed with large geometric deformation, do not necessarily need to be of high visual quality but are required to maintain as much identity information as possible. To this end, we adopt a model based on generative adversarial networks to disentangle the identity related and unrelated factors of an image. In order to preserve the fine-grained contextual details of the input image during the deformable transformation, a constrained nonalignment connection method is proposed to construct learnable highways between intermediate convolution blocks in the generator. Moreover, an adaptive identity modulation mechanism is proposed to transfer the identity information into the output image effectively. Extensive experiments on the CompCars and Multi-PIE datasets demonstrate that our model preserves the identity of the generated images much better than the state-of-the-art image-to-image transformation models, and as a result significantly boosts the visual recognition performance in fine-grained few-shot learning.

Existing deep learning methods for image deblurring typically train models using pairs of sharp images and their blurred counterparts. However, synthetically blurring images does not necessarily model the blurring process in real-world scenarios with sufficient accuracy. To address this problem, we propose a new method which combines two GAN models, i.e., a learning-to-Blur GAN (BGAN) and learning-to-DeBlur GAN (DBGAN), in order to learn a better model for image deblurring by primarily learning how to blur images. The first model, BGAN, learns how to blur sharp images with unpaired sharp and blurry image sets, and then guides the second model, DBGAN, to learn how to correctly deblur such images. In order to reduce the discrepancy between real blur and synthesized blur, a relativistic blur loss is leveraged. As an additional contribution, this paper also introduces a Real-World Blurred Image (RWBI) dataset including diverse blurry images. Our experiments show that the proposed method achieves consistently superior quantitative performance as well as higher perceptual quality on both the newly proposed dataset and the public GOPRO dataset.

Motion-blurred images are the result of light accumulation over the period of camera exposure time, during which the camera and objects in the scene are in relative motion to each other. The inverse process of extracting an image sequence from a single motion-blurred image is an ill-posed vision problem. One key challenge is that the motions across frames are subtle, which makes the generating networks difficult to capture them and thus the recovery sequences lack motion details. In order to alleviate this problem, we propose a detail-aware network with three consecutive stages to improve the reconstruction quality by addressing specific aspects in the recovery process. The detail-aware network firstly models the dynamics using a cycle flow loss, resolving the temporal ambiguity of the reconstruction in the first stage. Then, a GramNet is proposed in the second stage to refine subtle motion between continuous frames using Gram matrices as motion representation. Finally, we introduce a HeptaGAN in the third stage to bridge the continuous and discrete nature of exposure time and recovered frames, respectively, in order to maintain rich detail. Experiments show that the proposed detail-aware networks produce sharp image sequences with rich details and subtle motion, outperforming the state-of-the-art methods.

We study active object tracking, where a tracker takes visual observations (i.e., frame sequences) as input and produces the corresponding camera control signals as output (e.g., move forward, turn left, etc.). Conventional methods tackle tracking and camera control tasks separately, and the resulting system is difficult to tune jointly. These methods also require significant human efforts for image labeling and expensive trial-and-error system tuning in the real world. To address these issues, we propose, in this paper, an end-to-end solution via deep reinforcement learning. A ConvNet-LSTM function approximator is adopted for the direct frame-to-action prediction. We further propose an environment augmentation technique and a customized reward function, which are crucial for successful training. The tracker trained in simulators (ViZDoom and Unreal Engine) demonstrates good generalization behaviors in the case of unseen object moving paths, unseen object appearances, unseen backgrounds, and distracting objects. The system is robust and can restore tracking after occasional lost of the target being tracked. We also find that the tracking ability, obtained solely from simulators, can potentially transfer to real-world scenarios. We demonstrate successful examples of such transfer, via experiments over the VOT dataset and the deployment of a real-world robot using the proposed active tracker trained in simulation.

The Deep learning of optical flow has been an active area for its empirical success. For the difficulty of obtaining accurate dense correspondence labels, unsupervised learning of optical flow has drawn more and more attention, while the accuracy is still far from satisfaction. By holding the philosophy that better estimation models can be trained with betterapproximated labels, which in turn can be obtained from better estimation models, we propose a self-taught learning framework to continually improve the accuracy using self-generated pseudo labels. The estimated optical flow is first filtered by bidirectional flow consistency validation and occlusion-aware dense labels are then generated by edge-aware interpolation from selected sparse matches. Moreover, by combining reconstruction loss with regression loss on the generated pseudo labels, the performance is further improved. The experimental results demonstrate that our models achieve state-of-the-art results among unsupervised methods on the public KITTI, MPI-Sintel and Flying Chairs datasets.

We study the problem of sketch image recognition. This problem is plagued with two major challenges: 1) sketch images are often scarce in contrast to the abundance of natural images, rendering the training task difficult, and 2) the significant domain gap between sketch image and its natural image counterpart makes the task of bridging the two domains challenging. In order to overcome these challenges, in this paper we propose to transfer the knowledge of a network learned from natural images to a sketch network - a new deep net architecture which we term as cousin network. This network guides a sketch-recognition network to extract more relevant features that are close to those of natural images, via adversarial training. Moreover, to enhance the transfer ability of the classification model, a sketch-to-image attribute warehouse is constructed to approximate the transformation between the sketch domain and the real image domain. Extensive experiments conducted on the TU-Berlin dataset show that the proposed model is able to efficiently distill knowledge from natural images and achieves superior performance than the current state of the art.

In this paper, we address a novel task, namely weakly-supervised spatio-temporally grounding natural sentence in video.Specifically, given a natural sentence and a video, we localize a spatio-temporal tube in the video that semantically corresponds to the given sentence, with no reliance on any spatio-temporal annotations during training.First, a set of spatiotemporal tubes, referred to as instances, are extracted from the video.We then encode these instances and the sentence using our proposed attentive interactor which can exploit their fine-grained relationships to characterize their matching behaviors.Besides a ranking loss, a novel diversity loss is introduced to train the proposed attentive interactor to strengthen the matching behaviors of reliable instance-sentence pairs and penalize the unreliable ones.Moreover, we also contribute a dataset, called VID-sentence, based on the Im-ageNet video object detection dataset, to serve as a benchmark for our task.Extensive experimental results demonstrate the superiority of our model over the baseline approaches.Our code and the constructed VID-sentence dataset are available at: https://github.com/ JeffCHEN2017/WSSTG.git.

We propose to compose dynamic tree structures that place the objects in an image into a visual context, helping visual reasoning tasks such as scene graph generation and visual Q&A. Our visual context tree model, dubbed VCTree, has two key advantages over existing structured object representations including chains and fully-connected graphs: 1) The efficient and expressive binary tree encodes the inherent parallel/hierarchical relationships among objects, e.g., ``clothes'' and ``pants'' are usually co-occur and belong to ``person''; 2) the dynamic structure varies from image to image and task to task, allowing more content-/task-specific message passing among objects. To construct a VCTree, we design a score function that calculates the task-dependent validity between each object pair, and the tree is the binary version of the maximum spanning tree from the score matrix. Then, visual contexts are encoded by bidirectional TreeLSTM and decoded by task-specific models. We develop a hybrid learning procedure which integrates end-task supervised learning and the tree structure reinforcement learning, where the former's evaluation result serves as a self-critic for the latter's structure exploration. Experimental results on two benchmarks, which require reasoning over contexts: Visual Genome for scene graph generation and VQA2.0 for visual Q&A, show that VCTree outperforms state-of-the-art results while discovering interpretable visual context structures.

Crowd counting is a challenging task due to factors such as large variations in crowdedness and severe occlusions. Although recent deep learning based counting algorithms have achieved a great progress, the correlation knowledge among samples and the semantic prior have not yet been fully exploited. In this paper, a residual regression framework is proposed for crowd counting utilizing the correlation information among samples. By incorporating such information into our network, we discover that more intrinsic characteristics can be learned by the network which thus generalizes better to unseen scenarios. Besides, we show how to effectively leverage the semantic prior to improve the performance of crowd counting. We also observe that the adversarial loss can be used to improve the quality of predicted density maps, thus leading to an improvement in crowd counting. Experiments on public datasets demonstrate the effectiveness and generalization ability of the proposed method.

Face anti-spoofing is an important task in full-stack face applications including face detection, verification, and recognition. Previous approaches build models on datasets which do not simulate the real-world data well (e.g., small scale, insignificant variance, etc.). Existing models may rely on auxiliary information, which prevents these anti-spoofing solutions from generalizing well in practice. In this paper, we present a data collection solution along with a data synthesis technique to simulate digital medium-based face spoofing attacks, which can easily help us obtain a large amount of training data well reflecting the real-world scenarios. Through exploiting a novel Spatio-Temporal Anti-Spoof Network (STASN), we are able to push the performance on public face anti-spoofing datasets over state-of-the-art methods by a large margin. Since the proposed model can automatically attend to discriminative regions, it makes analyzing the behaviors of the network possible.We conduct extensive experiments and show that the proposed model can distinguish spoof faces by extracting features from a variety of regions to seek out subtle evidences such as borders, moire patterns, reflection artifacts, etc.

Gait recognition is an important biometric method popularly used in video surveillance, where the task is to identify people at a distance by their walking patterns from video sequences. Most of the current successful approaches for gait recognition either use a pair of gait images to form a cross-gait representation or rely on a single gait image for unique-gait representation. These two types of representations emperically complement one another. In this paper, we propose a new Joint Unique-gait and Cross-gait Network (JUCNet), to combine the advantages of unique-gait representation with that of cross-gait representation, leading to an significantly improved performance. Another key contribution of this paper is a novel quintuplet loss function, which simultaneously increases the inter-class differences by pushing representations extracted from different subjects apart and decreases the intra-class variations by pulling representations extracted from the same subject together. Experiments show that our method achieves the state-of-the-art performance tested on standard benchmark datasets, demonstrating its superiority over existing methods.

We tackle the human motion imitation, appearance transfer, and novel view synthesis within a unified framework, which means that the model once being trained can be used to handle all these tasks. The existing task-specific methods mainly use 2D keypoints (pose) to estimate the human body structure. However, they only expresses the position information with no abilities to characterize the personalized shape of the individual person and model the limbs rotations. In this paper, we propose to use a 3D body mesh recovery module to disentangle the pose and shape, which can not only model the joint location and rotation but also characterize the personalized body shape. To preserve the source information, such as texture, style, color, and face identity, we propose a Liquid Warping GAN with Liquid Warping Block (LWB) that propagates the source information in both image and feature spaces, and synthesizes an image with respect to the reference. Specifically, the source features are extracted by a denoising convolutional auto-encoder for characterizing the source identity well. Furthermore, our proposed method is able to support a more flexible warping from multiple sources. In addition, we build a new dataset, namely Impersonator (iPER) dataset, for the evaluation of human motion imitation, appearance transfer, and novel view synthesis. Extensive experiments demonstrate the effectiveness of our method in several aspects, such as robustness in occlusion case and preserving face identity, shape consistency and clothes details. All codes and datasets are available on https://svip-lab.github.io/project/impersonator.html.

This paper proposes a new approach to multi-object tracking by semantic topic discovery. We dynamically cluster frame-by-frame detections and treat objects as topics, allowing the application of the Dirichlet process mixture model. The tracking problem is cast as a topic-discovery task, where the video sequence is treated analogously to a document. It addresses tracking issues such as object exclusivity constraints as well as tracking management without the need for heuristic thresholds. Variation of object appearance is modeled as the dynamics of word co-occurrence and handled by updating the cluster parameters across the sequence in the dynamical clustering procedure. We develop two kinds of visual representation based on super-pixel and deformable part model and integrate them into the model of automatic topic discovery for tracking rigid and non-rigid objects, respectively. In experiments on public data sets, we demonstrate the effectiveness of the proposed algorithm.

Camera shake or target movement often leads to undesired blur effects in videos captured by a hand-held camera. Despite significant efforts having been devoted to video-deblur research, two major challenges remain: 1) how to model the spatio-temporal characteristics across both the spatial domain (i.e., image plane) and the temporal domain (i.e., neighboring frames) and 2) how to restore sharp image details with respect to the conventionally adopted metric of pixel-wise errors. In this paper, to address the first challenge, we propose a deblurring network (DBLRNet) for spatial-temporal learning by applying a 3D convolution to both the spatial and temporal domains. Our DBLRNet is able to capture jointly spatial and temporal information encoded in neighboring frames, which directly contributes to the improved video deblur performance. To tackle the second challenge, we leverage the developed DBLRNet as a generator in the generative adversarial network (GAN) architecture and employ a content loss in addition to an adversarial loss for efficient adversarial training. The developed network, which we name as deblurring GAN, is tested on two standard benchmarks and achieves the state-of-the-art performance.

Taking a photo outside, can we predict the immediate future, e.g., how would the cloud move in the sky? We address this problem by presenting a generative adversarial network (GAN) based two-stage approach to generating realistic time-lapse videos of high resolution. Given the first frame, our model learns to generate long-term future frames. The first stage generates videos of realistic contents for each frame. The second stage refines the generated video from the first stage by enforcing it to be closer to real videos with regard to motion dynamics. To further encourage vivid motion in the final generated video, Gram matrix is employed to model the motion more precisely. We build a large scale time-lapse dataset, and test our approach on this new dataset. Using our model, we are able to generate realistic videos of up to 128 Ã- 128 resolution for 32 frames. Quantitative and qualitative experiment results demonstrate the superiority of our model over the state-of-the-art models.

We study active object tracking, where a tracker takes as input the visual observation (i.e. frame sequence) and produces the camera control signal (e.g., move forward, turn left, etc). Conventional methods tackle the tracking and the camera control separately, which is challenging to tune jointly. It also incurs many human efforts for labeling and many expensive trial-and-errors in real-world. To address these issues, we propose, in this paper, an end-to-end solution via deep reinforcement learning, where a ConvNet-LSTM function approximator is adopted for the direct frame-to-action prediction. We further propose an environment augmentation technique and a customized reward function, which are crucial for a successful training. The tracker trained in simulators (ViZDoom, Unreal Engine) shows good generalization in the case of unseen object moving path, unseen object appearance, unseen background, and distracting object. It can restore tracking when occasionally losing the target. With the experiments over the VOT dataset, we also find that the tracking ability, obtained solely from simulators, can potentially transfer to real-world scenarios.

Recent research endeavors have shown the potential of using feed-forward convolutional neural networks to accomplish fast style transfer for images. In this work, we take one step further to explore the possibility of exploiting a feed-forward network to perform style transfer for videos and simultaneously maintain temporal consistency among stylized video frames. Our feed-forward network is trained by enforcing the outputs of consecutive frames to be both well stylized and temporally consistent. More specifically, a hybrid loss is proposed to capitalize on the content information of input frames, the style information of a given style image, and the temporal information of consecutive frames. To calculate the temporal loss during the training stage, a novel two-frame synergic training mechanism is proposed. Compared with directly applying an existing image style transfer method to videos, our proposed method employs the trained network to yield temporally consistent stylized videos which are much more visually pleasant. In contrast to the prior video style transfer method which relies on time-consuming optimization on the fly, our method runs in real time while generating competitive visual results.

This paper proposes a new approach to multi-object tracking by semantic topic discovery. We dynamically cluster frame-by-frame detections and treat objects as topics, allowing the application of the Dirichlet Process Mixture Model (DPMM). The tracking problem is cast as a topic-discovery task where the video sequence is treated analogously to a document. This formulation addresses tracking issues such as object exclusivity constraints as well as cannot-link constraints which are integrated without the need for heuristic thresholds. The video is temporally segmented into epochs to model the dynamics of word (superpixel) co-occurrences and to model the temporal damping effect. In experiments on public data sets we demonstrate the effectiveness of the proposed algorithm.

In this paper, we propose a label propagation framework to handle the multiple object tracking (MOT) problem for a generic object type (cf. pedestrian tracking). Given a target object by an initial bounding box, all objects of the same type are localized together with their identities. We treat this as a problem of propagating bi-labels, i.e. a binary class label for detection and individual object labels for tracking. To propagate the class label, we adopt clustered Multiple Task Learning (cMTL) while enforcing spatio-temporal consistency and show that this improves the performance when given limited training data. To track objects, we propagate labels from trajectories to detections based on affinity using appearance, motion, and context. Experiments on public and challenging new sequences show that the proposed method improves over the current state of the art on this task.

In this paper, we present a unified method for joint face image analysis, i.e., simultaneously estimating head pose, facial expression and landmark positions in real-world face images. To achieve this goal, we propose a novel iterative Multi-Output Random Forests (iMORF) algorithm, which explicitly models the relations among multiple tasks and iteratively exploits such relations to boost the performance of all tasks. Specifically, a hierarchical face analysis forest is learned to perform classification of pose and expression at the top level, while performing landmark positions regression at the bottom level. On one hand, the estimated pose and expression provide strong shape prior to constrain the variation of landmark positions. On the other hand, more discriminative shape-related features could be extracted from the estimated landmark positions to further improve the predictions of pose and expression. This relatedness of face analysis tasks is iteratively exploited through several cascaded hierarchical face analysis forests until convergence. Experiments conducted on publicly available real-world face datasets demonstrate that the performance of all individual tasks are significantly improved by the proposed iMORF algorithm. In addition, our method outperforms state-of-the-arts for all three face analysis tasks.

We address Multiple Object Tracking (MOT) in crowds, where the type of target objects is generic and not limited to pedestrians as in most previous work. Following the popular tracking-by-detection strategy, we decompose this problem into two main tasks, detection and tracking, and formulate them under the Multiple Task Learning (MTL) framework. A binary detector is learnt to detect objects in images, whilst multiple trackers are learnt on top of the detector by MTL to trace detected objects in subsequent frames. The detector is utilised to anchor the trackers, helping them not drift away from targets. The trackers are jointly learnt by sharing common features. To further improve the performance, we use a smoothness term which considers all labelled and unlabelled data globally. Experiments on challenging new generic object sequences as well as a publicly available sequence show that the proposed method significantly outperforms the state-of-the-art methods.

In this paper, we present a framework for active contour-based visual tracking using level sets. The main components of our framework include contour-based tracking initialization, color-based contour evolution, adaptive shape-based contour evolution for non-periodic motions, dynamic shape-based contour evolution for periodic motions, and the handling of abrupt motions. For the initialization of contour-based tracking, we develop an optical flow-based algorithm for automatically initializing contours at the first frame. For the color-based contour evolution, Markov random field theory is used to measure correlations between values of neighboring pixels for posterior probability estimation. For adaptive shape-based contour evolution, the global shape information and the local color information are combined to hierarchically evolve the contour, and a flexible shape updating model is constructed. For the dynamic shape-based contour evolution, a shape mode transition matrix is learnt to characterize the temporal correlations of object shapes. For the handling of abrupt motions, particle swarm optimization is adopted to capture the global motion which is applied to the contour in the current frame to produce an initial contour in the next frame.

Object appearance modeling is crucial for tracking objects, especially in videos captured by nonstationary cameras and for reasoning about occlusions between multiple moving objects. Based on the log-euclidean Riemannian metric on symmetric positive definite matrices, we propose an incremental log-euclidean Riemannian subspace learning algorithm in which covariance matrices of image features are mapped into a vector space with the log-euclidean Riemannian metric. Based on the subspace learning algorithm, we develop a log-euclidean block-division appearance model which captures both the global and local spatial layout information about object appearances. Single object tracking and multi-object tracking with occlusion reasoning are then achieved by particle filtering-based Bayesian state inference. During tracking, incremental updating of the log-euclidean block-division appearance model captures changes in object appearance. For multi-object tracking, the appearance models of the objects can be updated even in the presence of occlusions. Experimental results demonstrate that the proposed tracking algorithm obtains more accurate results than six state-of-the-art tracking algorithms.

Tracking multiple objects under occlusion is one of the most challenging issues in computer vision. Occlusion results in mistaken match when finding the most similar candidate. Adapting to the change of objects is essential for tracking as objects often undergo intrinsic changes, but noise is unavoidably introduced during updating of the object, and this further confuses the tracker. In order to address these problems, a block-division appearance model is introduced to efficiently handle occlusion. In this model, spatial information is introduced to avoid the mistaken match between object and candidate. Based on this model, a selective updating strategy is proposed to incrementally learn the change of the object, avoiding introducing noise when updating. At the same time occlusion is deduced by monitoring the variation of each block. Experimental results in various videos validate the effectiveness of our algorithm in tracking multiple objects under occlusion.

In this paper, we propose a boosting based tracking framework using transfer learning. To deal with complex appearance variations, the proposed tracking framework tries to utilize discriminative information from previous frames to conduct the tracking task in the current frame, and thus transfers some prior knowledge from the previous source data domain to the current target data domain, resulting in a high discriminative tracker for distinguishing the object from the background. The proposed tracking system has been tested on several challenging sequences. Experimental results demonstrate the effectiveness of the proposed tracking framework.