Weihao Gan
Weihao Gan has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Wei Wu
Tsinghua University
5 shared publications - Junjie Yan
Jiangsu Institute of Nuclear Medicine
3 shared publications - Chi-Hao Wu
Megvii Technology, Chengdu, China
2 shared publications - Chung-Chieh Jay Kuo
University of Southern California
2 shared publications - Wanli Ouyang
Shanghai Artificial Intelligence Laboratory
2 shared publications - Bo Li
State Key Laboratory of Cyberspace Security Defense, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
1 shared publication
Latest Publications
- 24 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 1267-1280
Similarity- and Quality-Guided Relation Learning for Joint Detection and Tracking
Joint detection and tracking, which solves two fundamental vision challenges in a unified manner, is a challenging topic in computer vision. In this area, the proper use of spatial-temporal information in videos can help reduce local defects and improve the quality of feature representations. Although modeling low-level (usually pixel-wise) spatial-temporal information has been studied, instance-level spatial-temporal correlations (i.e., relations between semantic regions in which instances have occurred) have not been fully exploited. In comparison, modeling instance-level correlation is a more flexible and reasonable way to enhance feature representations. However, we have found that conventional instance-level relation learning that works for the separate tasks of detection or tracking is not effective in joint tasks in which a variety of scenarios may be presented. To try to resolve this problem, in this study, we effectively exploited instance-level spatial-temporal semantic information for joint detection and tracking via a joint relation learning pipeline with a novel relation learning mechanism called Similarity- and Quality-Guided Attention (SQGA). Specifically, we added task-specific SQGA relation modules before the corresponding task prediction heads to refine the instance feature representation using features of other reference instances in the neighboring frames; these features are aggregated on the basis of relational affinities. In particular, in SQGA, relational affinities were factorized to similarity and quality terms so that fine-grained supervision rules could be applied. Then we added task-specific attention losses for each SQGA relation module, resulting in a better feature aggregation for the corresponding task. Quantitative experiments based on several challenging multi-object tracking benchmarks showed that our approach was more effective than the baselines and provided competitive results compared with recent state-of-the-art methods.
- 24 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 1267-1280
Similarity- and Quality-Guided Relation Learning for Joint Detection and Tracking
Joint detection and tracking, which solves two fundamental vision challenges in a unified manner, is a challenging topic in computer vision. In this area, the proper use of spatial-temporal information in videos can help reduce local defects and improve the quality of feature representations. Although modeling low-level (usually pixel-wise) spatial-temporal information has been studied, instance-level spatial-temporal correlations (i.e., relations between semantic regions in which instances have occurred) have not been fully exploited. In comparison, modeling instance-level correlation is a more flexible and reasonable way to enhance feature representations. However, we have found that conventional instance-level relation learning that works for the separate tasks of detection or tracking is not effective in joint tasks in which a variety of scenarios may be presented. To try to resolve this problem, in this study, we effectively exploited instance-level spatial-temporal semantic information for joint detection and tracking via a joint relation learning pipeline with a novel relation learning mechanism called Similarity- and Quality-Guided Attention (SQGA). Specifically, we added task-specific SQGA relation modules before the corresponding task prediction heads to refine the instance feature representation using features of other reference instances in the neighboring frames; these features are aggregated on the basis of relational affinities. In particular, in SQGA, relational affinities were factorized to similarity and quality terms so that fine-grained supervision rules could be applied. Then we added task-specific attention losses for each SQGA relation module, resulting in a better feature aggregation for the corresponding task. Quantitative experiments based on several challenging multi-object tracking benchmarks showed that our approach was more effective than the baselines and provided competitive results compared with recent state-of-the-art methods.
- Open Access
Unsupervised Learning of Accurate Siamese Tracking
Unsupervised learning has been popular in various computer vision tasks, including visual object tracking. However, prior unsupervised tracking approaches rely heavily on spatial supervision from template-search pairs and are still unable to track objects with strong variation over a long time span. As unlimited self-supervision signals can be obtained by tracking a video along a cycle in time, we investigate evolving a Siamese tracker by tracking videos forward-backward. We present a novel unsupervised tracking framework, in which we can learn temporal correspondence both on the classification branch and regression branch. Specifically, to propagate reliable template feature in the forward propagation process so that the tracker can be trained in the cycle, we first propose a consistency propagation transformation. We then identify an ill-posed penalty problem in conventional cycle training in backward propagation process. Thus, a differentiable region mask is proposed to select features as well as to implicitly penalize tracking errors on intermediate frames. Moreover, since noisy labels may degrade training, we propose a mask-guided loss reweighting strategy to assign dynamic weights based on the quality of pseudo labels. In extensive experiments, our tracker outperforms preceding unsupervised methods by a substantial margin, performing on par with supervised methods on large-scale datasets such as TrackingNet and LaSOT. Code is available at https://github.com/FlorinShum/ULAST.
Open AccessUnsupervised Learning of Accurate Siamese Tracking
Unsupervised learning has been popular in various computer vision tasks, including visual object tracking. However, prior unsupervised tracking approaches rely heavily on spatial supervision from template-search pairs and are still unable to track objects with strong variation over a long time span. As unlimited self-supervision signals can be obtained by tracking a video along a cycle in time, we investigate evolving a Siamese tracker by tracking videos forward-backward. We present a novel unsupervised tracking framework, in which we can learn temporal correspondence both on the classification branch and regression branch. Specifically, to propagate reliable template feature in the forward propagation process so that the tracker can be trained in the cycle, we first propose a consistency propagation transformation. We then identify an ill-posed penalty problem in conventional cycle training in backward propagation process. Thus, a differentiable region mask is proposed to select features as well as to implicitly penalize tracking errors on intermediate frames. Moreover, since noisy labels may degrade training, we propose a mask-guided loss reweighting strategy to assign dynamic weights based on the quality of pseudo labels. In extensive experiments, our tracker outperforms preceding unsupervised methods by a substantial margin, performing on par with supervised methods on large-scale datasets such as TrackingNet and LaSOT. Code is available at https://github.com/FlorinShum/ULAST.
- Open Access
TSI: Temporal Saliency Integration for Video Action Recognition
Efficient spatiotemporal modeling is an important yet challenging problem for video action recognition. Existing state-of-the-art methods exploit neighboring feature differences to obtain motion clues for short-term temporal modeling with a simple convolution. However, only one local convolution is incapable of handling various kinds of actions because of the limited receptive field. Besides, action-irrelated noises brought by camera movement will also harm the quality of extracted motion features. In this paper, we propose a Temporal Saliency Integration (TSI) block, which mainly contains a Salient Motion Excitation (SME) module and a Cross-perception Temporal Integration (CTI) module. Specifically, SME aims to highlight the motion-sensitive area through spatial-level local-global motion modeling, where the saliency alignment and pyramidal motion modeling are conducted successively between adjacent frames to capture motion dynamics with fewer noises caused by misaligned background. CTI is designed to perform multi-perception temporal modeling through a group of separate 1D convolutions respectively. Meanwhile, temporal interactions across different perceptions are integrated with the attention mechanism. Through these two modules, long short-term temporal relationships can be encoded efficiently by introducing limited additional parameters. Extensive experiments are conducted on several popular benchmarks (i.e., Something-Something V1 & V2, Kinetics-400, UCF-101, and HMDB-51), which demonstrate the effectiveness of our proposed method.
Open AccessTSI: Temporal Saliency Integration for Video Action Recognition
Efficient spatiotemporal modeling is an important yet challenging problem for video action recognition. Existing state-of-the-art methods exploit neighboring feature differences to obtain motion clues for short-term temporal modeling with a simple convolution. However, only one local convolution is incapable of handling various kinds of actions because of the limited receptive field. Besides, action-irrelated noises brought by camera movement will also harm the quality of extracted motion features. In this paper, we propose a Temporal Saliency Integration (TSI) block, which mainly contains a Salient Motion Excitation (SME) module and a Cross-perception Temporal Integration (CTI) module. Specifically, SME aims to highlight the motion-sensitive area through spatial-level local-global motion modeling, where the saliency alignment and pyramidal motion modeling are conducted successively between adjacent frames to capture motion dynamics with fewer noises caused by misaligned background. CTI is designed to perform multi-perception temporal modeling through a group of separate 1D convolutions respectively. Meanwhile, temporal interactions across different perceptions are integrated with the attention mechanism. Through these two modules, long short-term temporal relationships can be encoded efficiently by introducing limited additional parameters. Extensive experiments are conducted on several popular benchmarks (i.e., Something-Something V1 & V2, Kinetics-400, UCF-101, and HMDB-51), which demonstrate the effectiveness of our proposed method.
- 14 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 34 (6) , 2951-2964
Learning Social Spatio-Temporal Relation Graph in the Wild and a Video Benchmark
Social relations are ubiquitous and form the basis of social structure in our daily life. However, existing studies mainly focus on recognizing social relations from still images and movie clips, which are different from real-world scenarios. For example, movie-based datasets define the task as the video classification, only recognizing one relation in the scene. In this article, we aim to study the problem of social relation recognition in an open environment. To close the gap, we provide the first video dataset collected from real-life scenarios, named social relation in the wild (SRIW), where the number of people can be huge and vary, and each pair of relations needs to be recognized. To overcome new challenges, we propose a spatio-temporal relation graph convolutional network (STRGCN) architecture, utilizing correlative visual features to recognize social relations intuitively. Our method decouples the task into two classification tasks: person-level and pair-level relation recognition. Specifically, we propose a person behavior and character module to encode moving and static features in two explicit ways. Then we take them as node features to build a relation graph with meaningful edges in a scene. Based on the relation graph, we introduce the graph convolutional network (GCN) and local GCN to encode social relation features which are used for both recognitions. Experimental results demonstrate the effectiveness of the proposed framework, achieving 83.1% and 40.8% mAP in person-level and pair-level classification. Moreover, the study also contributes to the practicality in this field.
- 14 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 34 (6) , 2951-2964
Learning Social Spatio-Temporal Relation Graph in the Wild and a Video Benchmark
Social relations are ubiquitous and form the basis of social structure in our daily life. However, existing studies mainly focus on recognizing social relations from still images and movie clips, which are different from real-world scenarios. For example, movie-based datasets define the task as the video classification, only recognizing one relation in the scene. In this article, we aim to study the problem of social relation recognition in an open environment. To close the gap, we provide the first video dataset collected from real-life scenarios, named social relation in the wild (SRIW), where the number of people can be huge and vary, and each pair of relations needs to be recognized. To overcome new challenges, we propose a spatio-temporal relation graph convolutional network (STRGCN) architecture, utilizing correlative visual features to recognize social relations intuitively. Our method decouples the task into two classification tasks: person-level and pair-level relation recognition. Specifically, we propose a person behavior and character module to encode moving and static features in two explicit ways. Then we take them as node features to build a relation graph with meaningful edges in a scene. Based on the relation graph, we introduce the graph convolutional network (GCN) and local GCN to encode social relation features which are used for both recognitions. Experimental results demonstrate the effectiveness of the proposed framework, achieving 83.1% and 40.8% mAP in person-level and pair-level classification. Moreover, the study also contributes to the practicality in this field.
- Open Access
Class-wise Dynamic Graph Convolution for Semantic Segmentation
Recent works have made great progress in semantic segmentation by exploiting contextual information in a local or global manner with dilated convolutions, pyramid pooling or self-attention mechanism. In order to avoid potential misleading contextual information aggregation in previous works, we propose a class-wise dynamic graph convolution (CDGC) module to adaptively propagate information. The graph reasoning is performed among pixels in the same class. Based on the proposed CDGC module, we further introduce the Class-wise Dynamic Graph Convolution Network(CDGCNet), which consists of two main parts including the CDGC module and a basic segmentation network, forming a coarse-to-fine paradigm. Specifically, the CDGC module takes the coarse segmentation result as class mask to extract node features for graph construction and performs dynamic graph convolutions on the constructed graph to learn the feature aggregation and weight allocation. Then the refined feature and the original feature are fused to get the final prediction. We conduct extensive experiments on three popular semantic segmentation benchmarks including Cityscapes, PASCAL VOC 2012 and COCO Stuff, and achieve state-of-the-art performance on all three benchmarks.
Open AccessClass-wise Dynamic Graph Convolution for Semantic Segmentation
Recent works have made great progress in semantic segmentation by exploiting contextual information in a local or global manner with dilated convolutions, pyramid pooling or self-attention mechanism. In order to avoid potential misleading contextual information aggregation in previous works, we propose a class-wise dynamic graph convolution (CDGC) module to adaptively propagate information. The graph reasoning is performed among pixels in the same class. Based on the proposed CDGC module, we further introduce the Class-wise Dynamic Graph Convolution Network(CDGCNet), which consists of two main parts including the CDGC module and a basic segmentation network, forming a coarse-to-fine paradigm. Specifically, the CDGC module takes the coarse segmentation result as class mask to extract node features for graph construction and performs dynamic graph convolutions on the constructed graph to learn the feature aggregation and weight allocation. Then the refined feature and the original feature are fused to get the final prediction. We conduct extensive experiments on three popular semantic segmentation benchmarks including Cityscapes, PASCAL VOC 2012 and COCO Stuff, and achieve state-of-the-art performance on all three benchmarks.
- Open Access
STM: SpatioTemporal and Motion Encoding for Action Recognition
Spatiotemporal and motion features are two complementary and crucial information for video action recognition. Recent state-of-the-art methods adopt a 3D CNN stream to learn spatiotemporal features and another flow stream to learn motion features. In this work, we aim to efficiently encode these two features in a unified 2D framework. To this end, we first propose an STM block, which contains a Channel-wise SpatioTemporal Module (CSTM) to present the spatiotemporal features and a Channel-wise Motion Module (CMM) to efficiently encode motion features. We then replace original residual blocks in the ResNet architecture with STM blcoks to form a simple yet effective STM network by introducing very limited extra computation cost. Extensive experiments demonstrate that the proposed STM network outperforms the state-of-the-art methods on both temporal-related datasets (i.e., Something-Something v1 & v2 and Jester) and scene-related datasets (i.e., Kinetics-400, UCF-101, and HMDB-51) with the help of encoding spatiotemporal and motion features together.
Open AccessSTM: SpatioTemporal and Motion Encoding for Action Recognition
Spatiotemporal and motion features are two complementary and crucial information for video action recognition. Recent state-of-the-art methods adopt a 3D CNN stream to learn spatiotemporal features and another flow stream to learn motion features. In this work, we aim to efficiently encode these two features in a unified 2D framework. To this end, we first propose an STM block, which contains a Channel-wise SpatioTemporal Module (CSTM) to present the spatiotemporal features and a Channel-wise Motion Module (CMM) to efficiently encode motion features. We then replace original residual blocks in the ResNet architecture with STM blcoks to form a simple yet effective STM network by introducing very limited extra computation cost. Extensive experiments demonstrate that the proposed STM network outperforms the state-of-the-art methods on both temporal-related datasets (i.e., Something-Something v1 & v2 and Jester) and scene-related datasets (i.e., Kinetics-400, UCF-101, and HMDB-51) with the help of encoding spatiotemporal and motion features together.
- Open Access
Dynamic Curriculum Learning for Imbalanced Data Classification
Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed. Common techniques such as re-sampling and cost-sensitive learning require prior-knowledge to train the system. To address this problem, we propose a unified framework called Dynamic Curriculum Learning (DCL) to online adaptively adjust the sampling strategy and loss learning in single batch, which resulting in better generalization and discrimination. Inspired by the curriculum learning, DCL consists of two level curriculum schedulers: (1) sampling scheduler not only manages the data distribution from imbalanced to balanced but also from easy to hard; (2) loss scheduler controls the learning importance between classification and metric learning loss. Learning from these two schedulers, we demonstrate our DCL framework with the new state-of-the-art performance on the widely used face attribute dataset CelebA and pedestrian attribute dataset RAP.
Open AccessDynamic Curriculum Learning for Imbalanced Data Classification
Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed. Common techniques such as re-sampling and cost-sensitive learning require prior-knowledge to train the system. To address this problem, we propose a unified framework called Dynamic Curriculum Learning (DCL) to online adaptively adjust the sampling strategy and loss learning in single batch, which resulting in better generalization and discrimination. Inspired by the curriculum learning, DCL consists of two level curriculum schedulers: (1) sampling scheduler not only manages the data distribution from imbalanced to balanced but also from easy to hard; (2) loss scheduler controls the learning importance between classification and metric learning loss. Learning from these two schedulers, we demonstrate our DCL framework with the new state-of-the-art performance on the widely used face attribute dataset CelebA and pedestrian attribute dataset RAP.
- 1 May 2018
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 53, 180-191
Online object tracking via motion-guided convolutional neural network (MGNet)
- 1 May 2018
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 53, 180-191
Online object tracking via motion-guided convolutional neural network (MGNet)
- 1 March 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 540-549
Boosted Convolutional Neural Networks (BCNN) for Pedestrian Detection
A boosted convolutional neural network (BCNN) system is proposed to enhance the pedestrian detection performance in this work. Being inspired by the classic boosting idea, we develop a weighted loss function that emphasizes challenging samples in training a convolutional neural network (CNN). Two types of samples are considered challenging: 1) samples with detection scores falling in the decision boundary, and 2) temporally associated samples with inconsistent scores. A weighting scheme is designed for each of them. Finally, we train a boosted fusion layer to benefit from the integration of these two weighting schemes. We use the Fast-RCNN as the baseline, and test the corresponding BCNN on the Caltech pedestrian dataset in the experiment, and show a significant performance gain of the BCNN over its baseline.
- 1 March 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 540-549
Boosted Convolutional Neural Networks (BCNN) for Pedestrian Detection
A boosted convolutional neural network (BCNN) system is proposed to enhance the pedestrian detection performance in this work. Being inspired by the classic boosting idea, we develop a weighted loss function that emphasizes challenging samples in training a convolutional neural network (CNN). Two types of samples are considered challenging: 1) samples with detection scores falling in the decision boundary, and 2) temporally associated samples with inconsistent scores. A weighting scheme is designed for each of them. Finally, we train a boosted fusion layer to benefit from the integration of these two weighting schemes. We use the Fast-RCNN as the baseline, and test the corresponding BCNN on the Caltech pedestrian dataset in the experiment, and show a significant performance gain of the BCNN over its baseline.
- 1 September 2016
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 47, 303-312
Object tracking with temporal prediction and spatial refinement (TPSR)
- 1 September 2016
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 47, 303-312
Object tracking with temporal prediction and spatial refinement (TPSR)