Alert button
Picture for Xiaohu Huang

Xiaohu Huang

Alert button

Condition-Adaptive Graph Convolution Learning for Skeleton-Based Gait Recognition

Aug 13, 2023
Xiaohu Huang, Xinggang Wang, Zhidianqiu Jin, Bo Yang, Botao He, Bin Feng, Wenyu Liu

Figure 1 for Condition-Adaptive Graph Convolution Learning for Skeleton-Based Gait Recognition
Figure 2 for Condition-Adaptive Graph Convolution Learning for Skeleton-Based Gait Recognition
Figure 3 for Condition-Adaptive Graph Convolution Learning for Skeleton-Based Gait Recognition
Figure 4 for Condition-Adaptive Graph Convolution Learning for Skeleton-Based Gait Recognition

Graph convolutional networks have been widely applied in skeleton-based gait recognition. A key challenge in this task is to distinguish the individual walking styles of different subjects across various views. Existing state-of-the-art methods employ uniform convolutions to extract features from diverse sequences and ignore the effects of viewpoint changes. To overcome these limitations, we propose a condition-adaptive graph (CAG) convolution network that can dynamically adapt to the specific attributes of each skeleton sequence and the corresponding view angle. In contrast to using fixed weights for all joints and sequences, we introduce a joint-specific filter learning (JSFL) module in the CAG method, which produces sequence-adaptive filters at the joint level. The adaptive filters capture fine-grained patterns that are unique to each joint, enabling the extraction of diverse spatial-temporal information about body parts. Additionally, we design a view-adaptive topology learning (VATL) module that generates adaptive graph topologies. These graph topologies are used to correlate the joints adaptively according to the specific view conditions. Thus, CAG can simultaneously adjust to various walking styles and viewpoints. Experiments on the two most widely used datasets (i.e., CASIA-B and OU-MVLP) show that CAG surpasses all previous skeleton-based methods. Moreover, the recognition performance can be enhanced by simply combining CAG with appearance-based methods, demonstrating the ability of CAG to provide useful complementary information.The source code will be available at https://github.com/OliverHxh/CAG.

* Accepted by TIP journal 
Viaarxiv icon

GaitGS: Temporal Feature Learning in Granularity and Span Dimension for Gait Recognition

Jun 01, 2023
Haijun Xiong, Yunze Deng, Xiaohu Huang, Xinggang Wang, Wenyu Liu, Bin Feng

Figure 1 for GaitGS: Temporal Feature Learning in Granularity and Span Dimension for Gait Recognition
Figure 2 for GaitGS: Temporal Feature Learning in Granularity and Span Dimension for Gait Recognition
Figure 3 for GaitGS: Temporal Feature Learning in Granularity and Span Dimension for Gait Recognition
Figure 4 for GaitGS: Temporal Feature Learning in Granularity and Span Dimension for Gait Recognition

Gait recognition is an emerging biological recognition technology that identifies and verifies individuals based on their walking patterns. However, many current methods are limited in their use of temporal information. In order to fully harness the potential of gait recognition, it is crucial to consider temporal features at various granularities and spans. Hence, in this paper, we propose a novel framework named GaitGS, which aggregates temporal features in the granularity dimension and span dimension simultaneously. Specifically, Multi-Granularity Feature Extractor (MGFE) is proposed to focus on capturing the micro-motion and macro-motion information at the frame level and unit level respectively. Moreover, we present Multi-Span Feature Learning (MSFL) module to generate global and local temporal representations. On three popular gait datasets, extensive experiments demonstrate the state-of-the-art performance of our method. Our method achieves the Rank-1 accuracies of 92.9% (+0.5%), 52.0% (+1.4%), and 97.5% (+0.8%) on CASIA-B, GREW, and OU-MVLP respectively. The source code will be released soon.

* 14 pages, 6 figures 
Viaarxiv icon

Graph Contrastive Learning for Skeleton-based Action Recognition

Jan 26, 2023
Xiaohu Huang, Hao Zhou, Bin Feng, Xinggang Wang, Wenyu Liu, Jian Wang, Haocheng Feng, Junyu Han, Errui Ding, Jingdong Wang

Figure 1 for Graph Contrastive Learning for Skeleton-based Action Recognition
Figure 2 for Graph Contrastive Learning for Skeleton-based Action Recognition
Figure 3 for Graph Contrastive Learning for Skeleton-based Action Recognition
Figure 4 for Graph Contrastive Learning for Skeleton-based Action Recognition

In the field of skeleton-based action recognition, current top-performing graph convolutional networks (GCNs) exploit intra-sequence context to construct adaptive graphs for feature aggregation. However, we argue that such context is still \textit{local} since the rich cross-sequence relations have not been explicitly investigated. In this paper, we propose a graph contrastive learning framework for skeleton-based action recognition (\textit{SkeletonGCL}) to explore the \textit{global} context across all sequences. In specific, SkeletonGCL associates graph learning across sequences by enforcing graphs to be class-discriminative, \emph{i.e.,} intra-class compact and inter-class dispersed, which improves the GCN capacity to distinguish various action patterns. Besides, two memory banks are designed to enrich cross-sequence context from two complementary levels, \emph{i.e.,} instance and semantic levels, enabling graph contrastive learning in multiple context scales. Consequently, SkeletonGCL establishes a new training paradigm, and it can be seamlessly incorporated into current GCNs. Without loss of generality, we combine SkeletonGCL with three GCNs (2S-ACGN, CTR-GCN, and InfoGCN), and achieve consistent improvements on NTU60, NTU120, and NW-UCLA benchmarks. The source code will be available at \url{https://github.com/OliverHxh/SkeletonGCL}.

* Accepted by ICLR2023 
Viaarxiv icon

Context-Sensitive Temporal Feature Learning for Gait Recognition

Apr 08, 2022
Xiaohu Huang, Duowang Zhu, Xinggang Wang, Hao Wang, Bo Yang, Botao He, Wenyu Liu, Bin Feng

Figure 1 for Context-Sensitive Temporal Feature Learning for Gait Recognition
Figure 2 for Context-Sensitive Temporal Feature Learning for Gait Recognition
Figure 3 for Context-Sensitive Temporal Feature Learning for Gait Recognition
Figure 4 for Context-Sensitive Temporal Feature Learning for Gait Recognition

Although gait recognition has drawn increasing research attention recently, it remains challenging to learn discriminative temporal representation, since the silhouette differences are quite subtle in spatial domain. Inspired by the observation that human can distinguish gaits of different subjects by adaptively focusing on temporal clips with different time scales, we propose a context-sensitive temporal feature learning (CSTL) network for gait recognition. CSTL produces temporal features in three scales, and adaptively aggregates them according to the contextual information from local and global perspectives. Specifically, CSTL contains an adaptive temporal aggregation module that subsequently performs local relation modeling and global relation modeling to fuse the multi-scale features. Besides, in order to remedy the spatial feature corruption caused by temporal operations, CSTL incorporates a salient spatial feature learning (SSFL) module to select groups of discriminative spatial features. Particularly, we utilize transformers to implement the global relation modeling and the SSFL module. To the best of our knowledge, this is the first work that adopts transformer in gait recognition. Extensive experiments conducted on three datasets demonstrate the state-of-the-art performance. Concretely, we achieve rank-1 accuracies of 98.7%, 96.2% and 88.7% under normal-walking, bag-carrying and coat-wearing conditions on CASIA-B, 97.5% on OU-MVLP and 50.6% on GREW.

* Submitted to TPAMI 
Viaarxiv icon