Haoyuan Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Haoyuan Zhang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Wanqing Li
University of Wollongong
2 shared publications - Yonghong Hou
School of Electrical and Information Engineering, Tianjin University, Tianjin, China
2 shared publications - Pichao Wang
Amazon
1 shared publication - Wenjing Zhang
Tianjin University
1 shared publication - Zihui Guo
Tianjin Chengjian University
1 shared publication
Latest Publications
- Open Access
Contrastive Mask Learning for Self-Supervised 3D Skeleton-Based Action Recognition
In this paper, we propose a contrastive mask learning (CML) method for self-supervised 3D skeleton-based action recognition. Specifically, the mask modeling mechanism is integrated into multi-level contrastive learning with the aim of forming a mutually beneficial learning scheme from both contrastive learning and masked skeleton reconstruction. The contrastive objective is extended from an individual skeleton instance to clusters by closing the gap between cluster assignment from different instances of the same category, with the goal of pursuing inter-instance consistency. Compared with previous methods, CML integrates contrastive and masked learning comprehensively and enables intra-/inter-instance consistency pursuit via multi-level contrast, which leads to more discriminative skeleton representation learning. Our extensive evaluation of the challenging NTU RGB+D and PKU-MMD benchmarks demonstrates that representations learned via CML exhibit superior discriminability, consistently outperforming state-of-the-art methods in terms of action recognition accuracy.
Open AccessContrastive Mask Learning for Self-Supervised 3D Skeleton-Based Action Recognition
In this paper, we propose a contrastive mask learning (CML) method for self-supervised 3D skeleton-based action recognition. Specifically, the mask modeling mechanism is integrated into multi-level contrastive learning with the aim of forming a mutually beneficial learning scheme from both contrastive learning and masked skeleton reconstruction. The contrastive objective is extended from an individual skeleton instance to clusters by closing the gap between cluster assignment from different instances of the same category, with the goal of pursuing inter-instance consistency. Compared with previous methods, CML integrates contrastive and masked learning comprehensively and enables intra-/inter-instance consistency pursuit via multi-level contrast, which leads to more discriminative skeleton representation learning. Our extensive evaluation of the challenging NTU RGB+D and PKU-MMD benchmarks demonstrates that representations learned via CML exhibit superior discriminability, consistently outperforming state-of-the-art methods in terms of action recognition accuracy.
- Open Access
- 19 July 2024
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 10 (6) , 7487-7496
Attention-guided mask learning for self-supervised 3D action recognition
Most existing 3D action recognition works rely on the supervised learning paradigm, yet the limited availability of annotated data limits the full potential of encoding networks. As a result, effective self-supervised pre-training strategies have been actively researched. In this paper, we target to explore a self-supervised learning approach for 3D action recognition, and propose the Attention-guided Mask Learning (AML) scheme. Specifically, the dropping mechanism is introduced into contrastive learning to develop Attention-guided Mask (AM) module as well as mask learning strategy, respectively. The AM module leverages the spatial and temporal attention to guide the corresponding features masking, so as to produce the masked contrastive object. The mask learning strategy enables the model to discriminate different actions even with important features masked, which makes action representation learning more discriminative. What’s more, to alleviate the strict positive constraint that would hinder representation learning, the positive-enhanced learning strategy is leveraged in the second-stage training. Extensive experiments on NTU-60, NTU-120, and PKU-MMD datasets show that the proposed AML scheme improves the performance in self-supervised 3D action recognition, achieving state-of-the-art results.
- 19 July 2024
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 10 (6) , 7487-7496
Open AccessAttention-guided mask learning for self-supervised 3D action recognition
Most existing 3D action recognition works rely on the supervised learning paradigm, yet the limited availability of annotated data limits the full potential of encoding networks. As a result, effective self-supervised pre-training strategies have been actively researched. In this paper, we target to explore a self-supervised learning approach for 3D action recognition, and propose the Attention-guided Mask Learning (AML) scheme. Specifically, the dropping mechanism is introduced into contrastive learning to develop Attention-guided Mask (AM) module as well as mask learning strategy, respectively. The AM module leverages the spatial and temporal attention to guide the corresponding features masking, so as to produce the masked contrastive object. The mask learning strategy enables the model to discriminate different actions even with important features masked, which makes action representation learning more discriminative. What’s more, to alleviate the strict positive constraint that would hinder representation learning, the positive-enhanced learning strategy is leveraged in the second-stage training. Extensive experiments on NTU-60, NTU-120, and PKU-MMD datasets show that the proposed AML scheme improves the performance in self-supervised 3D action recognition, achieving state-of-the-art results.
- 28 October 2022
- Published by Springer Nature
- p. 36-51
Contrastive Positive Mining for Unsupervised 3D Action Representation Learning
- 28 October 2022
- Published by Springer Nature
- p. 36-51
Contrastive Positive Mining for Unsupervised 3D Action Representation Learning
- Open Access
SAR-NAS: Skeleton-based Action Recognition via Neural Architecture Searching
This paper presents a study of automatic design of neural network architectures for skeleton-based action recognition. Specifically, we encode a skeleton-based action instance into a tensor and carefully define a set of operations to build two types of network cells: normal cells and reduction cells. The recently developed DARTS (Differentiable Architecture Search) is adopted to search for an effective network architecture that is built upon the two types of cells. All operations are 2D based in order to reduce the overall computation and search space. Experiments on the challenging NTU RGB+D and Kinectics datasets have verified that most of the networks developed to date for skeleton-based action recognition are likely not compact and efficient. The proposed method provides an approach to search for such a compact network that is able to achieve comparative or even better performance than the state-of-the-art methods.
Open AccessSAR-NAS: Skeleton-based Action Recognition via Neural Architecture Searching
This paper presents a study of automatic design of neural network architectures for skeleton-based action recognition. Specifically, we encode a skeleton-based action instance into a tensor and carefully define a set of operations to build two types of network cells: normal cells and reduction cells. The recently developed DARTS (Differentiable Architecture Search) is adopted to search for an effective network architecture that is built upon the two types of cells. All operations are 2D based in order to reduce the overall computation and search space. Experiments on the challenging NTU RGB+D and Kinectics datasets have verified that most of the networks developed to date for skeleton-based action recognition are likely not compact and efficient. The proposed method provides an approach to search for such a compact network that is able to achieve comparative or even better performance than the state-of-the-art methods.