Binqian Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Binqian Xu has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Xiangbo Shu
Nanjing University of Science and Technology
8 shared publications - Jiachao Zhang
Artificial Intelligence Industrial Technology Research Institute, Nanjing Institute of Technology, Nanjing, China
4 shared publications - Basura Fernando
Agency for Science, Technology and Research, Institute of High-Performance Computing, Singapore
1 shared publication - Boyang Li
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
1 shared publication - Chenghao Hu
Nanjing University of Science and Technology
1 shared publication - Chun-Mei Feng
Agency for Science, Technology and Research (A*STAR)
1 shared publication
Latest Publications
- 6 November 2026
- Published by Elsevier in Information Sciences
- Vol. 766
TASL: Byzantine-resilient swarm learning with tripartite auditing and hierarchical blockchain storage
- 6 November 2026
- Published by Elsevier in Information Sciences
- Vol. 766
TASL: Byzantine-resilient swarm learning with tripartite auditing and hierarchical blockchain storage
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 4862-4875
Federated Unsupervised Skeletal Action Recognition From Condensation to Expansion
Most skeleton-based unsupervised action recognition methods rely on centralized learning, which poses privacy risks when applied to human-related data. Federated learning (FL) is widely recognized for preserving data privacy but still struggles with data heterogeneity. Data condensation, as a representative approach, effectively mitigates heterogeneity while safeguarding client privacy. Existing data condensation methods in FL mainly focus on clients, while overlooking two critical issues that arise during global model training on the server. First, the limited data availability elevates the risk of overfitting in the global model. Second, information loss induced by data condensation results in performance degradation. To overcome these limitations, we propose Fed-C&E, featuring a closed-loop condensation-expansion paradigm where client-side condensation is followed by server-side expansion via a dual-level expansion mechanism. During the expansion stage, we present a novel prototype-to-sequence similarity transformation matrix pool to synthesize more samples that align with client data distributions. Furthermore, to mitigate the inherent semantic sparsity of skeletal data and condensation-induced information loss, we devise a feature expansion strategy that leverages second-order client statistics to supplement global information, where the expanded features serve as novel supervisory signals for contrastive learning. Extensive experiments across multiple datasets demonstrate that Fed-C&E not only outperforms aggregate-then-adapt FL methods but also effectively preserves data privacy.
- 29 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 4862-4875
Federated Unsupervised Skeletal Action Recognition From Condensation to Expansion
Most skeleton-based unsupervised action recognition methods rely on centralized learning, which poses privacy risks when applied to human-related data. Federated learning (FL) is widely recognized for preserving data privacy but still struggles with data heterogeneity. Data condensation, as a representative approach, effectively mitigates heterogeneity while safeguarding client privacy. Existing data condensation methods in FL mainly focus on clients, while overlooking two critical issues that arise during global model training on the server. First, the limited data availability elevates the risk of overfitting in the global model. Second, information loss induced by data condensation results in performance degradation. To overcome these limitations, we propose Fed-C&E, featuring a closed-loop condensation-expansion paradigm where client-side condensation is followed by server-side expansion via a dual-level expansion mechanism. During the expansion stage, we present a novel prototype-to-sequence similarity transformation matrix pool to synthesize more samples that align with client data distributions. Furthermore, to mitigate the inherent semantic sparsity of skeletal data and condensation-induced information loss, we devise a feature expansion strategy that leverages second-order client statistics to supplement global information, where the expanded features serve as novel supervisory signals for contrastive learning. Extensive experiments across multiple datasets demonstrate that Fed-C&E not only outperforms aggregate-then-adapt FL methods but also effectively preserves data privacy.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 13300-13311
FedIGA: Improving Global Model Aggregation for Federated Self-Supervised Skeletal Action Recognition
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 13300-13311
FedIGA: Improving Global Model Aggregation for Federated Self-Supervised Skeletal Action Recognition
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 1-12
Topology-Evolving Semantic Adaptation for Few-Shot Class-Incremental Action Recognition
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 1-12
Topology-Evolving Semantic Adaptation for Few-Shot Class-Incremental Action Recognition
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 1521-1534
Attack-Augmented Mixing-Contrastive Skeletal Representation Learning
Contrastive learning facilitates the acquisition of informative skeleton representations for unsupervised action recognition by leveraging effective positive and negative sample pairs. However, most existing methods construct these pairs through weak or strong data augmentations, which typically rely on random appearance alterations of skeletons. While such augmentations are somewhat effective, they introduce semantic variations only indirectly and face two inherent limitations. First, simply modifying the appearance of skeletons often fails to reflect meaningful semantic variations. Second, random perturbations can unintentionally blur the boundary between positive and negative pairs, weakening the contrastive objective. To address these challenges, we propose an attack-driven augmentation framework that explicitly introduces semantic-level perturbations. This approach facilitates the generation of hard positives while guiding the model to mine more informative hard negatives. Building on this idea, we present Attack-Augmented Mixing-Contrastive Skeletal Representation Learning (A 2MC), a novel framework that focuses on contrasting hard positive and hard negative samples for more robust representation learning. Within A 2MC, we design an Attack-Augmentation (Att-Aug) module that integrates both targeted (attack-based) and untargeted (augmentation-based) perturbations to generate informative hard positive samples. In parallel, we propose the Positive-Negative Mixer (PNM), which blends hard positive and negative features to synthesize challenging hard negatives. These are then used to update a mixed memory bank for more effective contrastive learning. Comprehensive evaluations across three public benchmarks demonstrate that our approach, termed A 2MC, achieves performance on par with or exceeding existing state-of-the-art methods.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 1521-1534
Attack-Augmented Mixing-Contrastive Skeletal Representation Learning
Contrastive learning facilitates the acquisition of informative skeleton representations for unsupervised action recognition by leveraging effective positive and negative sample pairs. However, most existing methods construct these pairs through weak or strong data augmentations, which typically rely on random appearance alterations of skeletons. While such augmentations are somewhat effective, they introduce semantic variations only indirectly and face two inherent limitations. First, simply modifying the appearance of skeletons often fails to reflect meaningful semantic variations. Second, random perturbations can unintentionally blur the boundary between positive and negative pairs, weakening the contrastive objective. To address these challenges, we propose an attack-driven augmentation framework that explicitly introduces semantic-level perturbations. This approach facilitates the generation of hard positives while guiding the model to mine more informative hard negatives. Building on this idea, we present Attack-Augmented Mixing-Contrastive Skeletal Representation Learning (A 2MC), a novel framework that focuses on contrasting hard positive and hard negative samples for more robust representation learning. Within A 2MC, we design an Attack-Augmentation (Att-Aug) module that integrates both targeted (attack-based) and untargeted (augmentation-based) perturbations to generate informative hard positive samples. In parallel, we propose the Positive-Negative Mixer (PNM), which blends hard positive and negative features to synthesize challenging hard negatives. These are then used to update a mixed memory bank for more effective contrastive learning. Comprehensive evaluations across three public benchmarks demonstrate that our approach, termed A 2MC, achieves performance on par with or exceeding existing state-of-the-art methods.
- 10 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (8) , 11035-11048
Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semisupervised Skeleton-Based Action Recognition
Contrastive learning has been successfully leveraged to learn action representations for addressing the problem of semisupervised skeleton-based action recognition. However, most contrastive learning-based methods only contrast global features mixing spatiotemporal information, which confuses the spatial-and temporal-specific information reflecting different semantic at the frame level and joint level. Thus, we propose a novel spatiotemporal decouple-and-squeeze contrastive learning (SDS-CL) framework to comprehensively learn more abundant representations of skeleton-based actions by jointly contrasting spatial-squeezing features, temporal-squeezing features, and global features. In SDS-CL, we design a new spatiotemporal-decoupling intra–inter attention (SIIA) mechanism to obtain the spatiotemporal-decoupling attentive features for capturing spatiotemporal specific information by calculating spatial-and temporal-decoupling intra-attention maps among joint/motion features, as well as spatial-and temporal-decoupling inter-attention maps between joint and motion features. Moreover, we present a new spatial-squeezing temporal-contrasting loss (STL), a new temporal-squeezing spatial-contrasting loss (TSL), and the global-contrasting loss (GL) to contrast the spatial-squeezing joint and motion features at the frame level, temporal-squeezing joint and motion features at the joint level, as well as global joint and motion features at the skeleton level. Extensive experimental results on four public datasets show that the proposed SDS-CL achieves performance gains compared with other competitive methods.
- 10 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (8) , 11035-11048
Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semisupervised Skeleton-Based Action Recognition
Contrastive learning has been successfully leveraged to learn action representations for addressing the problem of semisupervised skeleton-based action recognition. However, most contrastive learning-based methods only contrast global features mixing spatiotemporal information, which confuses the spatial-and temporal-specific information reflecting different semantic at the frame level and joint level. Thus, we propose a novel spatiotemporal decouple-and-squeeze contrastive learning (SDS-CL) framework to comprehensively learn more abundant representations of skeleton-based actions by jointly contrasting spatial-squeezing features, temporal-squeezing features, and global features. In SDS-CL, we design a new spatiotemporal-decoupling intra–inter attention (SIIA) mechanism to obtain the spatiotemporal-decoupling attentive features for capturing spatiotemporal specific information by calculating spatial-and temporal-decoupling intra-attention maps among joint/motion features, as well as spatial-and temporal-decoupling inter-attention maps between joint and motion features. Moreover, we present a new spatial-squeezing temporal-contrasting loss (STL), a new temporal-squeezing spatial-contrasting loss (TSL), and the global-contrasting loss (GL) to contrast the spatial-squeezing joint and motion features at the frame level, temporal-squeezing joint and motion features at the joint level, as well as global joint and motion features at the skeleton level. Extensive experimental results on four public datasets show that the proposed SDS-CL achieves performance gains compared with other competitive methods.
- 17 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (6) , 7559-7576
Multi-Granularity Anchor-Contrastive Representation Learning for Semi-Supervised Skeleton-Based Action Recognition
In the semi-supervised skeleton-based action recognition task, obtaining more discriminative information from both labeled and unlabeled data is a challenging problem. As the current mainstream approach, contrastive learning can learn more representations of augmented data, which can be considered as the pretext task of action recognition. However, such a method still confronts three main limitations: 1) It usually learns global-granularity features that cannot well reflect the local motion information. 2) The positive/negative pairs are usually pre-defined, some of which are ambiguous. 3) It generally measures the distance between positive/negative pairs only within the same granularity, which neglects the contrasting between the cross-granularity positive and negative pairs. Toward these limitations, we propose a novel Multi-granularity Anchor-Contrastive representation Learning (dubbed as MAC-Learning) to learn multi-granularity representations by conducting inter- and intra-granularity contrastive pretext tasks on the learnable and structural-link skeletons among three types of granularities covering local, context, and global views. To avoid the disturbance of ambiguous pairs from noisy and outlier samples, we design a more reliable Multi-granularity Anchor-Contrastive Loss (dubbed as MAC-Loss) that measures the agreement/disagreement between high-confidence soft-positive/negative pairs based on the anchor graph instead of the hard-positive/negative pairs in the conventional contrastive loss. Extensive experiments on both NTU RGB+D and Northwestern-UCLA datasets show that the proposed MAC-Learning outperforms existing competitive methods in semi-supervised skeleton-based action recognition tasks.
- 17 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (6) , 7559-7576
Multi-Granularity Anchor-Contrastive Representation Learning for Semi-Supervised Skeleton-Based Action Recognition
In the semi-supervised skeleton-based action recognition task, obtaining more discriminative information from both labeled and unlabeled data is a challenging problem. As the current mainstream approach, contrastive learning can learn more representations of augmented data, which can be considered as the pretext task of action recognition. However, such a method still confronts three main limitations: 1) It usually learns global-granularity features that cannot well reflect the local motion information. 2) The positive/negative pairs are usually pre-defined, some of which are ambiguous. 3) It generally measures the distance between positive/negative pairs only within the same granularity, which neglects the contrasting between the cross-granularity positive and negative pairs. Toward these limitations, we propose a novel Multi-granularity Anchor-Contrastive representation Learning (dubbed as MAC-Learning) to learn multi-granularity representations by conducting inter- and intra-granularity contrastive pretext tasks on the learnable and structural-link skeletons among three types of granularities covering local, context, and global views. To avoid the disturbance of ambiguous pairs from noisy and outlier samples, we design a more reliable Multi-granularity Anchor-Contrastive Loss (dubbed as MAC-Loss) that measures the agreement/disagreement between high-confidence soft-positive/negative pairs based on the anchor graph instead of the hard-positive/negative pairs in the conventional contrastive loss. Extensive experiments on both NTU RGB+D and Northwestern-UCLA datasets show that the proposed MAC-Learning outperforms existing competitive methods in semi-supervised skeleton-based action recognition tasks.