Zhicheng Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhicheng Zhang has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Jianqin Yin
Beijing University of Posts and Telecommunications, Beijing, China
9 shared publications Jianqin Yin
School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications, Beijing, China
5 shared publications- Jin Tang
Beijing University of Posts and Telecommunications
5 shared publications - Xiaoli Liu
School of Artificial Intelligence Beijing University of Posts and Telecommunications 100876 Haidian Beijing China
3 shared publications Yonghao Dang
School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications, Beijing, China
3 shared publications- Yonghao Dang
School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China
3 shared publications
Latest Publications
- Top Cited Papers
- 2 January 2026
- Published by Springer Nature
- p. 176-183
SELD-Mamba: Selective State Space Model for Sound Event Localization and Detection with Source Distance Estimation
- 2 January 2026
- Published by Springer Nature
- p. 176-183
Top Cited PapersSELD-Mamba: Selective State Space Model for Sound Event Localization and Detection with Source Distance Estimation
- 2 January 2026
- Published by Springer Nature
- p. 403-412
S-CMAE: Supervised Contrastive Masked Autoencoders for Respiratory Sound Classification
- 2 January 2026
- Published by Springer Nature
- p. 403-412
S-CMAE: Supervised Contrastive Masked Autoencoders for Respiratory Sound Classification
- Open Access
- 26 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 30-34
Emo-Synergy: Synergizing Task-Specific and General Experts for Multimodal Emotion Recognition
- 26 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 30-34
Open AccessEmo-Synergy: Synergizing Task-Specific and General Experts for Multimodal Emotion Recognition
- 4 April 2025
- Published by Springer Nature in Journal of Shanghai Jiaotong University (Science)
- Vol. 31 (1) , 143-153
ListPose: Lightweight and Implicit Spatial-Temporal Modeling with TokenPose for Video-Based Pose Estimation
- 4 April 2025
- Published by Springer Nature in Journal of Shanghai Jiaotong University (Science)
- Vol. 31 (1) , 143-153
ListPose: Lightweight and Implicit Spatial-Temporal Modeling with TokenPose for Video-Based Pose Estimation
- 28 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 17 (2) , 1344-1358
Facial 3D Regional Structural Motion Representation Using Lightweight Point Cloud Networks for Micro-Expression Recognition
Human-computer interaction (HCI) relies on understanding and adapting to users' emotional states. Micro-expressions (MEs), a critical component of emotional perception, are characterized by their spontaneity, rapidity, subtlety, and difficulty to control. They often reveal an individual's true emotions. A comprehensive and detailed representation of motion is necessary to capture the nuances of facial dynamics effectively. Presently, motion representation methods are predominantly confined to 2D analysis within RGB images, overlooking the critical role of facial structure and its movements in conveying emotions. To overcome this limitation, we introduce an innovative facial motion representation that encompasses 3D facial structure, regionalized RGB and structural motion features. Furthermore, we segment the face into eight distinct regions, selecting only the most significant motion points to delineate the primary motion characteristics of each area. To model the interactions among crucial facial motion regions, we employ an advanced, lightweight point cloud and graph convolution network (Lite-Point-GCN). Comprehensive testing on the $\mathrm{CAS(ME)^{3}}$ dataset, using leave-one-subject-out (LOSO), demonstrates that our method outperforms existing state-of-the-art methods.
- 28 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 17 (2) , 1344-1358
Facial 3D Regional Structural Motion Representation Using Lightweight Point Cloud Networks for Micro-Expression Recognition
Human-computer interaction (HCI) relies on understanding and adapting to users' emotional states. Micro-expressions (MEs), a critical component of emotional perception, are characterized by their spontaneity, rapidity, subtlety, and difficulty to control. They often reveal an individual's true emotions. A comprehensive and detailed representation of motion is necessary to capture the nuances of facial dynamics effectively. Presently, motion representation methods are predominantly confined to 2D analysis within RGB images, overlooking the critical role of facial structure and its movements in conveying emotions. To overcome this limitation, we introduce an innovative facial motion representation that encompasses 3D facial structure, regionalized RGB and structural motion features. Furthermore, we segment the face into eight distinct regions, selecting only the most significant motion points to delineate the primary motion characteristics of each area. To model the interactions among crucial facial motion regions, we employ an advanced, lightweight point cloud and graph convolution network (Lite-Point-GCN). Comprehensive testing on the $\mathrm{CAS(ME)^{3}}$ dataset, using leave-one-subject-out (LOSO), demonstrates that our method outperforms existing state-of-the-art methods.
- 4 December 2024
- Published by Springer Nature
- p. 260-272
Full-Frequency Dynamic Convolution: A Physical Frequency-Dependent Convolution for Sound Event Detection
- 4 December 2024
- Published by Springer Nature
- p. 260-272
Full-Frequency Dynamic Convolution: A Physical Frequency-Dependent Convolution for Sound Event Detection
- Open Access
MTDA-HSED: Mutual-Assistance Tuning and Dual-Branch Aggregating for Heterogeneous Sound Event Detection
Sound Event Detection (SED) plays a vital role in comprehending and perceiving acoustic scenes. Previous methods have demonstrated impressive capabilities. However, they are deficient in learning features of complex scenes from heterogeneous dataset. In this paper, we introduce a novel dual-branch architecture named Mutual-Assistance Tuning and Dual-Branch Aggregating for Heterogeneous Sound Event Detection (MTDA-HSED). The MTDA-HSED architecture employs the Mutual-Assistance Audio Adapter (M3A) to effectively tackle the multi-scenario problem and uses the Dual-Branch Mid-Fusion (DBMF) module to tackle the multi-granularity problem. Specifically, M3A is integrated into the BEATs block as an adapter to improve the BEATs' performance by fine-tuning it on the multi-scenario dataset. The DBMF module connects BEATs and CNN branches, which facilitates the deep fusion of information from the BEATs and the CNN branches. Experimental results show that the proposed methods exceed the baseline of mpAUC by \textbf{$5\%$} on the DESED and MAESTRO Real datasets. Code is available at https://github.com/Visitor-W/MTDA.
Open AccessMTDA-HSED: Mutual-Assistance Tuning and Dual-Branch Aggregating for Heterogeneous Sound Event Detection
Sound Event Detection (SED) plays a vital role in comprehending and perceiving acoustic scenes. Previous methods have demonstrated impressive capabilities. However, they are deficient in learning features of complex scenes from heterogeneous dataset. In this paper, we introduce a novel dual-branch architecture named Mutual-Assistance Tuning and Dual-Branch Aggregating for Heterogeneous Sound Event Detection (MTDA-HSED). The MTDA-HSED architecture employs the Mutual-Assistance Audio Adapter (M3A) to effectively tackle the multi-scenario problem and uses the Dual-Branch Mid-Fusion (DBMF) module to tackle the multi-granularity problem. Specifically, M3A is integrated into the BEATs block as an adapter to improve the BEATs' performance by fine-tuning it on the multi-scenario dataset. The DBMF module connects BEATs and CNN branches, which facilitates the deep fusion of information from the BEATs and the CNN branches. Experimental results show that the proposed methods exceed the baseline of mpAUC by \textbf{$5\%$} on the DESED and MAESTRO Real datasets. Code is available at https://github.com/Visitor-W/MTDA.
- 11 March 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 292
April-GCN: Adjacency Position-velocity Relationship Interaction Learning GCN for Human motion prediction
- 11 March 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 292
April-GCN: Adjacency Position-velocity Relationship Interaction Learning GCN for Human motion prediction
- 26 January 2024
- Published by Elsevier in Neurocomputing
- Vol. 575
Physics-constrained attack against convolution-based human motion prediction
- 26 January 2024
- Published by Elsevier in Neurocomputing
- Vol. 575
Physics-constrained attack against convolution-based human motion prediction
- Open Access
Physics-constrained Attack against Convolution-based Human Motion Prediction
Human motion prediction has achieved a brilliant performance with the help of convolution-based neural networks. However, currently, there is no work evaluating the potential risk in human motion prediction when facing adversarial attacks. The adversarial attack will encounter problems against human motion prediction in naturalness and data scale. To solve the problems above, we propose a new adversarial attack method that generates the worst-case perturbation by maximizing the human motion predictor's prediction error with physical constraints. Specifically, we introduce a novel adaptable scheme that facilitates the attack to suit the scale of the target pose and two physical constraints to enhance the naturalness of the adversarial example. The evaluating experiments on three datasets show that the prediction errors of all target models are enlarged significantly, which means current convolution-based human motion prediction models are vulnerable to the proposed attack. Based on the experimental results, we provide insights on how to enhance the adversarial robustness of the human motion predictor and how to improve the adversarial attack against human motion prediction.
Open AccessPhysics-constrained Attack against Convolution-based Human Motion Prediction
Human motion prediction has achieved a brilliant performance with the help of convolution-based neural networks. However, currently, there is no work evaluating the potential risk in human motion prediction when facing adversarial attacks. The adversarial attack will encounter problems against human motion prediction in naturalness and data scale. To solve the problems above, we propose a new adversarial attack method that generates the worst-case perturbation by maximizing the human motion predictor's prediction error with physical constraints. Specifically, we introduce a novel adaptable scheme that facilitates the attack to suit the scale of the target pose and two physical constraints to enhance the naturalness of the adversarial example. The evaluating experiments on three datasets show that the prediction errors of all target models are enlarged significantly, which means current convolution-based human motion prediction models are vulnerable to the proposed attack. Based on the experimental results, we provide insights on how to enhance the adversarial robustness of the human motion predictor and how to improve the adversarial attack against human motion prediction.