Shaojie Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shaojie Zhang has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
Jianqin Yin
4 shared publications- Jianqin Yin
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 Baoxun Gu
2 shared publications- Jin Tang
Beijing University of Posts and Telecommunications
2 shared publications - Mingxiu Chen2 shared publications
Latest Publications
- Open Access
- 19 June 2026
- Published by Elsevier in SSRN Electronic Journal
Test on the Unseen: Making Human Motion Prediction Generalizable
Traditional human motion prediction (HMP) tasks usually follow a training scheme with the same or similar distributions of action and actor classes.However, it is difficult for training samples to cover all action types and actor characteristics in the real world.This motivates us to propose a novel generalization task for human motion prediction (G-HMP), which uses incomplete action and actor classes during training to predict the new unseen ones.The core objective of G-HMP is to enhance the model's ability to understand action semantics and human kinematic patterns, enabling it to achieve transferable prediction and domain generalization in real-world scenarios.To address the challenges of data scarcity and decreased variety of learnable motion patterns posed by G-HMP, we propose cross-action actor augmentation (CA) and positional blurred motion prediction (PB) methods.CA is a method that enhances dataset diversity by generating new motion sequences across different actions and actors through time reversal, skeletal mirroring, and inertial motion techniques.PB encourages the learning of motion dynamics rather than accurate joint positions by blurring positional information, consequently improving the model's generalization and predictive performance.Experiments on H3.6M and CMU datasets validate the validity of G-HMP and the effectiveness of the proposed methods.
- 19 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessTest on the Unseen: Making Human Motion Prediction Generalizable
Traditional human motion prediction (HMP) tasks usually follow a training scheme with the same or similar distributions of action and actor classes.However, it is difficult for training samples to cover all action types and actor characteristics in the real world.This motivates us to propose a novel generalization task for human motion prediction (G-HMP), which uses incomplete action and actor classes during training to predict the new unseen ones.The core objective of G-HMP is to enhance the model's ability to understand action semantics and human kinematic patterns, enabling it to achieve transferable prediction and domain generalization in real-world scenarios.To address the challenges of data scarcity and decreased variety of learnable motion patterns posed by G-HMP, we propose cross-action actor augmentation (CA) and positional blurred motion prediction (PB) methods.CA is a method that enhances dataset diversity by generating new motion sequences across different actions and actors through time reversal, skeletal mirroring, and inertial motion techniques.PB encourages the learning of motion dynamics rather than accurate joint positions by blurring positional information, consequently improving the model's generalization and predictive performance.Experiments on H3.6M and CMU datasets validate the validity of G-HMP and the effectiveness of the proposed methods.
- Open Access
- 18 May 2026
- Published by Elsevier in SSRN Electronic Journal
Test on the Unseen: Making Human Motion Prediction Generalizable
Traditional human motion prediction (HMP) tasks usually follow a training scheme with the same or similar distributions of action and actor classes.However, it is difficult for training samples to cover all action types and actor characteristics in the real world.This motivates us to propose a novel generalization task for human motion prediction (G-HMP), which uses incomplete action and actor classes during training to predict the new unseen ones.The core objective of G-HMP is to enhance the model's ability to understand action semantics and human kinematic patterns, enabling it to achieve transferable prediction and domain generalization in real-world scenarios.To address the challenges of data scarcity and decreased variety of learnable motion patterns posed by G-HMP, we propose cross-action\&actor augmentation (CA) and positional blurred motion prediction (PB) methods.CA is a method that enhances dataset diversity by generating new motion sequences across different actions and actors through time reversal, skeletal mirroring, and inertial motion techniques.PB encourages the learning of motion dynamics rather than accurate joint positions by blurring positional information, consequently improving the model's generalization and predictive performance.Experiments on H3.6M and CMU datasets validate the validity of G-HMP and the effectiveness of the proposed methods.
- 18 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessTest on the Unseen: Making Human Motion Prediction Generalizable
Traditional human motion prediction (HMP) tasks usually follow a training scheme with the same or similar distributions of action and actor classes.However, it is difficult for training samples to cover all action types and actor characteristics in the real world.This motivates us to propose a novel generalization task for human motion prediction (G-HMP), which uses incomplete action and actor classes during training to predict the new unseen ones.The core objective of G-HMP is to enhance the model's ability to understand action semantics and human kinematic patterns, enabling it to achieve transferable prediction and domain generalization in real-world scenarios.To address the challenges of data scarcity and decreased variety of learnable motion patterns posed by G-HMP, we propose cross-action\&actor augmentation (CA) and positional blurred motion prediction (PB) methods.CA is a method that enhances dataset diversity by generating new motion sequences across different actions and actors through time reversal, skeletal mirroring, and inertial motion techniques.PB encourages the learning of motion dynamics rather than accurate joint positions by blurring positional information, consequently improving the model's generalization and predictive performance.Experiments on H3.6M and CMU datasets validate the validity of G-HMP and the effectiveness of the proposed methods.
- 5 March 2025
- Published by Elsevier in Pattern Recognition
- Vol. 164
A generically Contrastive Spatiotemporal Representation Enhancement for 3D skeleton action recognition
- 5 March 2025
- Published by Elsevier in Pattern Recognition
- Vol. 164
A generically Contrastive Spatiotemporal Representation Enhancement for 3D skeleton action recognition
- 3 September 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 304
MLP-AIR: An effective MLP-based module for actor interaction relation learning in group activity recognition
- 3 September 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 304
MLP-AIR: An effective MLP-based module for actor interaction relation learning in group activity recognition
- 9 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (9) , 8122-8134
SiT-MLP: A Simple MLP With Point-Wise Topology Feature Learning for Skeleton-Based Action Recognition
Graph convolution networks (GCNs) have achieved remarkable performance in skeleton-based action recognition. However, previous GCN-based methods rely on elaborate human priors excessively and construct complex feature aggregation mechanisms, which limits the generalizability and effectiveness of networks. To solve these problems, we propose a novel Spatial Topology Gating Unit (STGU), an MLP-based variant without extra priors, to capture the co-occurrence topology features that encode the spatial dependency across all joints. In STGU, to learn the point-wise topology features, a new gate-based feature interaction mechanism is introduced to activate the features point-to-point by the attention map generated from the input sample. Based on the STGU, we propose the first MLP-based model, SiT-MLP, for skeleton-based action recognition in this work. Compared with previous methods on three large-scale datasets, SiT-MLP achieves competitive performance. In addition, SiT-MLP reduces the parameters significantly with favorable results. The code will be available at https://github.com/BUPTSJZhang/SiT-MLP.
- 9 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (9) , 8122-8134
SiT-MLP: A Simple MLP With Point-Wise Topology Feature Learning for Skeleton-Based Action Recognition
Graph convolution networks (GCNs) have achieved remarkable performance in skeleton-based action recognition. However, previous GCN-based methods rely on elaborate human priors excessively and construct complex feature aggregation mechanisms, which limits the generalizability and effectiveness of networks. To solve these problems, we propose a novel Spatial Topology Gating Unit (STGU), an MLP-based variant without extra priors, to capture the co-occurrence topology features that encode the spatial dependency across all joints. In STGU, to learn the point-wise topology features, a new gate-based feature interaction mechanism is introduced to activate the features point-to-point by the attention map generated from the input sample. Based on the STGU, we propose the first MLP-based model, SiT-MLP, for skeleton-based action recognition in this work. Compared with previous methods on three large-scale datasets, SiT-MLP achieves competitive performance. In addition, SiT-MLP reduces the parameters significantly with favorable results. The code will be available at https://github.com/BUPTSJZhang/SiT-MLP.
- 29 January 2024
- Published by Elsevier in Pattern Recognition
- Vol. 150
Kinematics modeling network for video-based human pose estimation
- 29 January 2024
- Published by Elsevier in Pattern Recognition
- Vol. 150
Kinematics modeling network for video-based human pose estimation
- 1 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 31 (10577149) , 3973-3986
Relation-Based Associative Joint Location for Human Pose Estimation in Videos
Video-based human pose estimation (VHPE) is a vital yet challenging task. While deep learning algorithms have made tremendous progress for the VHPE, lots of these approaches to this task implicitly model the long-range interaction between joints by expanding the receptive field of the convolution or designing a graph manually. Unlike prior methods, we design a lightweight and plug-and-play joint relation extractor (JRE) to explicitly and automatically model the associative relationship between joints. The JRE takes the pseudo heatmaps of joints as input and calculates their similarity. In this way, the JRE can flexibly learn the correlation between any two joints, allowing it to learn the rich spatial configuration of human poses. Furthermore, the JRE can infer invisible joints according to the correlation between joints, which is beneficial for locating occluded joints. Then, combined with temporal semantic continuity modeling, we propose a Relation-based Pose Semantics Transfer Network (RPSTN) for video-based human pose estimation. Specifically, to capture the temporal dynamics of poses, the pose semantic information of the current frame is transferred to the next with a joint relation guided pose semantics propagator (JRPSP). The JRPSP can transfer the pose semantic features from the non-occluded frame to the occluded frame. The proposed RPSTN achieves state-of-the-art or competitive results on the video-based Penn Action, Sub-JHMDB, PoseTrack2018, and HiEve datasets. Moreover, the proposed JRE improves the performance of backbones on the image-based COCO2017 dataset. Code is available at https://github.com/YHDang/pose-estimation .
- 1 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 31 (10577149) , 3973-3986
Relation-Based Associative Joint Location for Human Pose Estimation in Videos
Video-based human pose estimation (VHPE) is a vital yet challenging task. While deep learning algorithms have made tremendous progress for the VHPE, lots of these approaches to this task implicitly model the long-range interaction between joints by expanding the receptive field of the convolution or designing a graph manually. Unlike prior methods, we design a lightweight and plug-and-play joint relation extractor (JRE) to explicitly and automatically model the associative relationship between joints. The JRE takes the pseudo heatmaps of joints as input and calculates their similarity. In this way, the JRE can flexibly learn the correlation between any two joints, allowing it to learn the rich spatial configuration of human poses. Furthermore, the JRE can infer invisible joints according to the correlation between joints, which is beneficial for locating occluded joints. Then, combined with temporal semantic continuity modeling, we propose a Relation-based Pose Semantics Transfer Network (RPSTN) for video-based human pose estimation. Specifically, to capture the temporal dynamics of poses, the pose semantic information of the current frame is transferred to the next with a joint relation guided pose semantics propagator (JRPSP). The JRPSP can transfer the pose semantic features from the non-occluded frame to the occluded frame. The proposed RPSTN achieves state-of-the-art or competitive results on the video-based Penn Action, Sub-JHMDB, PoseTrack2018, and HiEve datasets. Moreover, the proposed JRE improves the performance of backbones on the image-based COCO2017 dataset. Code is available at https://github.com/YHDang/pose-estimation .