Zhihao Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhihao Yang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Haoyu Ji
Harbin Institute of Technology Shenzhen
3 shared publications - Honghai Liu
Harbin Institute of Technology (Shenzhen)
3 shared publications - Weihong Ren
Harbin Institute of Technology
3 shared publications - Wenze Huang
State Key Laboratory of Robotics and Systems, Harbin Institute of Technology (Shenzhen), Shenzhen, China
3 shared publications - Zhiyong Wang
Harbin Institute of Technology
3 shared publications - Bowen Chen
State Key Laboratory of Robotics and Systems, Harbin Institute of Technology (Shenzhen), Shenzhen, China
2 shared publications
Latest Publications
- 12 September 2026
- Published by Springer Nature
- p. 613-631
PhysFlowNet: Learning Canonical Latent Manifolds via Spatio-Spectral Physics Priors for Underwater Object Detection
- 12 September 2026
- Published by Springer Nature
- p. 613-631
PhysFlowNet: Learning Canonical Latent Manifolds via Spatio-Spectral Physics Priors for Underwater Object Detection
- 27 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (5) , 7236-7249
Topology-Motion Decoupling Framework With Textual Regularization for Skeleton-Based Temporal Action Segmentation
Skeleton-based temporal action segmentation aims to capture key information in long skeleton motion sequences to temporally segment and identify actions at a fine-grained level. Existing approaches have achieved promising results by improving the modeling of topological spatial relationships and long-term temporal dependencies. However, current methods often overlook the distinct nature of motion and topological information, applying a monolithic modeling paradigm to both. This approach fails to fully exploit their differential contributions to precise boundary localization and effective class discrimination. To address these limitations, we propose a novel Topology-Motion Decoupling Framework (TMD). Our framework incorporates three key designs. First, an auxiliary Differential Motion Perception Branch explicitly models the temporal gradients of skeletal trajectory to decouple boundary-sensitive motion features. Second, we introduce two effective fusion modules that integrate the complementary features from both branches for mutual enhancement. Finally, a Boundary-Aware Textual Regularization scheme leverages a dual set of semantic prompts for boundary/non-boundary to differentially guide the feature learning process. By design, TMD explicitly mitigates semantic and temporal confusion between actions, thereby enhancing inter-class discriminability and boundary awareness. Extensive experiments on five challenging public datasets demonstrate that our TMD achieves state-of-the-art performance.
- 27 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (5) , 7236-7249
Topology-Motion Decoupling Framework With Textual Regularization for Skeleton-Based Temporal Action Segmentation
Skeleton-based temporal action segmentation aims to capture key information in long skeleton motion sequences to temporally segment and identify actions at a fine-grained level. Existing approaches have achieved promising results by improving the modeling of topological spatial relationships and long-term temporal dependencies. However, current methods often overlook the distinct nature of motion and topological information, applying a monolithic modeling paradigm to both. This approach fails to fully exploit their differential contributions to precise boundary localization and effective class discrimination. To address these limitations, we propose a novel Topology-Motion Decoupling Framework (TMD). Our framework incorporates three key designs. First, an auxiliary Differential Motion Perception Branch explicitly models the temporal gradients of skeletal trajectory to decouple boundary-sensitive motion features. Second, we introduce two effective fusion modules that integrate the complementary features from both branches for mutual enhancement. Finally, a Boundary-Aware Textual Regularization scheme leverages a dual set of semantic prompts for boundary/non-boundary to differentially guide the feature learning process. By design, TMD explicitly mitigates semantic and temporal confusion between actions, thereby enhancing inter-class discriminability and boundary awareness. Extensive experiments on five challenging public datasets demonstrate that our TMD achieves state-of-the-art performance.
- 29 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 7305-7320
Text-Derived Relational Graph-Enhanced Network for Skeleton-Based Action Segmentation
Skeleton-based Temporal Action Segmentation (STAS) aims to segment and recognize various actions from long, untrimmed sequences of human skeletal movements. Current STAS methods typically employ spatio-temporal modeling to establish dependencies among joints as well as frames, and utilize one-hot encoding with cross-entropy loss for frame-wise classification supervision. However, these methods overlook the intrinsic correlations among joints and actions within skeletal features, leading to a limited understanding of human movements. To address this, we propose a Text-Derived Relational Graph-Enhanced Network (TRG-Net) that leverages prior graphs generated by Large Language Models (LLM) to enhance both modeling and supervision. For modeling, the Dynamic Spatio-Temporal Fusion Modeling (DSFM) method incorporates Text-Derived Joint Graphs (TJG) with channel- and frame-level dynamic adaptation to effectively model spatial relations, while integrating spatio-temporal core features during temporal modeling. For supervision, the Absolute-Relative Inter-Class Supervision (ARIS) method employs contrastive learning between action features and text embeddings to regularize the absolute class distributions, and utilizes Text-Derived Action Graphs (TAG) to capture the relative inter-class relationships among action features. Additionally, we propose a Spatial-Aware Enhancement Processing (SAEP) method, which incorporates random joint occlusion and axial rotation to enhance spatial generalization. Performance evaluations on four public datasets demonstrate that TRG-Net achieves state-of-the-art results.
- 29 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 7305-7320
Text-Derived Relational Graph-Enhanced Network for Skeleton-Based Action Segmentation
Skeleton-based Temporal Action Segmentation (STAS) aims to segment and recognize various actions from long, untrimmed sequences of human skeletal movements. Current STAS methods typically employ spatio-temporal modeling to establish dependencies among joints as well as frames, and utilize one-hot encoding with cross-entropy loss for frame-wise classification supervision. However, these methods overlook the intrinsic correlations among joints and actions within skeletal features, leading to a limited understanding of human movements. To address this, we propose a Text-Derived Relational Graph-Enhanced Network (TRG-Net) that leverages prior graphs generated by Large Language Models (LLM) to enhance both modeling and supervision. For modeling, the Dynamic Spatio-Temporal Fusion Modeling (DSFM) method incorporates Text-Derived Joint Graphs (TJG) with channel- and frame-level dynamic adaptation to effectively model spatial relations, while integrating spatio-temporal core features during temporal modeling. For supervision, the Absolute-Relative Inter-Class Supervision (ARIS) method employs contrastive learning between action features and text embeddings to regularize the absolute class distributions, and utilizes Text-Derived Action Graphs (TAG) to capture the relative inter-class relationships among action features. Additionally, we propose a Spatial-Aware Enhancement Processing (SAEP) method, which incorporates random joint occlusion and axial rotation to enhance spatial generalization. Performance evaluations on four public datasets demonstrate that TRG-Net achieves state-of-the-art results.