Wenze Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wenze Huang 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
4 shared publications - Honghai Liu
Harbin Institute of Technology (Shenzhen)
4 shared publications - Weihong Ren
Harbin Institute of Technology
4 shared publications - Zhiyong Wang
Harbin Institute of Technology
4 shared publications - Bowen Chen
State Key Laboratory of Robotics and Systems, Harbin Institute of Technology (Shenzhen), Shenzhen, China
3 shared publications - Zhihao Yang
State Key Laboratory of Robotics and Systems, Harbin Institute of Technology (Shenzhen), Shenzhen, China
3 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.
- 6 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (9) , 17462-17476
Snippet-Aware Transformer With Multiple Action Elements for Skeleton-Based Action Segmentation
The skeleton-based temporal action segmentation (STAS) aims to densely segment and classify human actions within lengthy untrimmed skeletal motion sequences. Current methods primarily rely on graph convolutional networks (GCNs) for intraframe spatial modeling and temporal convolutional networks (TCNs) for interframe temporal modeling to discern motion patterns. However, these approaches often overlook the distinctive nature of essential action elements across various actions, including engaged core body parts and key subactions. This oversight limits the ability to distinguish different actions within a given sequence. To address these limitations, the snippet-aware Transformer with multiple action element (ME-ST) is proposed to enhance the discrimination and segmentation among actions, which leverages intrasnippet attention along joints and sequences to identify core joints and key subactions at different scales. Specifically, in terms of the spatial domain, the intrasnippet cross-joint attention (CJA) module divides the sequence into distinct snippets and computes attention to establish intricate joint semantic relationships, emphasizing the identification of core motion joints. In terms of the temporal domain, in the encoder, the intrasnippet cross-frame attention (CFA) module segments the sequence in a blockwise expansion manner and establishes interframe relationships to highlight the most discriminative frames. In the decoder, clip-level representations at various temporal scales are initially generated through an hourglass-like sampling process, followed by the intrasnippet cross-scale attention (CSA) module to integrate the key clip information across different time scales. The performance evaluation on five public datasets demonstrates that ME-ST achieves state-of-the-art (SOTA) performance.
- 6 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (9) , 17462-17476
Snippet-Aware Transformer With Multiple Action Elements for Skeleton-Based Action Segmentation
The skeleton-based temporal action segmentation (STAS) aims to densely segment and classify human actions within lengthy untrimmed skeletal motion sequences. Current methods primarily rely on graph convolutional networks (GCNs) for intraframe spatial modeling and temporal convolutional networks (TCNs) for interframe temporal modeling to discern motion patterns. However, these approaches often overlook the distinctive nature of essential action elements across various actions, including engaged core body parts and key subactions. This oversight limits the ability to distinguish different actions within a given sequence. To address these limitations, the snippet-aware Transformer with multiple action element (ME-ST) is proposed to enhance the discrimination and segmentation among actions, which leverages intrasnippet attention along joints and sequences to identify core joints and key subactions at different scales. Specifically, in terms of the spatial domain, the intrasnippet cross-joint attention (CJA) module divides the sequence into distinct snippets and computes attention to establish intricate joint semantic relationships, emphasizing the identification of core motion joints. In terms of the temporal domain, in the encoder, the intrasnippet cross-frame attention (CFA) module segments the sequence in a blockwise expansion manner and establishes interframe relationships to highlight the most discriminative frames. In the decoder, clip-level representations at various temporal scales are initially generated through an hourglass-like sampling process, followed by the intrasnippet cross-scale attention (CSA) module to integrate the key clip information across different time scales. The performance evaluation on five public datasets demonstrates that ME-ST achieves state-of-the-art (SOTA) performance.