Zhenhua Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Zhenhua Wang has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
- Jianhua Zhang
Tianjin University of Technology
9 shared publications - Dongyan Guo
Zhejiang University of Technology
5 shared publications Jianhua Zhang
Zhejiang University of Technology Tianjin University of Technology The University of Adelaide
5 shared publications- Jifeng Ning
College of Information Engineering, Northwest A&F University, Yangling 712100, China
5 shared publications Shengyong Chen
Zhejiang University of Technology Tianjin University of Technology The University of Adelaide
5 shared publicationsDongyan Guo
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China
4 shared publications
Latest Publications
- Open Access
- 29 August 2026
- Published by Elsevier in Smart Agricultural Technology
- Vol. 15
Multi-label spatio-temporal behavior detection of dairy goats with decoupled fusion and instance-aware refinement
- 29 August 2026
- Published by Elsevier in Smart Agricultural Technology
- Vol. 15
Open AccessMulti-label spatio-temporal behavior detection of dairy goats with decoupled fusion and instance-aware refinement
- Open Access
- 16 April 2026
- Published by MDPI AG in Electronics
- Vol. 15 (8) , 1679
SheepTrack: Occlusion-Robust Detection and Tracking for Dense Sheep Monitoring
Automated detection and tracking of individual sheep are essential for precision livestock farming. However, existing approaches face significant challenges: (1) Limited dataset diversity with predominant aerial perspectives; (2) Detection failures under severe occlusions; (3) Frequent ID switches due to high appearance similarity. To address these challenges, our paper presents an integrated framework. Firstly, we construct a multi-scene indoor sheep dataset with diverse environmental conditions. Secondly, for detection, we propose an improved YOLOv8 incorporating SheepNMS and Flock-aware Localization Loss (FL-Loss) to handle crowded scenarios and occlusion. Finally, for tracking, we enhance BoT-SORT with a Flock Appearance Module (FAM) and Trajectory Correction Module (TCM) for robust association and drift mitigation. Extensive experiments demonstrate measurable improvements in detection accuracy, tracking consistency, and reductions in ID switches and fragmentations across diverse monitoring scenarios.
- 16 April 2026
- Published by MDPI AG in Electronics
- Vol. 15 (8) , 1679
Open AccessSheepTrack: Occlusion-Robust Detection and Tracking for Dense Sheep Monitoring
Automated detection and tracking of individual sheep are essential for precision livestock farming. However, existing approaches face significant challenges: (1) Limited dataset diversity with predominant aerial perspectives; (2) Detection failures under severe occlusions; (3) Frequent ID switches due to high appearance similarity. To address these challenges, our paper presents an integrated framework. Firstly, we construct a multi-scene indoor sheep dataset with diverse environmental conditions. Secondly, for detection, we propose an improved YOLOv8 incorporating SheepNMS and Flock-aware Localization Loss (FL-Loss) to handle crowded scenarios and occlusion. Finally, for tracking, we enhance BoT-SORT with a Flock Appearance Module (FAM) and Trajectory Correction Module (TCM) for robust association and drift mitigation. Extensive experiments demonstrate measurable improvements in detection accuracy, tracking consistency, and reductions in ID switches and fragmentations across diverse monitoring scenarios.
- 2 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computing
- Vol. PP (3) , 1-12
Adaptive Object Exploration and Mapping through Meta-Reinforcement Learning
Object Exploration and Mapping (OEM) is a novel embodied AI task that requires an agent to autonomously explore unknown environments, simultaneously detect and localize multiple objects, and construct a semantic object-level map. To solve this challenge, we propose a two-stage framework. First, a deep reinforcement learning-based OEM framework (DRL-OEM) is proposed to leverage auxiliary perception tasks and memory-augmented policy learning to guide efficient exploration. Second, we extend the DRL-OEM to Meta-OEM, where a meta-reinforcement learning framework is employed to enhance adaptation to unseen environments with a novel key-behavior-aware prioritized sampling strategy by reusing high-reward transitions. Extensive experiments conducted on customized AI2Thor scenes across diverse layouts and object configurations demonstrate that Meta-OEM significantly outperforms strong baselines, including DRL-OEM, PEARL, and MQL, achieving up to 2× higher success rates and faster convergence during adaptation. Visual and quantitative results confirm its superior object discovery coverage, pose estimation accuracy, and generalization capability in open-world scenarios.
- 2 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computing
- Vol. PP (3) , 1-12
Adaptive Object Exploration and Mapping through Meta-Reinforcement Learning
Object Exploration and Mapping (OEM) is a novel embodied AI task that requires an agent to autonomously explore unknown environments, simultaneously detect and localize multiple objects, and construct a semantic object-level map. To solve this challenge, we propose a two-stage framework. First, a deep reinforcement learning-based OEM framework (DRL-OEM) is proposed to leverage auxiliary perception tasks and memory-augmented policy learning to guide efficient exploration. Second, we extend the DRL-OEM to Meta-OEM, where a meta-reinforcement learning framework is employed to enhance adaptation to unseen environments with a novel key-behavior-aware prioritized sampling strategy by reusing high-reward transitions. Extensive experiments conducted on customized AI2Thor scenes across diverse layouts and object configurations demonstrate that Meta-OEM significantly outperforms strong baselines, including DRL-OEM, PEARL, and MQL, achieving up to 2× higher success rates and faster convergence during adaptation. Visual and quantitative results confirm its superior object discovery coverage, pose estimation accuracy, and generalization capability in open-world scenarios.
- 4 January 2026
- Published by Elsevier in Pattern Recognition
- Vol. 175
LTSTrack: Visual tracking with long-term temporal sequence
- 4 January 2026
- Published by Elsevier in Pattern Recognition
- Vol. 175
LTSTrack: Visual tracking with long-term temporal sequence
- 12 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (2) , 2433-2448
Exploring Pruning-Based Efficient Object Tracking via Hybrid Knowledge Distillation
Transformer-based trackers have demonstrated remarkable advancements in real-time tracking tasks on edge devices. Since lightweight backbone networks are typically designed for general-purpose tasks, our analysis reveals that, when applied to target tracking, they often contain structurally redundant layers, which limits the model’s efficiency. To address this issue, we propose a novel tracking framework that integrates backbone pruning with Hybrid Knowledge Distillation (HKD), effectively reducing model parameters and FLOPs while preserving high tracking accuracy. Inspired by the success of MiniLM and Focal and Global Distillation (FGD), we design a HKD framework tailored for tracking tasks. Our HKD introduces a multi-level and complementary distillation scheme, consisting of Token Distillation, Local Distillation, and Global Distillation. In Token Distillation, unlike MiniLM, which distills attention via QK dot-products and V, we disentangle and separately distill Q, K, and V representations to enhance structural attention alignment for tracking. For Local Distillation, we use the FGD concept by incorporating spatial foreground-background masks to capture region-specific discriminative cues more effectively. In Global Distillation, we use Vision Mamba module to model long-range dependencies and enhance semantic-level feature alignment. Our tracker HKDT achieves state-of-the-art (SOTA) performance across multiple datasets. On the GOT-10k benchmark, it demonstrates a groundbreaking 67.6% Average Overlap (AO), outperforming the current SOTA real-time tracker HiT-Base by 3.6% in accuracy while reducing computational costs by 64% and achieving 115% faster tracking speed on CPU platforms. The code and model will be available soon.
- 12 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (2) , 2433-2448
Exploring Pruning-Based Efficient Object Tracking via Hybrid Knowledge Distillation
Transformer-based trackers have demonstrated remarkable advancements in real-time tracking tasks on edge devices. Since lightweight backbone networks are typically designed for general-purpose tasks, our analysis reveals that, when applied to target tracking, they often contain structurally redundant layers, which limits the model’s efficiency. To address this issue, we propose a novel tracking framework that integrates backbone pruning with Hybrid Knowledge Distillation (HKD), effectively reducing model parameters and FLOPs while preserving high tracking accuracy. Inspired by the success of MiniLM and Focal and Global Distillation (FGD), we design a HKD framework tailored for tracking tasks. Our HKD introduces a multi-level and complementary distillation scheme, consisting of Token Distillation, Local Distillation, and Global Distillation. In Token Distillation, unlike MiniLM, which distills attention via QK dot-products and V, we disentangle and separately distill Q, K, and V representations to enhance structural attention alignment for tracking. For Local Distillation, we use the FGD concept by incorporating spatial foreground-background masks to capture region-specific discriminative cues more effectively. In Global Distillation, we use Vision Mamba module to model long-range dependencies and enhance semantic-level feature alignment. Our tracker HKDT achieves state-of-the-art (SOTA) performance across multiple datasets. On the GOT-10k benchmark, it demonstrates a groundbreaking 67.6% Average Overlap (AO), outperforming the current SOTA real-time tracker HiT-Base by 3.6% in accuracy while reducing computational costs by 64% and achieving 115% faster tracking speed on CPU platforms. The code and model will be available soon.
- 25 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (5) , 9474-9487
Graph Attention Network for Context-Aware Visual Tracking
Siamese-network-based trackers convert the general object tracking as a similarity matching task between a template and a search region. Using convolutional feature cross correlation (Xcorr) for similarity matching, a large number of Siamese trackers are proposed and achieved great success. However, due to the predefined size of the target feature, these trackers suffer from either retaining much background information or losing important foreground information. Moreover, the global matching between the target and search region also largely neglects the part-level structural information and the contextual information of the target. To tackle the aforementioned obstacles, in this article, we propose a simple context-aware Siamese graph attention network, which establishes part-to-part correspondence between the Siamese branches with a complete bipartite graph. The object information from the template is propagated to the search region via a graph attention mechanism. With such a design, a target-aware template input is enabled to replace the prefixed template region, which can adaptively fit the size and aspect ratio variations in different objects. Based on it, we further construct a context-aware feature matching mechanism to embed both the target and the contextual information in the search region. Experiments on challenging benchmarks including GOT-10k, TrackingNet, LaSOT, VOT2020, and OTB-100 demonstrate that the proposed SiamGAT* outperforms many state-of-the-art trackers and achieves leading performance. Code is available at: https://git.io/SiamGAT.
- 25 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (5) , 9474-9487
Graph Attention Network for Context-Aware Visual Tracking
Siamese-network-based trackers convert the general object tracking as a similarity matching task between a template and a search region. Using convolutional feature cross correlation (Xcorr) for similarity matching, a large number of Siamese trackers are proposed and achieved great success. However, due to the predefined size of the target feature, these trackers suffer from either retaining much background information or losing important foreground information. Moreover, the global matching between the target and search region also largely neglects the part-level structural information and the contextual information of the target. To tackle the aforementioned obstacles, in this article, we propose a simple context-aware Siamese graph attention network, which establishes part-to-part correspondence between the Siamese branches with a complete bipartite graph. The object information from the template is propagated to the search region via a graph attention mechanism. With such a design, a target-aware template input is enabled to replace the prefixed template region, which can adaptively fit the size and aspect ratio variations in different objects. Based on it, we further construct a context-aware feature matching mechanism to embed both the target and the contextual information in the search region. Experiments on challenging benchmarks including GOT-10k, TrackingNet, LaSOT, VOT2020, and OTB-100 demonstrate that the proposed SiamGAT* outperforms many state-of-the-art trackers and achieves leading performance. Code is available at: https://git.io/SiamGAT.
- 9 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 5073-5085
Modeling of Multiple Spatial-Temporal Relations for Robust Visual Object Tracking
Recently, one-stream trackers have achieved parallel feature extraction and relation modelling through the exploitation of Transformer-based architectures. This design greatly improves the performance of trackers. However, as one-stream trackers often overlook crucial tracking cues beyond the template, they prone to give unsatisfactory results against complex tracking scenarios. To tackle these challenges, we propose a multi-cue single-stream tracker, dubbed MCTrack here, which seamlessly integrates template information, historical trajectory, historical frame, and the search region for synchronized feature extraction and relation modelling. To achieve this, we employ two types of encoders to convert the template, historical frames, search region, and historical trajectory into tokens, which are then collectively fed into a Transformer architecture. To distill temporal and spatial cues, we introduce a novel adaptive update mechanism, which incorporates a thresholding component and a local multi-peak component to filter out less accurate and overly disturbed tracking cues. Empirically, MCTrack achieves leading performance on mainstream benchmark datasets, surpassing the most advanced SeqTrack by 2.0% in terms of the AO metric on GOT-10k. The source code will be made available.
- 9 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 5073-5085
Modeling of Multiple Spatial-Temporal Relations for Robust Visual Object Tracking
Recently, one-stream trackers have achieved parallel feature extraction and relation modelling through the exploitation of Transformer-based architectures. This design greatly improves the performance of trackers. However, as one-stream trackers often overlook crucial tracking cues beyond the template, they prone to give unsatisfactory results against complex tracking scenarios. To tackle these challenges, we propose a multi-cue single-stream tracker, dubbed MCTrack here, which seamlessly integrates template information, historical trajectory, historical frame, and the search region for synchronized feature extraction and relation modelling. To achieve this, we employ two types of encoders to convert the template, historical frames, search region, and historical trajectory into tokens, which are then collectively fed into a Transformer architecture. To distill temporal and spatial cues, we introduce a novel adaptive update mechanism, which incorporates a thresholding component and a local multi-peak component to filter out less accurate and overly disturbed tracking cues. Empirically, MCTrack achieves leading performance on mainstream benchmark datasets, surpassing the most advanced SeqTrack by 2.0% in terms of the AO metric on GOT-10k. The source code will be made available.
- 13 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (8) , 7259-7271
Bidirectional Interaction of CNN and Transformer Feature for Visual Tracking
Empowered by the sophisticated long-range dependency modeling ability of Transformer, tracking performance has seen a dynamic increase in recent years. Approaches in this vein leverage the Transformer feature to integrate the information of target and search regions while neglecting the superior local representation extracted by their CNN backbone. To address this, we introduce a BIdirectional inTeraction mechanism between CNN and Transformer features for visual tracking, termed BIT-Tracker, which admits a comprehensive fusion of local and global representations, and thus boosts tracking performance. The first ingredient of BIT-Tracker is an aggregation of multi-level Transformer features to achieve a better global modeling ability. In order to combine the merits of both local and global representations, our second ingredient performs a bi-directional interaction between CNN and Transformer features, where the interaction is achieved via either querying the CNN feature from the Transformer feature or querying the Transformer feature from the CNN feature. Afterwards, the outputs from both directions are fused to predict the temporal locations of targets. Extensive experiments demonstrate the effectiveness of the proposed feature aggregation and bi-directional interaction modules. Impressively, BIT-Tracker achieves leading performance on eight tracking benchmarks and outperforms SOTA results by salient margins. Code will be made available.
- 13 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (8) , 7259-7271
Bidirectional Interaction of CNN and Transformer Feature for Visual Tracking
Empowered by the sophisticated long-range dependency modeling ability of Transformer, tracking performance has seen a dynamic increase in recent years. Approaches in this vein leverage the Transformer feature to integrate the information of target and search regions while neglecting the superior local representation extracted by their CNN backbone. To address this, we introduce a BIdirectional inTeraction mechanism between CNN and Transformer features for visual tracking, termed BIT-Tracker, which admits a comprehensive fusion of local and global representations, and thus boosts tracking performance. The first ingredient of BIT-Tracker is an aggregation of multi-level Transformer features to achieve a better global modeling ability. In order to combine the merits of both local and global representations, our second ingredient performs a bi-directional interaction between CNN and Transformer features, where the interaction is achieved via either querying the CNN feature from the Transformer feature or querying the Transformer feature from the CNN feature. Afterwards, the outputs from both directions are fused to predict the temporal locations of targets. Extensive experiments demonstrate the effectiveness of the proposed feature aggregation and bi-directional interaction modules. Impressively, BIT-Tracker achieves leading performance on eight tracking benchmarks and outperforms SOTA results by salient margins. Code will be made available.