Hongsong 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
Hongsong Wang has a total of 102 co-authors. Here are the top co-authors by number of shared publications:
- Jie Gui
School of Cyber Science and Engineering, Southeast University, Nanjing, China
13 shared publications - Liang Wang
Institute of Automation, Chinese Academy of Sciences, Beijing, China
8 shared publications - Guo-Sen Xie
Nanjing University of Science and Technology, Nanjing, China
7 shared publications - Xin Geng
School of Computer Science and Engineering, Southeast University, Nanjing, China and Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China
7 shared publications - Junbo Wang
School of Software, Northwestern Polytechnical University, Xian, China
5 shared publications - Fang Zhao
Nanjing University
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4194-4203
GenPrior: Unleashing Text-to-Motion Generative Priors for Zero-Shot Skeleton-based Action Recognition
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4194-4203
Open AccessGenPrior: Unleashing Text-to-Motion Generative Priors for Zero-Shot Skeleton-based Action Recognition
- 1 October 2026
- Published by Springer Nature
- p. 152-169
QST-SAM: Leveraging Cross-Modal Instructions for Few-Shot Referring Video Object Segmentation
- 1 October 2026
- Published by Springer Nature
- p. 152-169
QST-SAM: Leveraging Cross-Modal Instructions for Few-Shot Referring Video Object Segmentation
- 13 September 2026
- Published by Springer Nature
- p. 300-318
Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection
- 13 September 2026
- Published by Springer Nature
- p. 300-318
Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection
- 10 September 2026
- Published by Springer Nature
- p. 58-75
Virtual Category-Guided Continual Generalized Category Discovery
- 10 September 2026
- Published by Springer Nature
- p. 58-75
Virtual Category-Guided Continual Generalized Category Discovery
- Open Access
- 3 August 2026
- Published by Springer Nature in Visual Intelligence
- Vol. 4 (1) , 20
PAMD: plausibility-aware motion diffusion model for long dance generation
Computational dance generation is crucial in many areas, such as art, human-computer interaction, virtual reality, and digital entertainment, particularly for generating coherent and expressive long dance sequences. Diffusion-based music-to-dance generation has made significant progress, yet existing methods still struggle to produce physically plausible motions. To address this, we propose plausibility-aware motion diffusion (PAMD), a framework for generating dances that are both musically aligned and physically realistic. The core of PAMD lies in the plausible motion constraint (PMC), which leverages neural distance fields (NDFs) to model the actual pose manifold and to guide generated motions toward a physically valid pose manifold. To provide more effective guidance during generation, we incorporate prior motion guidance (PMG), which uses standing poses as auxiliary conditions alongside music features. To further enhance realism for complex movements, we introduce the contact-based motion refinement (CMR) module, which addresses foot-skating artifacts by bridging the gap between the optimization objective in linear joint position space and the data representation in nonlinear rotation space. Extensive experiments show that PAMD significantly improves musical alignment and enhances the physical plausibility of generated motions.
- 3 August 2026
- Published by Springer Nature in Visual Intelligence
- Vol. 4 (1) , 20
Open AccessPAMD: plausibility-aware motion diffusion model for long dance generation
Computational dance generation is crucial in many areas, such as art, human-computer interaction, virtual reality, and digital entertainment, particularly for generating coherent and expressive long dance sequences. Diffusion-based music-to-dance generation has made significant progress, yet existing methods still struggle to produce physically plausible motions. To address this, we propose plausibility-aware motion diffusion (PAMD), a framework for generating dances that are both musically aligned and physically realistic. The core of PAMD lies in the plausible motion constraint (PMC), which leverages neural distance fields (NDFs) to model the actual pose manifold and to guide generated motions toward a physically valid pose manifold. To provide more effective guidance during generation, we incorporate prior motion guidance (PMG), which uses standing poses as auxiliary conditions alongside music features. To further enhance realism for complex movements, we introduce the contact-based motion refinement (CMR) module, which addresses foot-skating artifacts by bridging the gap between the optimization objective in linear joint position space and the data representation in nonlinear rotation space. Extensive experiments show that PAMD significantly improves musical alignment and enhances the physical plausibility of generated motions.
- 8 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-12
Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models
Existing zero-shot temporal action detection (ZSTAD) methods predominantly use fully supervised or unsupervised strategies to recognize unseen activities. However, these training-based methods are susceptible to domain shifts and entail high computational costs. Unlike previous works, we present FreeZAD, an training-free method for ZSTAD, which leverages image-pretrained vision-language models (VLMs) to directly classify and localize unseen activities within untrimmed videos. We mitigate the need for explicit temporal modeling and reliance on pseudo-label quality by designing the Logarithmic decay weighted Outer-Inner-Contrastive Score (LogOIC) and frequency-based actionness calibration. Furthermore, we introduce a test-time adaptation (TTA) strategy using Prototype-Centric Sampling (PCS) to expand FreeZAD, enabling VLMs to adapt more effectively for ZSTAD. Extensive experiments on the THUMOS14 and ActivityNet-1.3 datasets demonstrate that our training-free method outperforms state-of-the-art unsupervised methods while requiring only 1/13 of the runtime, and the adaptation-enhanced extension further narrows the gap with fully supervised approaches. The code are available at: https://github.com/Chaolei98/FreeZAD.
- 8 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-12
Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models
Existing zero-shot temporal action detection (ZSTAD) methods predominantly use fully supervised or unsupervised strategies to recognize unseen activities. However, these training-based methods are susceptible to domain shifts and entail high computational costs. Unlike previous works, we present FreeZAD, an training-free method for ZSTAD, which leverages image-pretrained vision-language models (VLMs) to directly classify and localize unseen activities within untrimmed videos. We mitigate the need for explicit temporal modeling and reliance on pseudo-label quality by designing the Logarithmic decay weighted Outer-Inner-Contrastive Score (LogOIC) and frequency-based actionness calibration. Furthermore, we introduce a test-time adaptation (TTA) strategy using Prototype-Centric Sampling (PCS) to expand FreeZAD, enabling VLMs to adapt more effectively for ZSTAD. Extensive experiments on the THUMOS14 and ActivityNet-1.3 datasets demonstrate that our training-free method outperforms state-of-the-art unsupervised methods while requiring only 1/13 of the runtime, and the adaptation-enhanced extension further narrows the gap with fully supervised approaches. The code are available at: https://github.com/Chaolei98/FreeZAD.
- 22 May 2026
- Published by Elsevier in Pattern Recognition
- Vol. 180
Efficient Neural Architecture Search for brain-inspired spiking neural network
- 22 May 2026
- Published by Elsevier in Pattern Recognition
- Vol. 180
Efficient Neural Architecture Search for brain-inspired spiking neural network
- 30 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-11
RGS: A Unified Representation-Generation-Selection Framework for Knowledge-Based Visual Question Answering
Knowledge-based visual question answering (VQA) is a task that answers questions with additional knowledge beyond the image itself. Existing methods have either retrieved external knowledge bases to obtain explicit knowledge or utilized large language models (LLMs) to get implicit knowledge. However, it is a complicated pipeline to construct and retrieve these knowledge bases, which can introduce additional information unrelated to the question. In addition, LLM-based methods leverage image captions related to the question as contextual information to prompt LLMs, which suffer from insufficient contextual information and lack the key details necessary to answer the question. To address the issues, we propose a unified representation-generation-selection framework, named RGS, which first obtains multi-source captioning-fused image context representation based on multiple different question-aware image captioning models, then generates candidate answers via a two-stream in-context learning method combined with the image context representation, finally selects the best answer from the candidate answers by means of instruction tuning. To balance the trade-off between complexity and performance, we only additionally finetune a question-aware image captioning model named InstructCap and an optimal answer reasoning model named InstructJudge. Compared to most methods that rely on LLMs with over 100 billion parameters (e.g., GPT-3 - 175B), our approach leverages the 7B-parameter LLM Mistral-7B as implicit knowledge, achieving state-of-the-art performance on multiple knowledge-based VQA benchmarks and significantly outperforming several previous state-of-the-art methods.
- 30 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-11
RGS: A Unified Representation-Generation-Selection Framework for Knowledge-Based Visual Question Answering
Knowledge-based visual question answering (VQA) is a task that answers questions with additional knowledge beyond the image itself. Existing methods have either retrieved external knowledge bases to obtain explicit knowledge or utilized large language models (LLMs) to get implicit knowledge. However, it is a complicated pipeline to construct and retrieve these knowledge bases, which can introduce additional information unrelated to the question. In addition, LLM-based methods leverage image captions related to the question as contextual information to prompt LLMs, which suffer from insufficient contextual information and lack the key details necessary to answer the question. To address the issues, we propose a unified representation-generation-selection framework, named RGS, which first obtains multi-source captioning-fused image context representation based on multiple different question-aware image captioning models, then generates candidate answers via a two-stream in-context learning method combined with the image context representation, finally selects the best answer from the candidate answers by means of instruction tuning. To balance the trade-off between complexity and performance, we only additionally finetune a question-aware image captioning model named InstructCap and an optimal answer reasoning model named InstructJudge. Compared to most methods that rely on LLMs with over 100 billion parameters (e.g., GPT-3 - 175B), our approach leverages the 7B-parameter LLM Mistral-7B as implicit knowledge, achieving state-of-the-art performance on multiple knowledge-based VQA benchmarks and significantly outperforming several previous state-of-the-art methods.
- 15 April 2026
- Published by Springer Nature in Machine Intelligence Research
- Vol. 23 (5) , 1028-1040
Multimodal Skeleton-based Action Representation Learning via Decomposition and Composition
- 15 April 2026
- Published by Springer Nature in Machine Intelligence Research
- Vol. 23 (5) , 1028-1040
Multimodal Skeleton-based Action Representation Learning via Decomposition and Composition
- 24 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 3623-3632
Data-Free Class-Incremental Gesture Recognition With Prototype-Guided Pseudo-Feature Replay
Gesture recognition is an important research area in the field of computer vision. Most existing efforts focus on close-set scenarios, thereby limiting the capacity to effectively handle unseen or novel gestures. We aim to address class-incremental gesture recognition, which entails the ability to accommodate new and previously unseen gestures over time. Specifically, we introduce a Prototype-Guided Pseudo Feature Replay framework for data-free class-incremental learning. This framework comprises four components: Pseudo Feature Generation with Batch Prototypes (PFGBP), Variational Prototype Replay for old classes, Truncated Cross-Entropy for new classes, and Continual Classifier Re-Training. To tackle the issue of catastrophic forgetting, the PFGBP dynamically generates a diversity of pseudo features in an online manner, leveraging class prototypes of old classes along with batch class prototypes of new classes. Furthermore, the Variational Prototype Replay enforces consistency between the classifier’s weights and the prototypes of old classes, leveraging class prototypes and covariance matrices to enhance robustness and generalization capabilities. The Truncated Cross-Entropy mitigates the impact of domain differences of the classifier caused by pseudo features. Finally, the Continual Classifier Re-Training training strategy is designed to prevent overfitting to new classes and ensure the stability of features extracted from old classes. Extensive experiments conducted on two widely used gesture recognition datasets, namely SHREC 2017 3D and EgoGesture 3D, demonstrate that our approach outperforms existing state-of-the-art methods by 11.8% and 12.8% in terms of mean global accuracy, respectively. The code is available on https://github.com/sunao-101/PGPFR-3/.
- 24 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 3623-3632
Data-Free Class-Incremental Gesture Recognition With Prototype-Guided Pseudo-Feature Replay
Gesture recognition is an important research area in the field of computer vision. Most existing efforts focus on close-set scenarios, thereby limiting the capacity to effectively handle unseen or novel gestures. We aim to address class-incremental gesture recognition, which entails the ability to accommodate new and previously unseen gestures over time. Specifically, we introduce a Prototype-Guided Pseudo Feature Replay framework for data-free class-incremental learning. This framework comprises four components: Pseudo Feature Generation with Batch Prototypes (PFGBP), Variational Prototype Replay for old classes, Truncated Cross-Entropy for new classes, and Continual Classifier Re-Training. To tackle the issue of catastrophic forgetting, the PFGBP dynamically generates a diversity of pseudo features in an online manner, leveraging class prototypes of old classes along with batch class prototypes of new classes. Furthermore, the Variational Prototype Replay enforces consistency between the classifier’s weights and the prototypes of old classes, leveraging class prototypes and covariance matrices to enhance robustness and generalization capabilities. The Truncated Cross-Entropy mitigates the impact of domain differences of the classifier caused by pseudo features. Finally, the Continual Classifier Re-Training training strategy is designed to prevent overfitting to new classes and ensure the stability of features extracted from old classes. Extensive experiments conducted on two widely used gesture recognition datasets, namely SHREC 2017 3D and EgoGesture 3D, demonstrate that our approach outperforms existing state-of-the-art methods by 11.8% and 12.8% in terms of mean global accuracy, respectively. The code is available on https://github.com/sunao-101/PGPFR-3/.