Selected Publications

2026

1. TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition

   Yanan Liu, Jun Liu, Hao Zhang, Kangjian He, Dan Xu, Hossein Rahmani, Mohammed Bennamoun, and Qiuhong Ke

   BMVC 2026| British Machine Vision Conference

   PDF Code
2. CineDub: Scaling End-to-End Video Dubbing to Multi-Speaker Dialogues with Coherent Sound Effects

   Yusheng Dai, Kangdi Wang, Baolong Gao, Yuxuan Jiang, Weiqiang Wang, Qiuhong Ke, and Jianfei Cai

   ACMMM 2026| ACM International Conference on Multimedia
3. Co-Steer: Cross-Modal Collaborative Steering for Jailbreaking MLLMs

   Jingmin Zhu, Rollin Omari, Junae Kim Abraham, Amardeep Kaur, Trung Le, Dinh Phung, and Qiuhong Ke

   ECCV 2026| European Conference on Computer Vision
4. SkelHCC: A Hyperbolic CLIP-Driven Cache Adaptation Framework for Skeleton-based One-Shot Action Recognition

   Yanan Liu, Anqi Zhu, Jingmin Zhu, Jun Liu, Hossein Rahmani, Mohammed Bennamoun, Farid Boussaid, Dan Xu, and Qiuhong Ke

   ICML 2026| International Conference on Machine Learning

   PDF Code
5. DynaPURLS: Dynamic Refinement of Part-aware Representations for Skeleton-based Zero-Shot Action Recognition

   Jingmin Zhu, Anqi Zhu, James Bailey, Jun Liu, Hossein Rahmani, Mohammed Bennamoun, Farid Boussaid, and Qiuhong Ke

   TPAMI 2026| IEEE Transactions on Pattern Analysis and Machine Intelligence

   PDF Code
6. Multi-stage Metric Learning with CLIP-based Adaptation for Few-shot Action Recognition

   Shuo Zheng, Yuanjie Dang, Peng Chen, Ruohong Huan, Dongdong Zhao, Ronghua Liang, and Qiuhong Ke

   TMM 2026| IEEE Transactions on Multimedia
7. Boot-and-Feedback Framework for Generalist-Expert Model Collaboration in Breast Ultrasound Diagnosis

   Ming Cheng, Hongyu Sun, Zhaolin Chen, Jun Liu, Hossein Rahmani, and Qiuhong Ke

   ICASSP (oral) 2026| IEEE International Conference on Acoustics, Speech and Signal Processing
8. Omni2Sound: A Fundamental Study on Dataset, Base Model, and Benchmark for Unified Video-Text-to-Audio Generation

   Yusheng Dai, Zehua Chen, Yuxuan Jiang, Qiuhong Ke, Jianfei Cai, and Jun Zhu

   CVPR 2026| Conference on Computer Vision and Pattern Recognition
9. Translating Signals to Languages for sEMG-Based Activity Recognition

   Ming Wang, Haoxuan Qu, Qiuhong Ke, Wei Zhou, Hossein Rahmani, and Jun Liu

   CVPR 2026| Conference on Computer Vision and Pattern Recognition
10. Fresco: Frequency–Spatial Consistent Optimization for Fine-Grained Head Avatar Modeling

    Shikun Zhang, Yong Li, Yiqun Wang, Qiuhong Ke, and Cunjian Chen

    CVPR (highlight) 2026| Conference on Computer Vision and Pattern Recognition
11. Sports-qa: A large-scale video question answering benchmark for complex and professional sports

    Haopeng Li, Andong Deng, Jun Liu, Hossein Rahmani, Yulan Guo, Bernt Schiele, Chen Chen, and Qiuhong Ke

    IJCV 2026| International Journal of Computer Vision

    PDF Code

2025

1. Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation

   Jingmin Zhu, Anqi Zhu, Hossein Rahmani, Jun Liu, Mohammed Bennamoun, and Qiuhong Ke

   NeurIPS 2025| Advances in Neural Information Processing Systems

   PDF Code
2. Semantic-guided Cross-Modal Prompt Learning for Skeleton-based Zero-shot Action Recognition

   Anqi Zhu, Jingmin Zhu, James Bailey, Mingming Gong, and Qiuhong Ke

   CVPR 2025| Proceedings of the Computer Vision and Pattern Recognition Conference

   PDF
3. Watch and Listen: Understanding Audio-Visual-Speech Moments with Multimodal LLM

   Zinuo Li, Xian Zhang, Yongxin Guo, Mohammed Bennamoun, Farid Boussaid, Girish Dwivedi, Luqi Gong, and Qiuhong Ke

   NeurIPS 2025| Advances in Neural Information Processing Systems

   PDF Code
4. Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis

   Hongyu Sun, Qiuhong Ke, Ming Cheng, Yongcai Wang, Deying Li, Chenhui Gou, and Jianfei Cai

   CVPR 2025| Conference on Computer Vision and Pattern Recognition

   PDF Code
5. ST-GDance: Long-Term and Collision-Free Group Choreography from Music

   Jing Xu, Weiqiang Wang, Cunjian Chen, Jun Liu, and Qiuhong Ke

   BMVC (oral) 2025| British Machine Vision Conference

   Oral Presentation

   PDF Code

2024

1. Part-aware unified representation of language and skeleton for zero-shot action recognition

   Anqi Zhu, Qiuhong Ke, Mingming Gong, and James Bailey

   CVPR 2024| Conference on Computer Vision and Pattern Recognition

   PDF Code
2. Point-PRC: A prompt learning based regulation framework for generalizable point cloud analysis

   Hongyu Sun, Qiuhong Ke, Yongcai Wang, Wang Chen, Kang Yang, Deying Li, and Jianfei Cai

   NeurIPS 2024| Advances in Neural Information Processing Systems

   PDF Code

2023

1. Progressive video summarization via multimodal self-supervised learning

   Haopeng Li, Qiuhong Ke, Mingming Gong, and Tom Drummond

   WACV 2023| IEEE/CVF Winter Conference on Applications of Ccomputer Vision

   PDF Code

2022

1. Human action recognition from various data modalities: A review

   Zehua Sun, Qiuhong Ke, Hossein Rahmani, Mohammed Bennamoun, Gang Wang, and Jun Liu

   TPAMI 2022| IEEE Transactions on Pattern Analysis and Machine Intelligence

   PDF
2. Video joint modelling based on hierarchical transformer for co-summarization

   Haopeng Li, Qiuhong Ke, Mingming Gong, and Rui Zhang

   TPAMI 2022| IEEE Transactions on Pattern Analysis and Machine Intelligence

   PDF Code