Hongyu Qu (瞿宏谕)

PHD Candidate

School of Computer Science and Engineering
Nanjing University of Science and Technology

Email: quhongyu@njust.edu.cn
[Google Scholar] [Github]

Biography

I am currently a second-year PHD candidate at Visual Intelligence and Multimedia (VIM) and Intelligent Media Analysis Group (IMAG), School of Computer Science and Engineering, Nanjing University of Science and Technology. I am privileged to be advised by Prof. Xiangbo Shu, who serves as both an inspiring teacher and a profound role model in my life.

My research interests focus on Video Understanding (streaming and long-form video), Embodied AI (VLA), and Data-efficient Learning (few-shot/zero-shot learning). I also benefit greatly from the co-supervision of Prof. Shuicheng Yan (NUS) and Prof. Wenguan Wang (ZJU). Now I am spending a productive time as an intern at AntGroup InclusionAI. I’m open to exploring a wide range of topics with others. Please feel free to contact me via Email or WeChat.

News

Selected Publications [Full List] (^Co-first author; *Corresponding author)

 

Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition

Hongyu Qu, Xiangbo Shu*, Rui Yan, Hailiang Gao, Wenguan Wang, Jinhui Tang
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026.
[Paper]

 

Learning Clustering-based Prototypes for Compositional Zero-shot Learning

Hongyu Qu, Jianan Wei, Xiangbo Shu*, Wenguan Wang
International Conference on Learning Representations (ICLR), 2025.
[Paper]

 

OmniGaze: Reward-inspired Generalizable Gaze Estimation in the Wild

Hongyu Qu, Jianan Wei, Xiangbo Shu*, Yazhou Yao, Wenguan Wang*, Jinhui Tang
Annual Conference on Neural Information Processing Systems (NeurIPS), 2025.
[Paper]

 

MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition

Hongyu Qu, Rui Yan, Xiangbo Shu*, Hailiang Gao, Peng Huang, Guosen Xie
IEEE Transactions on Multimedia (TMM), 2025.
[Paper]

 

Condensed Test-Time Adaptation of VLMs for Action Recognition

Wenxuan Ge, Hongyu Qu^, Rui Yan, Guosen Xie, Yazhou Yao, Xiangbo Shu*, Jinhui Tang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
[Paper]

 

DTS-TPT: Dual Temporal-Sync Test-time Prompt Tuning for Zero-shot Activity Recognition

Rui Yan, Hongyu Qu^, Xiangbo Shu, Wenbin Li*, Jinhui Tang, Tieniu Tan
International Joint Conference on Artificial Intelligence (IJCAI), 2024.
[Paper]

 

CLEGAN: Toward Low-Light Image Enhancement for UAVs via Self-Similarity Exploitation

Ling Xing, Hongyu Qu^, Sheng Xu*, Yao Tian
IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2023.
[Paper]

 

Locality-aware cross-modal correspondence learning for dense audio-visual events localization

Ling Xing, Hongyu Qu, Rui Yan*, Xiangbo Shu, Jinhui Tang
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025.
[Paper]

 

TEST-V: TEst-time Support-set Tuning for Zero-shot Video Classification

Rui Yan, Jin Wang^, Hongyu Qu, Xiaoyu Du, Dong Zhang, Jinhui Tang, Tieniu Tan
International Joint Conference on Artificial Intelligence (IJCAI), 2025.
[Paper]

 

Reliable and Diverse Hierarchical Adapter for Zero-shot Video Classification

Wenxuan Ge, Peng Huang^, Rui Yan*, Hongyu Qu, Guosen Xie, Xiangbo Shu*
International Joint Conference on Artificial Intelligence (IJCAI), 2025.
[Paper]

 

Hierarchical Motion-Enhanced Matching Framework for Few-shot Action Recognition

Hailiang Gao, Guosen Xie, Rui Yan, Qiongjie Cui, Hongyu Qu, Xiangbo Shu*
IEEE Transactions on Multimedia (TMM), 2024.
[Paper]

Professional Services

Journal Reviewer:

  • International Journal of Computer Vision (IJCV)
  • IEEE Transactions on Information Forensics and Security (TIFS)
  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
  • IEEE Transactions on Multimedia (TMM)
  • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
  • IEEE Transactions on Consumer Electronics (TCE)
  • Knowledge-Based Systems (KBS)
  • Neurocomputing
  • The Visual Computer (TVCJ)
  • Pattern Recognition Letters (PRL)
  • Information Sciences

Conference Reviewer:

  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2026)
  • European Conference on Computer Vision (ECCV 2026)
  • International Conference on Machine Learning (ICML 2026)
  • Annual Conference on Neural Information Processing Systems (NeurIPS 2025)
  • International Conference on Learning Representations (ICLR 2025-2026)
  • AAAI Conference on Artificial Intelligence (AAAI 2026)
  • International Joint Conference on Artificial Intelligence (IJCAI 2025-2026)
  • ACM International Conference on Multimedia (ACM MM 2025-2026)