Hongxiang Li is a final year master’s student at Peking University, supervised by Yuexian Zou.
My research interests include Visual Generation and Video Understanding.
If interested in collaboration or discussion, please email me.
🔥 News
- 2025.02: One paper is accepted to IEEE TCSVT.
- 2025.01: One paper is accepted to ICLR 2025.
- 2024.12: One paper is accepted to IEEE TMI.
- 2024.08: Two papers are accepted to ECCV 2024.
- 2024.07: One paper is accepted to ACM MM 2024.
- 2023.12: One paper is accepted to AAAI 2024.
- 2023.07: Two papers are accepted to ICCV 2023. G2L is accepted as oral.
📝 Selected Publications
See full list at Google Scholar.
DisPose: Disentangling Pose Guidance for Controllable Human Image Animation
Hongxiang Li, Yaowei Li, Yuhang Yang, Junjie Cao, Zhihong Zhu, Xuxin Cheng, Long Chen#
International Conference on Learning Representations (ICLR), 2025
Exploiting Auxiliary Caption for Video Grounding
Hongxiang Li, Meng Cao, Xuxin Cheng, Yaowei Li, Zhihong Zhu, Yuexian Zou#
AAAI Conference on Artificial Intelligence (AAAI), 2024
G2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game Theory
Hongxiang Li, Meng Cao, Xuxin Cheng, Yaowei Li, Zhihong Zhu, Yuexian Zou#
International Conference on Computer Vision (ICCV), 2023 (Oral)
💻 Internships
- 2023 - 2024 Baidu VIS, Shenzhen, China.
- 2023 - 2023 Tencent YouTu Lab, Shanghai, China.
- 2021 - 2022 SenseTime Research, Chengdu, China.
🎖 Honors and Awards
- 2023 Merit Student Pacesetter, Peking University.
- 2021 National Scholarship.