Scholar
Hao Zhou
Google Scholar ID: xZ-0R3cAAAAJ
Bytedance
Citations & Impact
Citations
1,078
H-index
9
i10-index
9
Publications
14
Co-authors
12
list available
Contact
Resume (English only)
Academic Achievements
- PruneVid: Visual Token Pruning for Efficient Video Large Language Models, ACL Findings 2025
- Change3D: Revisiting Change Detection and Captioning from A Video Modeling Perspective, CVPR 2025
- Skim then Focus: Integrating Contextual and Fine-grained Views for Repetitive Action Counting, IJCV 2025
- Semi-Supervised Spoken Language Glossification, ACL 2024
- StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond, arXiv preprint 2024
- FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition, ICLR 2024
- HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception, NeurIPS 2023
- Sign Language Translation with Iterative Prototype, ICCV 2023
- Graph Contrastive Learning for Skeleton-based Action Recognition, ICLR 2023
- Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition and Translation, IEEE Transactions on Multimedia 2021
- Improving Sign Language Translation with Monolingual Data by Sign Back-Translation, CVPR 2021
- Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition, AAAI 2020
- Dynamic Pseudo Label Decoding for Continuous Sign Language Recognition, ICME 2019
Research Experience
- Researcher at Bytedance, working on generative AI in the ads tech and creative industry.
Education
- Ph.D. from University of Science and Technology of China (USTC) in 2022, supervised by Prof. Wengang Zhou and Prof. Houqiang Li; B.S. from Xidian University (XDU) in 2017.
Background
- Currently a researcher at Bytedance, focusing on developing generative AI in the ads tech and creative industry. Research interests include computer vision, particularly video understanding, generation, and editing.
Miscellany
- Invited reviewer for several journals and conferences, including IEEE TPAMI, TCSVT, TMM, etc.
