Poster · Sydney
OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning
- When
- Wed 9 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 3
- Authors
- Zhongyu Yang, Jiale Tao, Ruitao Chen, Zuhao Yang, Yingfang Yuan, Xueliang Zhao, Auden, Kai Wang, Shuai Shao, Biao Wang, Steve Yves, Qinglin Lu
- Organisations
- University of Electronic Science and Technology of China, Southern University of Science and Technology, Nanyang Technological University, Northumbria University, University of Hong Kong, Tencent, National University of Singapore
- QRS classification
- Language models, Computer vision, Speech and audio