Hi! I am Tiantian, a PhD candidate in computer science at University of Birmingham (2022-2026), supervised by Prof. Jinming Duan and Prof. Feng Zheng (SUSTech). Before that, I received my Bachelor’s degree and Master’s degree from University of Electronic Science and Technology of China (UESTC) in 2019 and 2022.

My research interests are focused on computer vision, multi-modal learning, video understanding. I am also interested in multi-modal large models and embodied AI.

News

• 2025.11: 🎉 One paper has been accepted to AAAI 2026.
• 2025.07: 🎉 One paper has been accepted to TPAMI 2025.
• 2025.02: 🎉 One paper has been accepted to CVPR 2025.
• 2025.01: 🎉 One paper has been accepted to ICLR 2025 Spotlight.

Publications

• 

  UniAV: Unified Audio-Visual Perception for Multi-Task Video Event Localization

  Tiantian Wang, ...

  TPAMI 2025 [Paper] [Project] [Code]

• 

  LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos

  Tiantian Geng, Jinrui Zhang, Qingni Wang, Teng Wang, Jinming Duan, Feng Zheng

  CVPR 2025 [Paper] [Project] [Code]

• 

  Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline

  Tiantian Wang, ...

  ICLR 2025 Spotlight [Paper] [Project] [Code]