4

Temporally-Adaptive Models for Efficient Video Understanding

TAdaFormer and TAdaConvNeXtV2, enabling state-of-the-art video understanding capabilities

Ziyuan Huang, Shiwei Zhang, Liang Pan, Zhiwu Qing, Yingya Zhang, Ziwei Liu, Marcelo H Ang Jr

Temporally-Adaptive Models for Efficient Video Understanding

A Stronger Baseline for Ego-Centric Action Detection

Rank 1 submission in the EPIC-Kitchens Action Detection Challenge. Codes are released.

Zhiwu Qing, Ziyuan Huang, Xiang Wang, Yutong Feng, Shiwei Zhang, Jianwen Jiang, Mingqian Tang, Changxin Gao, Marcelo H. Ang Jr, Nong Sang

A Stronger Baseline for Ego-Centric Action Detection

Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition

Rank 2 submission in the EPIC-Kitchens Action Recognition Challenge. Codes are released.

Ziyuan Huang, Zhiwu Qing, Xiang Wang, Yutong Feng, Shiwei Zhang, Jianwen Jiang, Zhurong Xia, Mingqian Tang, Nong Sang, Marcelo H. Ang Jr

Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition