Ju Liang — accepted AI-conference papers

2021

Multi-Modal Multi-Action Video Recognition

Zhensheng Shi, Ju Liang, Qianqian Li, Haiyong Zheng, Zhaorui Gu, Junyu Dong +1

ICCV 2021poster

Multi-action video recognition is much more challenging due to the requirement to recognize multiple actions co-occurring simultaneously or sequentially. Modeling multi-action relations is beneficial and crucial to understand videos with multiple actions, and actions in a video are usually presented…

Cited by 12 PDF ↗code ↗Scholar ↗

2020

CoTeRe-Net: Discovering Collaborative Ternary Relations in Videos

Zhensheng Shi, Cheng Guan, Liangjie Cao, Qianqian Li, Ju Liang, Zhaorui Gu +2

ECCV 2020poster

Modeling relations is crucial to understand videos for action and behavior recognition. Current relation models mainly reason about relations of invisibly implicit cues, while important relations of visually explicit cues are rarely considered, and the collaboration between them is usually ignored.…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗