3 citations · 6 across the 2 of their papers we have counts for
2 papers
cs.CV2019★ 3 cited
Deformable Tube Network for Action Detection in Videos
Wei Li, Zehuan Yuan, Dashan Guo +3
We address the problem of spatio-temporal action detection in videos. Existing methods commonly either ignore temporal context in action recognition and localization, or lack the m…
cs.CV2018★ 3 cited
Knowing Where to Look? Analysis on Attention of Visual Question Answering System
Wei Li, Zehuan Yuan, Xiangzhong Fang +1
Attention mechanisms have been widely used in Visual Question Answering (VQA) solutions due to their capacity to model deep cross-domain interactions. Analyzing attention maps offe…