26 citations · 70 across the 12 of their papers we have counts for
4 papers · 1 filter
Long-term Leap Attention, Short-term Periodic Shift for Video Classification
Hao Zhang, Lechao Cheng, Yanbin Hao +1
Video transformer naturally incurs a heavier computation burden than a static vision transformer, as the former processes times longer sequence than the latter under the curren…
Parameterization of Cross-Token Relations with Relative Positional Encoding for Vision MLP
Zhicai Wang, Yanbin Hao, Xingyu Gao +4
Vision multi-layer perceptrons (MLPs) have shown promising performance in computer vision tasks, and become the main competitor of CNNs and vision Transformers. They use token-mixi…
Attention in Attention: Modeling Context Correlation for Efficient Video Classification
Yanbin Hao, Shuo Wang, Pei Cao +4
Attention mechanisms have significantly boosted the performance of video classification neural networks thanks to the utilization of perspective contexts. However, the current rese…
Group Contextualization for Video Recognition
Yanbin Hao, Hao Zhang, Chong-Wah Ngo +1
Learning discriminative representation from the complex spatio-temporal dynamic space is essential for video recognition. On top of those stylized spatio-temporal computational uni…