research
∙
11/29/2022
Lightweight Structure-Aware Attention for Visual Understanding
Vision Transformers (ViTs) have become a dominant paradigm for visual re...
share
research
∙
11/02/2021
Relational Self-Attention: What's Missing in Attention for Video Understanding
Convolution has been arguably the most important feature transform for m...
research
∙
08/22/2021
Relational Embedding for Few-Shot Classification
We propose to address the problem of few-shot classification by meta-lea...
research
∙
02/14/2021
Learning Self-Similarity in Space and Time as Generalized Motion for Action Recognition
Spatio-temporal convolution often fails to learn motion dynamics in vide...
research
∙
07/20/2020
MotionSqueeze: Neural Motion Feature Learning for Video Understanding
Motion plays a crucial role in understanding videos and most state-of-th...
research
∙
07/13/2020