Search Results for author:
Found 7 papers, 6 papers with code
Lightweight Structure-Aware Attention for Visual Understanding
Vision Transformers (ViTs) have become a dominant paradigm for visual representation learning with self-attention operators.
Relational Self-Attention: What's Missing in Attention for Video Understanding
Convolution has been arguably the most important feature transform for modern neural networks, leading to the advance of deep learning.
Ranked #11 on
Action Recognition
on Diving-48
Relational Embedding for Few-Shot Classification
We propose to address the problem of few-shot classification by meta-learning "what to observe" and "where to attend" in a relational perspective.
Ranked #15 on
Few-Shot Image Classification
on CUB 200 5-way 5-shot
Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition
With a sufficient volume of the neighborhood in space and time, it effectively captures long-term interaction and fast motion in the video, leading to robust action recognition.
Ranked #18 on
Action Recognition
on Something-Something V1
(using extra training data)
Learning Self-Similarity in Space and Time as a Generalized Motion for Action Recognition
We leverage the whole volume of STSS and let our model learn to extract an effective motion representation from it.
MotionSqueeze: Neural Motion Feature Learning for Video Understanding
As the frame-by-frame optical flows require heavy computation, incorporating motion information has remained a major computational bottleneck for video understanding.
Ranked #1 on
Video Classification
on Something-Something V2
IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos
Most current action recognition methods heavily rely on appearance information by taking an RGB sequence of entire image regions as input.
