RubiksNet: Learnable 3D Shift for Efficient Video Action Recognition

Linxi Fan
Linxi Fan
Shyamal Buch
Shyamal Buch
Guanzhi Wang
Guanzhi Wang
Ryan Cao
Ryan Cao
Juan Carlos Niebles
Juan Carlos Niebles
Li Fei-Fei
Li Fei-Fei

Proceedings of the European Conference on Computer Vision (ECCV), 2020.

Cited by: 1|Bibtex|Views7

Abstract:

Video action recognition is a complex task dependent on modeling spatial and temporal context. Standard approaches rely on 2D or 3D convolutions to process such context, resulting in expensive operations with millions of parameters. Recent efficient architectures leverage a channel-wise shift-based primitive as a replacement for temporal ...More

Code:

Data:

Your rating :
0

 

Tags
Comments