Deep Feature Flow for Video Recognition

CVPR, 2017.

Cited by: 186|Bibtex|Views92
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Deep convolutional neutral networks have achieved great success on image recognition tasks. Yet, it is non-trivial to transfer the state-of-the-art image recognition networks to videos as per-frame evaluation is too slow and unaffordable. We present deep feature flow, a fast and accurate framework for video recognition. It runs the expens...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments