Less is More: Learning Highlight Detection from Video Duration

CVPR, 2019.

Cited by: 6|Bibtex|Views98
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Highlight detection has the potential to significantly ease video browsing, but existing methods often suffer from expensive supervision requirements, where human viewers must manually identify highlights in training videos. We propose a scalable unsupervised solution that exploits video duration as an implicit supervision signal. Our key...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments