DistInit - Learning Video Representations Without a Single Labeled Video

ICCV, pp. 852-861, 2019.

Cited by: 7|Bibtex|Views100|Links
EI

Abstract:

Video recognition models have progressed significantly over the past few years, evolving from shallow classifiers trained on hand-crafted features to deep spatiotemporal networks. However, labeled video data required to train such models has not been able to keep up with the ever increasing depth and sophistication of these networks. In...More

Code:

Data:

Your rating :
0

 

Tags
Comments