DistInit - Learning Video Representations Without a Single Labeled Video
ICCV, pp. 852-861, 2019.
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
PPT (Upload PPT)