1 code implementation • 21 Mar 2020 • Joshua Knights, Ben Harwood, Daniel Ward, Anthony Vanderkop, Olivia Mackenzie-Ross, Peyman Moghadam
The proposed method exploits inherent structure of unlabeled video data to explicitly enforce temporal coherency in the embedding space, rather than indirectly learning it through ranking or predictive proxy tasks.
Ranked #37 on Self-Supervised Action Recognition on UCF101