[Paper-Reading] CVPR2019-Action Recognition from Single Timestamp Supervision in Untrimmed Videos

Background

1. Marking every start and end times of every actions instance is very expensive and hard to acquire, but action recognition needs more and more large datasets to improve the performance.
2. Weak video-level supervision has been successfully exploited for recognition in untrimmed videos, however it's challenged when the number of different action instances in videos increases.

original version