Temporal Action Detection with Multi-level Supervision

Cited by: 0|Bibtex|Views20
Other Links: arxiv.org

Abstract:

Training temporal action detection in videos requires large amounts of labeled data, yet such annotation is expensive to collect. Incorporating unlabeled or weakly-labeled data to train action detection model could help reduce annotation cost. In this work, we first introduce the Semi-supervised Action Detection (SSAD) task with a mixtu...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments