Distill and Collect for Semi-Supervised Temporal Action Segmentation

Recent temporal action segmentation approaches need frame annotations during training to be effective. These annotations are very expensive and time-consuming to obtain. This limits their performances when only limited annotated data is available. In contrast, we can easily collect a large corpus of...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Biswas, Sovan, Rhodes, Anthony, Manuvinakurike, Ramesh, Raffa, Giuseppe, Beckwith, Richard
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!