VPN++ : Rethinking Video-Pose Embeddings for Understanding Activities of Daily Living

Many attempts have been made towards combining RGB and 3D poses for the recognition of Activities of Daily Living (ADL). ADL may look very similar and often necessitate to model fine-grained details to distinguish them. Because the recent 3D ConvNets are too rigid to capture the subtle visual patter...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 12 vom: 01. Dez., Seite 9703-9717
1. Verfasser:	Das, Srijan (VerfasserIn)
Weitere Verfasser:	Dai, Rui, Yang, Di, Bremond, Francois
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2022
Zugriff auf das übergeordnete Werk:	IEEE transactions on pattern analysis and machine intelligence
Schlagworte:	Journal Article Research Support, Non-U.S. Gov't