Metric learning for graph based semi-supervised human pose estimation

Discriminative approaches to human pose estimation have became popular in recent years. These approaches face a big challenge: Similar inputs might correspond to very dissimilar poses. This property misleads the mapping functions which rely on the Euclidean distances in the input space. In this pape...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Pourdamghani, N., Rabiee, H. R., Zolfaghari, M.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Estimation Humans Labeling Manifolds Measurement Pattern recognition Training data
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!