Low-Rank Transfer Human Motion Segmentation

Human motion segmentation has a great potential in real-world applications. Conventional segmentation approaches cluster data with no guidance from prior knowledge, which could easily cause unpredictable segmentation output and decrease the performance. To this end, we seek to improve the human-moti...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on image processing 2019-02, Vol.28 (2), p.1023-1034
Hauptverfasser:	Wang, Lichen, Ding, Zhengming, Fu, Yun
Format:	Artikel
Sprache:	eng
Schlagworte:	Clustering Clustering methods Computer vision Constraint modelling Data models Data structures Dictionaries Divergence Graphical representations Human motion Human motion segmentation Human performance Knowledge management low-rank learning Motion segmentation Motion stability Performance enhancement Segmentation State of the art Subspace methods Task analysis temporal data clustering
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!