Representation Learning on Visual-Symbolic Graphs for Video Understanding

Events in natural videos typically arise from spatio-temporal interactions between actors and objects and involve multiple co-occurring activities and object classes. To capture this rich visual and semantic context, we propose using two graphs: (1) an attributed spatio-temporal visual graph whose n...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-09
Hauptverfasser:	Mavroudi, Effrosyni, Benjamín Béjar Haro, Vidal, René
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptive filters Classification Computer vision Conditioning Edge joints Graph theory Graphical representations Labels Machine learning Message passing Modules Nodes Segmentation Semantics
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!