A Better Way to Attend: Attention With Trees for Video Question Answering

We propose a new attention model for video question answering. The main idea of the attention models is to locate on the most informative parts of the visual data. The attention mechanisms are quite popular these days. However, most existing visual attention mechanisms regard the question as a whole...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on image processing 2018-11, Vol.27 (11), p.5563-5574
Hauptverfasser:	Xue, Hongyang, Chu, Wenqing, Zhao, Zhou, Cai, Deng
Format:	Artikel
Sprache:	eng
Schlagworte:	attention model Computational modeling Knowledge discovery Natural languages scene understanding Semantics Sentences Syntactics Task analysis Trees Video question answering Visualization
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!