Capturing Temporal Structures for Video Captioning by Spatio-temporal Contexts and Channel Attention Mechanism

To generate a natural language description for videos, there has been tremendous interest in developing deep neural networks with the integration of temporal structures in different categories. Considering the spatial and temporal domains inherent in video frames, we contend that the video dynamics...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural processing letters 2017-08, Vol.46 (1), p.313-328
Hauptverfasser:	Guo, Dashan, Li, Wei, Fang, Xiangzhong
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial Intelligence Artificial neural networks Back propagation Classification Complex Systems Computational Intelligence Computer Science Convolution Deep learning Dynamic structural analysis Feature maps Investigations Neural networks Semantics
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!