Deep Insights into Convolutional Networks for Video Recognition

As the success of deep models has led to their deployment in all areas of computer vision, it is increasingly important to understand how these representations work and what they are capturing. In this paper, we shed light on deep spatiotemporal representations by visualizing the internal representa...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	International journal of computer vision 2020-02, Vol.128 (2), p.420-437
Hauptverfasser:	Feichtenhofer, Christoph, Pinz, Axel, Wildes, Richard P., Zisserman, Andrew
Format:	Artikel
Sprache:	eng
Schlagworte:	Analysis Artificial Intelligence Computer Imaging Computer Science Computer vision Human motion Image Processing and Computer Vision Machine vision Object motion Object recognition Pattern Recognition Pattern Recognition and Graphics Representations Vision
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!