Correlation Net: Spatiotemporal multimodal deep learning for action recognition

This paper describes a network that captures multimodal correlations over arbitrary timestamps. The proposed scheme operates as a complementary, extended network over a multimodal convolutional neural network (CNN). Spatial and temporal streams are required for action recognition by a deep CNN, but...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Signal processing. Image communication 2020-03, Vol.82, p.115731, Article 115731
Hauptverfasser:	Yudistira, Novanto, Kurita, Takio
Format:	Artikel
Sprache:	eng
Schlagworte:	Activity recognition Artificial neural networks CNN Correlation Correlation Net Deep learning Fusion Recognition Streams
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!