Label Independent Memory for Semi-Supervised Few-Shot Video Classification

In this paper, we propose to leverage freely available unlabeled video data to facilitate few-shot video classification. In this semi-supervised few-shot video classification task, millions of unlabeled data are available for each episode during training. These videos can be extremely imbalanced, wh...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2022-01, Vol.44 (1), p.273-285
Hauptverfasser:	Zhu, Linchao, Yang, Yi
Format:	Artikel
Sprache:	eng
Schlagworte:	Classification compound memory networks Compounds Data models Dynamics Feature extraction Few-shot video classification memory-augmented neural networks Prototypes semi-supervised learning Task analysis Training Video data
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!