Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention

Multi-label zero-shot learning extends conventional single-label zero-shot learning to a more realistic scenario that aims at recognizing multiple unseen labels of classes for each input sample. Existing works usually exploit attention mechanism to generate the correlation among different labels. Ho...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on multimedia 2023-01, Vol.25, p.1-15
Hauptverfasser:	Liu, Ziming, Guo, Song, Guo, Jingcai, Xu, Yuanyuan, Huo, Fushuo
Format:	Artikel
Sprache:	eng
Schlagworte:	Attention Mechanism Classification Computational modeling Correlation Feature extraction Image recognition Labels Multi-label Zero-shot learning Pattern Recognition Representations Semantic Feature Space Semantics Task analysis Training Zero-shot learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!