A Novel Perspective to Zero-Shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansion

Zero-shot learning aims at recognizing unseen classes (no training example) with knowledge transferred from seen classes. This is typically achieved by exploiting a semantic feature space shared by both seen and unseen classes, i.e., attribute or word vector, as the bridge. One common practice in ze...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on multimedia 2021, Vol.23, p.524-537
Hauptverfasser:	Guo, Jingcai, Guo, Song
Format:	Artikel
Sprache:	eng
Schlagworte:	Alignment autoencoder Domains Feature extraction manifold Manifolds Projection Prototypes semantic feature Semantics Task analysis Testing Training Visualization Zero-shot learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!