InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution

Over recent decades, significant advancements in cross-modal retrieval are mainly driven by breakthroughs in visual and linguistic modeling. However, a recent study shows that multi-modal data representations tend to cluster within a limited convex cone (as representation degeneration problem), whic...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Jian, Xiangru, Wang, Yimu
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning Computer Science - Multimedia
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!