Bias Mitigation and Representation Optimization for Noise-Robust Cross-modal Retrieval

The remarkable progress in cross-modal retrieval relies on accurately-annotated multimedia datasets. In practice, most existing datasets used for training cross-modal retrieval models are automatically collected from the Internet to reduce data collection costs. However, it inevitably contains misma...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	ACM transactions on multimedia computing communications and applications 2024-10
Hauptverfasser:	Liu, Yu, Chen, Haipeng, Qin, Guihe, Song, Jincai, Yang, Xun
Format:	Artikel
Sprache:	eng
Schlagworte:	Information retrieval Information systems Retrieval models and ranking Similarity measures
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!