Multimodal Contextualized Support for Enhancing Video Retrieval System

Current video retrieval systems, especially those used in competitions, primarily focus on querying individual keyframes or images rather than encoding an entire clip or video segment. However, queries often describe an action or event over a series of frames, not a specific image. This results in i...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Nguyen-Le, Quoc-Bao, Le-Nguyen, Thanh-Huy
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!