Parameter-efficient weakly supervised referring video object segmentation via chain-of-thought reasoning

Abstract Referring video object segmentation (RVOS) aims to segment the object corresponding to a language expression in a video. Most existing RVOS methods are trained using accurate per-pixel annotations, which are expensive and time-consuming to obtain. Moreover, they need to update the entire pa...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Xing Wang, Zhe Xu, Yuanshi Zheng, Handing Wang
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	Springer 2025-05-01
Schriftenreihe:	Complex & Intelligent Systems
Schlagworte:	Referring video object segmentation Weakly supervised learning Chain-of-thought reasoning
Online-Zugang:	https://doi.org/10.1007/s40747-025-01900-1
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!