Weakly-Supervised Temporal Action Localization via Video—Text Semantic Alignment and Full Video Dependency

In response to the challenges in existing Weakly-supervised Temporal Action Localization (WTAL) research, such as the underutilization of action temporal characteristics, global properties, and action semantic consistency, a method called Weakly-Supervised Action Localization via Video—Text Semantic...

Popoln opis

Bibliografske podrobnosti

Glavni avtor:	DANG Weichao, PEI Lixian, GAO Gaimei, LIU Chunxia
Format:	Artigo
Jezik:	Inglês
Izdano:	Editorial Office of Computer Engineering 2026-07-01
Serija:	Jisuanji gongcheng
Teme:	weakly-supervised temporal action localization (wtal)|video—text semantic alignment|full video dependency|pseudo-label generation|multimodal fusion
Online dostop:	https://www.ecice06.com/fileup/1000-3428/PDF/20260729.pdf
Oznake:	Označite Brez oznak, prvi označite!