Natural Language Video Localization : A Revisit in Span-Based Question Answering Framework

Natural Language Video Localization (NLVL) aims to locate a target moment from an untrimmed video that semantically corresponds to a text query. Existing approaches mainly solve the NLVL problem from the perspective of computer vision by formulating it as ranking, anchor, or regression tasks. These...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 8 vom: 23. Aug., Seite 4252-4266
1. Verfasser: Zhang, Hao (VerfasserIn)
Weitere Verfasser: Sun, Aixin, Jing, Wei, Zhen, Liangli, Zhou, Joey Tianyi, Goh, Rick Siow Mong
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article