Video Question Answering With Prior Knowledge and Object-Sensitive Learning

Video Question Answering (VideoQA), which explores spatial-temporal visual information of videos given a linguistic query, has received unprecedented attention over recent years. One of the main challenges lies in locating relevant visual and linguistic information, and therefore various attention-b...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 31(2022) vom: 09., Seite 5936-5948
1. Verfasser: Zeng, Pengpeng (VerfasserIn)
Weitere Verfasser: Zhang, Haonan, Gao, Lianli, Song, Jingkuan, Shen, Heng Tao
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article