Partial annotation-based video moment retrieval via iterative learning

• Main Authors: JI, Wei, LIANG, Renjie, LIAO, Lizi, FEI, Hao, FENG, Fuli
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2023
• 主題: Current; Coarse guidance; Iterative learning; Labour-intensive; Performance; Pseudo label; Query video; Retrieval methods; Time-stamp; Video moment retrieval; Databases and Information Systems
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/8585; https://ink.library.smu.edu.sg/context/sis_research/article/9588/viewcontent/Partial_Annotation_based_Video_Moment_Retrieval_via_Iterative_Learning.pdf

Given a descriptive language query, Video Moment Retrieval (VMR) aims to seek the corresponding semantic-consistent moment clip in the video, which is represented as a pair of the start and end timestamps. Although current methods have achieved satisfying performance, training these models heavily r...