M-VAD names: a dataset for video captioning with naming
Sign Up to like & getrecommendations! Published in 2018 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-018-7040-z
Abstract: Current movie captioning architectures are not capable of mentioning characters with their proper name, replacing them with a generic “someone” tag. The lack of movie description datasets with characters’ visual annotations surely plays a relevant… read more here.
Keywords: video captioning; names dataset; captioning naming; vad names ... See more keywords