Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Labson, Linzy"'
Autor:
Rodriguez, Pedro, Azab, Mahmoud, Silvert, Becka, Sanchez, Renato, Labson, Linzy, Shah, Hardik, Moon, Seungwhan
Searching troves of videos with textual descriptions is a core multimodal retrieval task. Owing to the lack of a purpose-built dataset for text-to-video retrieval, video captioning datasets have been re-purposed to evaluate models by (1) treating cap
Externí odkaz:
http://arxiv.org/abs/2210.05038
