arXiv - CSCL: "A Video is Worth 10,000 Words: Training and Bench…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

A Video is Worth 10,000 Words: Training and Benchmarking with Diverse Captions for Better Long Video Retrieval. (arXiv:2312.00115v1 [cs.CV])

http://arxiv.org/abs/2312.00115 #arXiv #NLProc

Dec 04, 2023, 03:19 · · arxiv-cscl · · ·

Sign in to participate in the conversation