arXiv - CSCL: "Scalable and Accurate Self-supervised Multimodal …" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data. (arXiv:2304.02080v1 [cs.CV])

http://arxiv.org/abs/2304.02080 #arXiv #NLProc

Apr 06, 2023, 03:08 · · arxiv-cscl · · ·

Sign in to participate in the conversation