arXiv - CSCL: "Text-Derived Knowledge Helps Vision: A Simple Cro…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

Text-Derived Knowledge Helps Vision: A Simple Cross-modal Distillation for Video-based Action Anticipation. (arXiv:2210.05991v2 [cs.CV] UPDATED)

http://arxiv.org/abs/2210.05991 #arXiv #NLProc

Feb 22, 2023, 03:09 · · arxiv-cscl · · ·

Sign in to participate in the conversation