arXiv - CSCL: "MAMO: Masked Multimodal Modeling for Fine-Grained…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

MAMO: Masked Multimodal Modeling for Fine-Grained Vision-Language Representation Learning. (arXiv:2210.04183v3 [cs.CV] UPDATED)

http://arxiv.org/abs/2210.04183 #arXiv #NLProc

Jun 18, 2023, 03:22 · · arxiv-cscl · · ·

Sign in to participate in the conversation