arXiv - CSCL: "From Association to Generation: Text-only Caption…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping. (arXiv:2304.13273v3 [cs.CV] UPDATED)

http://arxiv.org/abs/2304.13273 #arXiv #NLProc

May 09, 2023, 03:06 · · arxiv-cscl · · ·

Sign in to participate in the conversation