一作ACL 2026Poster· Natural Language Processing
Selective Contrastive Learning For Gloss Free Sign Language Translation
Chang Hao Lai · Rui Zhao · Xuewen Zhong · Jinsong Su · Yidong Chen
摘要
Sign language translation (SLT) converts continuous sign videos into spoken-language text, yet it remains challenging due to the intrinsic modality mismatch between visual signs and written text, particularly in gloss-free settings. Recent SLT systems increasingly adopt CLIP-like Vision-Language...