AI RESEARCH
Selective Contrastive Learning For Gloss Free Sign Language Translation
arXiv CS.CL
•
ArXi:2604.22374v1 Announce Type: new 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 pre