AI RESEARCH
CanonSLR: Canonical-View Guided Multi-View Continuous Sign Language Recognition
arXiv CS.CV
•
ArXi:2604.18184v1 Announce Type: new Continuous Sign Language Recognition (CSLR) has achieved remarkable progress in recent years; however, most existing methods are developed under single-view settings and thus remain insufficiently robust to viewpoint variations in real-world scenarios. To address this limitation, we propose CanonSLR, a canonical-view guided framework for multi-view CSLR. Specifically, we