2 papers
cs.CV2026
SMART: MLLM-guided Temporal Alignment for Unifying Sign Language Recognition and Spotting
Eunjee Choi, JungHoon Sung, Seongwhan Cho +2
Continuous sign language recognition (CSLR) aims to recognize gloss sequences from unsegmented sign videos under weak sequence-level supervision. However, existing methods rely on…
cs.CV2026
Context-Aware Autoregressive Diffusion for Gloss-Wise Sign Language Production
JungHoon Sung, Boeun Kim, Chu Xin +4
To generate natural and accurate sentence-level sign language, synthesizing the "gloss", the fundamental semantic unit, is essential. However, most current sign-language production…