FEA-SLT: A Gloss-Free End-to-End Framework for Facial-Expression-Aware Sign Language Translation
EA-SLT is proposed, a gloss-free end-to-end framework that uses facial dynamics to provide complementary cues to manual signals and achieves state-of-the-art BLEU performance among gloss-free methods, while targeted analyses support improved translation of facial-sensitive utterances.
Guobin Tu, Dietmar Weng
· 0 citations