Developing a Sign Dictionary using Continuous Turkish Sign Data via Sign Spotting Sürekli Türk ?I şaret Dili Verisinden ?Işaret Yakalama Yoluyla ?I şaret Sözlü?gü Geliştirme


Kuden B., Sahin S. N., Ozel O. C., AKARUN ERSOY L., SARAÇLAR M.

34th Signal Processing and Communications Applications Conference, SIU 2026, İstanbul, Türkiye, 7 - 10 Temmuz 2026, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/siu71813.2026.11637013
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Anahtar Kelimeler: bootstrapping, continuous sign language recognition, sign spotting, Turkish Sign Language
  • Boğaziçi Üniversitesi Adresli: Evet

Özet

Sign language recognition and translation require large-scale signed data. In this study, I3D, DINO, and SHu-BERT architectures were used to automatically capture signs corresponding to target words in subtitles on the BUTID dataset compiled from television programs interpreted in Turkish Sign Language (TİD) and their capture performances were analyzed comparatively. It was shown that the system's performance was increased with an bootstrapping procedure supported by human validation.