Hands in Focus: Sign Language Recognition Via Top-Down Attention

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet


  • Noha Sarhan
  • Christian Wilms
  • Vanessa Closius
  • Ulf Brefeld
  • Simone Frintrop

In this paper, we propose a novel Sign Language Recognition (SLR) model that leverages the task-specific knowledge to incorporate Top-Down (TD) attention to focus the processing of the network on the most relevant parts of the input video sequence. For SLR, this includes information about the hands' shape, orientation and positions, and motion trajectory. Our model consists of three streams that process RGB, optical flow and TD attention data. For the TD attention, we generate pixel-precise attention maps focusing on both hands, thereby retaining valuable hand information, while eliminating distracting background information. Our proposed method outperforms state-of-the-art on a challenging large-scale dataset by over 2%, and achieves strong results with a much simpler architecture compared to other systems on the newly released AUTSL dataset [1].

Titel2023 IEEE International Conference on Image Processing, ICIP 2023 - Proceedings : Proceedings
Anzahl der Seiten5
VerlagIEEE Electromagnetic Compatibility Society
ISBN (Print)978-1-7281-9836-1
ISBN (elektronisch)978-1-7281-9835-4
PublikationsstatusErschienen - 08.10.2023
Veranstaltung2023 IEEE International Conference on Image Processing - Kuala Lumpur Convention Centre, Kuala Lumpur, Malaysia
Dauer: 08.10.202311.10.2023
Konferenznummer: 30

Bibliographische Notiz

Publisher Copyright:
© 2023 IEEE.