|
|
|
|
| LEADER |
00000naa a2200000 a 4500 |
| 003 |
AR-LpUFIB |
| 005 |
20250311170534.0 |
| 008 |
230201s2024 xx o 000 0 eng d |
| 024 |
8 |
|
|a DIF-M8951
|b 9179
|z DIF008213
|
| 040 |
|
|
|a AR-LpUFIB
|b spa
|c AR-LpUFIB
|
| 100 |
1 |
|
|a Ríos, Gastón Gustavo
|
| 245 |
1 |
0 |
|a Scaling up convAtt for sign language recognition
|
| 300 |
|
|
|a 1 archivo (624 KB)
|
| 500 |
|
|
|a Formato de archivo PDF. -- Este documento es producción intelectual de la Facultad de Informática - UNLP (Colección BIPA/Biblioteca)
|
| 520 |
|
|
|a Sign language is crucial for communication within the deaf community, making Sign Language Recognition (SLR) essential for bridging the gap between signers and non-signers. However, SLR models often face challenges due to limited data availability and quality. This paper investigates various data augmentation and regularization techniques to enhance the performance of a lightweight SLR model. We focus on recognizing signs from the French Belgian Sign Language using a novel model architecture that integrates convolutional, channel attention, and selfattention layers. Our experiments demonstrate the effectiveness of these techniques, achieving a top-1 accuracy of 49.99% and a top-10 accuracy of 83.19% across 600 distinct signs.
|
| 534 |
|
|
|a Congreso Argentino de Ciencias de la Computación (30mo : 2024 : La Plata, Argentina)
|
| 650 |
|
4 |
|a TECNOLOGÍAS PARA PERSONAS CON DISCAPACIDADES
|
| 653 |
|
|
|a lenguaje de señas
|
| 700 |
1 |
|
|a Dal Bianco, Pedro Alejandro
|
| 700 |
1 |
|
|a Ronchetti, Franco
|
| 700 |
1 |
|
|a Quiroga, Facundo Manuel
|
| 700 |
1 |
|
|a Ponte Ahón, Santiago Andrés
|
| 700 |
1 |
|
|a Stanchi, Oscar
|
| 700 |
1 |
|
|a Hasperué, Waldo
|
| 856 |
4 |
0 |
|u http://sedici.unlp.edu.ar/handle/10915/176284
|
| 942 |
|
|
|c CP
|
| 952 |
|
|
|0 0
|1 0
|4 0
|6 A1380
|7 3
|8 BD
|9 84489
|a DIF
|b DIF
|d 2025-03-11
|l 0
|o A1380
|r 2025-03-11 17:05:34
|u http://catalogo.info.unlp.edu.ar/meran/getDocument.pl?id=2915
|w 2025-03-11
|y CP
|
| 999 |
|
|
|c 57982
|d 57982
|
