Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kindiroglu, Ahmet Alp, Kara, Ozgur, Ozdemir, Ogulcan, Akarun, Lale
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2403.14534
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910410673750016
author Kindiroglu, Ahmet Alp
Kara, Ozgur
Ozdemir, Ogulcan
Akarun, Lale
author_facet Kindiroglu, Ahmet Alp
Kara, Ozgur
Ozdemir, Ogulcan
Akarun, Lale
contents Sign language recognition (SLR) has recently achieved a breakthrough in performance thanks to deep neural networks trained on large annotated sign datasets. Of the many different sign languages, these annotated datasets are only available for a select few. Since acquiring gloss-level labels on sign language videos is difficult, learning by transferring knowledge from existing annotated sources is useful for recognition in under-resourced sign languages. This study provides a publicly available cross-dataset transfer learning benchmark from two existing public Turkish SLR datasets. We use a temporal graph convolution-based sign language recognition approach to evaluate five supervised transfer learning approaches and experiment with closed-set and partial-set cross-dataset transfer learning. Experiments demonstrate that improvement over finetuning based transfer learning is possible with specialized supervised transfer learning methods.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14534
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Transfer Learning for Cross-dataset Isolated Sign Language Recognition in Under-Resourced Datasets
Kindiroglu, Ahmet Alp
Kara, Ozgur
Ozdemir, Ogulcan
Akarun, Lale
Computer Vision and Pattern Recognition
Sign language recognition (SLR) has recently achieved a breakthrough in performance thanks to deep neural networks trained on large annotated sign datasets. Of the many different sign languages, these annotated datasets are only available for a select few. Since acquiring gloss-level labels on sign language videos is difficult, learning by transferring knowledge from existing annotated sources is useful for recognition in under-resourced sign languages. This study provides a publicly available cross-dataset transfer learning benchmark from two existing public Turkish SLR datasets. We use a temporal graph convolution-based sign language recognition approach to evaluate five supervised transfer learning approaches and experiment with closed-set and partial-set cross-dataset transfer learning. Experiments demonstrate that improvement over finetuning based transfer learning is possible with specialized supervised transfer learning methods.
title Transfer Learning for Cross-dataset Isolated Sign Language Recognition in Under-Resourced Datasets
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.14534