Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| 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 |