Pose-Based Sign Language Appearance Transfer
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915264862355456 |
|---|---|
| author | Moryossef, Amit Sant, Gerard Jiang, Zifan |
| author_facet | Moryossef, Amit Sant, Gerard Jiang, Zifan |
| contents | We introduce a method for transferring the signer's appearance in sign language skeletal poses while preserving the sign content. Using estimated poses, we transfer the appearance of one signer to another, maintaining natural movements and transitions. This approach improves pose-based rendering and sign stitching while obfuscating identity. Our experiments show that while the method reduces signer identification accuracy, it slightly harms sign recognition performance, highlighting a tradeoff between privacy and utility. Our code is available at https://github.com/sign-language-processing/pose-anonymization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_13675 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Pose-Based Sign Language Appearance Transfer Moryossef, Amit Sant, Gerard Jiang, Zifan Computer Vision and Pattern Recognition Computation and Language We introduce a method for transferring the signer's appearance in sign language skeletal poses while preserving the sign content. Using estimated poses, we transfer the appearance of one signer to another, maintaining natural movements and transitions. This approach improves pose-based rendering and sign stitching while obfuscating identity. Our experiments show that while the method reduces signer identification accuracy, it slightly harms sign recognition performance, highlighting a tradeoff between privacy and utility. Our code is available at https://github.com/sign-language-processing/pose-anonymization. |
| title | Pose-Based Sign Language Appearance Transfer |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2410.13675 |