Uncertainty-aware sign language video retrieval with probability distribution modeling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929366096674816 |
|---|---|
| author | Wu, Xuan Li, Hongxiang Luo, Yuanjiang Cheng, Xuxin Zhuang, Xianwei Cao, Meng Fu, Keren |
| author_facet | Wu, Xuan Li, Hongxiang Luo, Yuanjiang Cheng, Xuxin Zhuang, Xianwei Cao, Meng Fu, Keren |
| contents | Sign language video retrieval plays a key role in facilitating information access for the deaf community. Despite significant advances in video-text retrieval, the complexity and inherent uncertainty of sign language preclude the direct application of these techniques. Previous methods achieve the mapping between sign language video and text through fine-grained modal alignment. However, due to the scarcity of fine-grained annotation, the uncertainty inherent in sign language video is underestimated, limiting the further development of sign language retrieval tasks. To address this challenge, we propose a novel Uncertainty-aware Probability Distribution Retrieval (UPRet), that conceptualizes the mapping process of sign language video and text in terms of probability distributions, explores their potential interrelationships, and enables flexible mappings. Experiments on three benchmarks demonstrate the effectiveness of our method, which achieves state-of-the-art results on How2Sign (59.1%), PHOENIX-2014T (72.0%), and CSL-Daily (78.4%). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_19689 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Uncertainty-aware sign language video retrieval with probability distribution modeling Wu, Xuan Li, Hongxiang Luo, Yuanjiang Cheng, Xuxin Zhuang, Xianwei Cao, Meng Fu, Keren Computer Vision and Pattern Recognition Information Retrieval Sign language video retrieval plays a key role in facilitating information access for the deaf community. Despite significant advances in video-text retrieval, the complexity and inherent uncertainty of sign language preclude the direct application of these techniques. Previous methods achieve the mapping between sign language video and text through fine-grained modal alignment. However, due to the scarcity of fine-grained annotation, the uncertainty inherent in sign language video is underestimated, limiting the further development of sign language retrieval tasks. To address this challenge, we propose a novel Uncertainty-aware Probability Distribution Retrieval (UPRet), that conceptualizes the mapping process of sign language video and text in terms of probability distributions, explores their potential interrelationships, and enables flexible mappings. Experiments on three benchmarks demonstrate the effectiveness of our method, which achieves state-of-the-art results on How2Sign (59.1%), PHOENIX-2014T (72.0%), and CSL-Daily (78.4%). |
| title | Uncertainty-aware sign language video retrieval with probability distribution modeling |
| topic | Computer Vision and Pattern Recognition Information Retrieval |
| url | https://arxiv.org/abs/2405.19689 |