SEDS: Semantically Enhanced Dual-Stream Encoder for Sign Language Retrieval

Sign language retrieval is more biased towards understanding the semantic information of human actions contained in video clips. The proposed framework addresses these issues by integrating Pose and RGB modalities to represent the local and global information of sign language videos.

Data and Resources

Cite this as

Longtao Jiang, Min Wang, Zecheng Li, Yao Fang, Wengang Zhou, Houqiang Li (2024). Dataset: SEDS: Semantically Enhanced Dual-Stream Encoder for Sign Language Retrieval. https://doi.org/10.57702/do63vg3o

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2407.16394
Author Longtao Jiang
More Authors
Min Wang
Zecheng Li
Yao Fang
Wengang Zhou
Houqiang Li
Homepage https://github.com/longtaojiang/SEDS