xmartlabs/spoter-embeddings
Create embeddings from sign pose videos using Transformers
This project helps sign language researchers and educators analyze and understand sign language by converting videos of sign poses into numerical 'embedding' vectors. These vectors capture the essence of a sign, making it easy to compare different signs or identify similar ones. The input is skeletal keypoint data extracted from sign language videos, and the output is a compact numerical representation of the sign, enabling tasks like classification or similarity searches for individual words or phrases in sign languages globally.
No commits in the last 6 months.
Use this if you need to compare, classify, or find similarities between different sign language gestures from video data, especially for few-shot learning tasks on new datasets.
Not ideal if you need a direct, out-of-the-box sign language translation system without further model development or analysis.
Stars
32
Forks
3
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 28, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/xmartlabs/spoter-embeddings"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVlabs/MambaVision
[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone
sign-language-translator/sign-language-translator
Python library & framework to build custom translators for the hearing-impaired and translate...
kyegomez/Jamba
PyTorch Implementation of Jamba: "Jamba: A Hybrid Transformer-Mamba Language Model"
autonomousvision/transfuser
[PAMI'23] TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving;...
kyegomez/MultiModalMamba
A novel implementation of fusing ViT with Mamba into a fast, agile, and high performance...