Repository accompanying the "Sign Pose-based Transformer for Word-level Sign Language Recognition" paper
-
Updated
May 13, 2023 - Python
#
wlasl
Here are 5 public repositories matching this topic...
SignLens – Real-Time ASL Action Recognition using LSTM, MediaPipe, and WLASL100. Captures webcam video, extracts multi-hand 3D hand landmarks with MediaPipe, and runs a sliding-window LSTM model over 30-frame sequences to recognize American Sign Language signs in real time, with support for scaling to the WLASL100 vocabulary.
real-time computer-vision deep-learning asl sign-language lstm action-recognition gesture-recognition tesnorflow hand-tracking multimodal sequence-modeling mediapipe wlasl
-
Updated
Mar 10, 2026 - Python
Real-time ASL word translator that runs entirely in the browser. Uses MediaPipe Hands for landmark tracking and a stacked LSTM model converted to TensorFlow.js for fully client-side inference — no video ever leaves the user's device.
react python nlp machine-learning real-time computer-vision deep-learning accessibility tensorflow asl sign-language lstm gesture-recognition hand-tracking tensorflow-js mediapipe mediapipe-hands wlasl browser-ml client-side-inference
-
Updated
Jul 29, 2026 - Python
Word Level American Sign Language Recognition Using Action Detection - Research
-
Updated
Mar 26, 2026 - Jupyter Notebook
Real-time ASL sign recognition from webcam: Farneback + RAFT optical flow, MediaPipe hand cropping, MLP/SVM classifier, multi-threaded Flask demo
-
Updated
May 13, 2026 - Python
Add this topic to your repo
To associate your repository with the wlasl topic, visit your repo's landing page and select "manage topics."