SIGMA-ASL is a multimodal dataset with 93,545 word-level ASL clips from Kinect RGB-D, mmWave radar, and dual IMUs, plus benchmarking protocols for single- and multi-modal recognition.
Quantitative survey of the state of the art in sign language recognition
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Reframing head pose estimation as relative pose prediction between image pairs enables a synthetic-only trained model to outperform absolute regression methods on real benchmarks.
Isolated-sign emotion models fail in dialogue; eJSL Dialog benchmarks show a domain gap for generic multimodal ERC models on sign language.
citing papers explorer
-
SIGMA-ASL: Sensor-Integrated Multimodal Dataset for Sign Language Recognition
SIGMA-ASL is a multimodal dataset with 93,545 word-level ASL clips from Kinect RGB-D, mmWave radar, and dual IMUs, plus benchmarking protocols for single- and multi-modal recognition.
-
VGGT-HPE: Reframing Head Pose Estimation as Relative Pose Prediction
Reframing head pose estimation as relative pose prediction between image pairs enables a synthetic-only trained model to outperform absolute regression methods on real benchmarks.
-
Emotion Recognition in Sign Language Conversation
Isolated-sign emotion models fail in dialogue; eJSL Dialog benchmarks show a domain gap for generic multimodal ERC models on sign language.
- SignVerse-2M: A Two-Million-Clip Pose-Native Universe of 55+ Sign Languages