Research map / Detection and segmentation / Open-set and few-shot detection
Fingerspelling Detection in American Sign Language
Bowen Shi, Diane Brentari, Greg Shakhnarovich, Karen Livescu
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the multi-task detector instead of the strongest listed baseline | Fingerspelling detection · ChicagoFSWild test | MSA: .320 -> .341 | Improved |
| Use the multi-task detector instead of the strongest listed baseline | Fingerspelling detection · ChicagoFSWild+ test | MSA: .477 -> .503 | Improved |
| Add recognition loss (ablation) | Base 3 region-based detector · ChicagoFSWild dev | AP@0.1: .496 -> .505 | Improved |
| Add recognition loss (ablation) | Base 3 region-based detector · ChicagoFSWild dev | MSA: .359 -> .365 | Improved |
| Add LER loss to the recognition-loss model (ablation) | Multi-task detector · ChicagoFSWild dev | AP@0.1: .505 -> .531 | Improved |
| Add LER loss to the recognition-loss model (ablation) | Multi-task detector · ChicagoFSWild dev | MSA: .365 -> .378 | Improved |
| Add pose estimation loss (ablation) | Detector with recognition and LER losses · ChicagoFSWild dev | AP@0.1: .531 -> .539 | Improved |
| Add pose estimation loss (ablation) | Detector with recognition and LER losses · ChicagoFSWild dev | MSA: .378 -> .383 | Improved |
| Add second-stage refinement (ablation) | Detector with recognition, LER, and pose losses · ChicagoFSWild dev | AP@0.5: .399 -> .393 | Hurt |
| Add second-stage refinement (ablation) | Detector with recognition, LER, and pose losses · ChicagoFSWild dev | MSA: .383 -> .386 | Improved |
| Use OpenPose pose heatmaps as input rather than RGB (ablation) | Base 3 region-based detector · ChicagoFSWild dev | AP@0.1: .496 -> .368 | Hurt |
| Add pose heatmaps as input to RGB (ablation) | Base 3 region-based detector · ChicagoFSWild dev | AP@0.1: .496 -> .501 | Improved |
Closest papers by meaning
- OpenFS: Multi-Hand-Capable Fingerspelling Recognition with Implicit Signing-Hand Detection and Frame-Wise Letter-Conditioned Synthesis (CVPR 2026 · similarity 0.94)
- Fingerspelling Recognition in the Wild With Iterative Visual Attention (ICCV 2019 · similarity 0.92)
- BANZ-FS: BANZSL Fingerspelling Dataset (ICLR 2026 · similarity 0.91)
- FSboard: Over 3 Million Characters of ASL Fingerspelling Collected via Smartphones (CVPR 2025 · similarity 0.90)
- A Wireframe-Based Approach for Classifying and Acquiring Proficiency in the American Sign Language (Student Abstract) (AAAI 2024 · similarity 0.85)
- LERMO: A Novel Web Game for AI-Enhanced Sign Language Recognition (AAAI 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
