AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

ASL Citizen: A Community-Sourced Dataset for Advancing Isolated Sign Language Recognition

Aashaka Desai, Lauren Berger, Fyodor O Minakov, Vanessa Milan, Chinmay Singh, Kriston L Pumphrey, Richard Ladner, Hal Daumé III, Alex Xijie Lu, Naomi Caselli, Danielle Bragg

NeurIPS 2023 · Large language models › Language, safety and interpretability · approach: Sign language datasets and translation · 14 citations (OpenAlex)

Read the paperCheck 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 changedWhereMeasuredEffect
train on ASL Citizen instead of WLASL-2000 (same I3D)I3D · ASL Citizen test SubsetRec@1: 0.0849 -> 0.7416Improved
use ASL Citizen-trained features instead of WLASL-2000 featuresI3D features · ASL Citizen testRec@1: 0.0985 -> 0.5803Improved
use ASL Citizen-trained features instead of Kinetics featuresI3D features · ASL Citizen testRec@1: 0.0041 -> 0.5803Improved
use appearance-based I3D instead of pose-based ST-GCNASL Citizen classifier · ASL Citizen testRec@1: 0.5952 -> 0.6310Improved
reduce training set to 25%, 50%, 75% of videos (ablation)I3D · ASL Citizen testaccuracyHurt
replace random temporal crops with frame skipping/padding; add per-frame loss (ablation)I3D training · ASL CitizenconvergenceMixed

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy