AI Paper Atlas

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

PopSign ASL v1.0: An Isolated American Sign Language Dataset Collected via Smartphones

Thad Starner, Sean Forbes, Matthew So, David Martin, Rohit Sridhar, Gururaj Deshpande, Sam Sepah, Sahir Shahryar, Khushi Bhardwaj, Tyler Kwok, Daksh Sehgal, Saad Hassan and 12 more

NeurIPS 2023 · Large language models › Language, safety and interpretability · approach: Sign language datasets and translation

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
evaluate on test signers instead of validation signersBi-LSTM on MediaPipe Hands · PopSign ASL v1.0accuracy: 82.1% -> 84.2%Improved
include videos where MediaPipe tracking failed completely (validation)Bi-LSTM on MediaPipe Hands · PopSign validationaccuracy: 82.1% -> 81.9%Hurt
include videos where MediaPipe tracking failed completely (test)Bi-LSTM on MediaPipe Hands · PopSign testaccuracy: 84.2% -> 83.8%Hurt
restrict to 5-sign sets with a 2D-CNN (<=1MB) instead of 250-sign Bi-LSTMPopSignAI Preview · PopSign gameplayaccuracy: approximately 95%Improved
flip left-handed videos to right-handedpreprocessing · PopSign ASL v1.0accuracyNo clear effect
add MediaPipe Pose or Holistic featuresBi-LSTM on MediaPipe Hands · PopSign ASL v1.0accuracyNo clear effect

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