AI Paper Atlas

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

Ham2Pose: Animating Sign Language Notation Into Pose Sequences

CVPR 2023 · Large language models › Language, safety and interpretability · approach: Sign language datasets and translation · 32 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use normalized DTW-MJE with missing-keypoint handling instead of existing pose distancesPose-sequence similarity measurement · AUTSLmAP: 0.44 -> 0.58Helped
Use normalized keypoints for pose distance measurementsMSE, APE, and DTW-MJE measurements · AUTSLmAP: MSE: 0.27 -> 0.4; APE: 0.29 -> 0.44; DTW-MJE: 0.33 -> 0.58Helped
Generate poses with Ham2Pose rather than Progressive TransformersHamNoSys-to-pose generation · HamNoSys-to-pose distance ranksRank 1 (distance to ground truth): 0.0 -> 0.21Helped
Generate poses with Ham2Pose rather than a constant resting poseHamNoSys-to-pose generation · HamNoSys-to-pose distance ranksRank 1 (distance to ground truth): 0.008 -> 0.21Helped
Train without one Sign language and test on that held-out language (ablation)Ham2Pose · PJM, DGS, GSL, and LSF leave-one-outDistance ranksMixed

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