{"id":"W3021295796","doi":"10.1145/3377552","title":"Learning Three-dimensional Skeleton Data from Sign Language Video","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Intelligent Systems and Technology","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Sign language; Motion capture; Artificial intelligence; Computer vision; Avatar; Animation; Gesture; Classifier (UML); Character animation; Motion (physics); Computer animation; Speech recognition; Computer graphics (images); Human–computer interaction","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010178,0.0001460812,0.0001932955,0.0001953916,0.000229798,0.00009654233,0.0008336258,0.000165921,0.0001298572],"category_scores_gemma":[0.00005222903,0.0001359881,0.00003205792,0.0003689492,0.0000529467,0.0002764113,0.00007613256,0.0004228476,0.000375722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001843056,"about_ca_system_score_gemma":0.00002399097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002526351,"about_ca_topic_score_gemma":0.00006283195,"domain_scores_codex":[0.9987816,0.00004734136,0.0002590892,0.0005666775,0.0001649671,0.0001803179],"domain_scores_gemma":[0.9988942,0.0001467958,0.00008442432,0.0007392797,0.00004941198,0.00008591894],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000356337,0.0001977621,0.0002752021,0.00006124617,0.0002601194,0.00008757505,0.0009088368,0.002029364,0.01050188,0.004363467,0.001259194,0.9800197],"study_design_scores_gemma":[0.00148632,0.002073082,0.0002134532,0.0004573997,0.0001621029,0.000224138,0.003603127,0.7811775,0.08063046,0.01110226,0.1174611,0.001409017],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05407324,0.0005561988,0.939562,0.004535936,0.0003487026,0.0001984432,0.0000372274,0.0006059649,0.0000823271],"genre_scores_gemma":[0.9963667,0.00007207114,0.003059745,0.0002390219,0.00007545842,0.00002552024,0.00003928483,0.00001235789,0.0001098661],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9786107,"threshold_uncertainty_score":0.5545434,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04467870537470501,"score_gpt":0.2670606905505209,"score_spread":0.2223819851758159,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}