{"id":"W4388544041","doi":"10.1109/access.2023.3331687","title":"Contact Part Detection From 3D Human Motion Data Using Manually Labeled Contact Data and Deep Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Korea Creative Content Agency; Ministry of Culture, Sports and Tourism","keywords":"Computer science; Artificial intelligence; Motion (physics); Feature (linguistics); Motion capture; Computer vision; Affordance; Context (archaeology); Process (computing); Human–computer interaction; Virtual reality; Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005523583,0.001863264,0.001129835,0.002358855,0.0003778572,0.0005214494,0.0012985,0.001443155,0.002465985],"category_scores_gemma":[0.001991689,0.0004777545,0.0008167964,0.001273959,0.0005849336,0.0009896585,0.001380595,0.0006834265,0.002177214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003890462,"about_ca_system_score_gemma":0.0007069464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003285799,"about_ca_topic_score_gemma":0.007861269,"domain_scores_codex":[0.9989873,0.0001554743,0.00006072375,0.0003861819,0.000288509,0.000121822],"domain_scores_gemma":[0.9991992,0.0001473516,0.0001502087,0.0002407003,0.0001918886,0.00007071341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00112061,0.0007585197,0.01636036,0.000413107,0.0002132843,0.001106879,0.0002306719,0.03123773,0.0921957,0.001129636,0.01322012,0.8420133],"study_design_scores_gemma":[0.0000583749,0.0006132311,0.03682912,0.0001082087,0.00008658466,0.00167542,0.0002903833,0.9033397,0.04759885,0.00327546,0.006056086,0.00006855082],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1773018,0.001436892,0.8082611,0.0001936605,0.0002161253,0.000446836,0.001889787,0.006572156,0.00368174],"genre_scores_gemma":[0.8543473,0.0008051696,0.1329526,0.0002242707,0.0001036247,0.000360568,0.005688509,0.0001762829,0.005341674],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003285799,"threshold_uncertainty_score":0.008249581,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1653261047171309,"score_gpt":0.3682443666323879,"score_spread":0.202918261915257,"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."}}