{"id":"W2928521819","doi":"10.1109/iccv.2019.00554","title":"AMASS: Archive of Motion Capture As Surface Shapes","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Motion capture; Computer science; Motion (physics); Animation; Hyperparameter; Polygon mesh; Representation (politics); Artificial intelligence; Visualization; Computer animation; Computer vision; Computer graphics (images)","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":[0.0001317627,0.0001597124,0.0002236469,0.0001001737,0.00003110408,0.0001026176,0.0005653789,0.0001713579,0.0003292678],"category_scores_gemma":[0.00001508565,0.0001424138,0.0001342311,0.00007163178,0.00002324817,0.0001958412,0.0005656311,0.000349605,0.000571634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002409644,"about_ca_system_score_gemma":0.00009676039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002919387,"about_ca_topic_score_gemma":0.00002693877,"domain_scores_codex":[0.998875,0.00007138058,0.0002346835,0.0004281818,0.0002558241,0.0001349926],"domain_scores_gemma":[0.9991416,0.00006178143,0.0002197399,0.0004053011,0.0001248896,0.00004663271],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009389756,0.001740245,0.003328053,0.003857793,0.001073149,0.00008286109,0.02251255,0.1911317,0.03536388,0.4515179,0.0901744,0.1991236],"study_design_scores_gemma":[0.00104163,0.0002363987,0.01299503,0.0009867385,0.00009787515,0.00004677167,0.0004636061,0.5636001,0.05119868,0.3580947,0.009559681,0.001678852],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07954507,0.00006696731,0.838726,0.0005142085,0.0007868638,0.0003459864,0.00002864603,0.0001929845,0.0797933],"genre_scores_gemma":[0.9793601,0.00005129465,0.01641046,0.000258695,0.00006923833,0.000005075698,0.00006040476,0.000009269305,0.003775455],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.899815,"threshold_uncertainty_score":0.7347389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0187266840177888,"score_gpt":0.2496962269284956,"score_spread":0.2309695429107068,"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."}}