{"id":"W3048665613","doi":"10.1145/3386569.3392440","title":"Learned motion matching","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Human Motion and Animation","field":"Engineering","cited_by":136,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; Ubisoft (Canada)","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Animation; Matching (statistics); Artificial neural network; Scalability; Artificial intelligence; Generative model; Flexibility (engineering); Motion (physics); Bottleneck; Preprocessor; Generative grammar; Machine learning; Database; Computer graphics (images)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00003287803,0.00008616972,0.0000694265,0.00008441216,0.0001061808,0.00003057038,0.00009769687,0.00005857829,0.0002426553],"category_scores_gemma":[0.000007774053,0.00009565389,0.00006704013,0.0002525232,0.0000127902,0.0001343468,9.019108e-7,0.0002450254,0.0001975502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001340929,"about_ca_system_score_gemma":0.000002884189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002020536,"about_ca_topic_score_gemma":0.000007454807,"domain_scores_codex":[0.9995515,0.00001510284,0.0001174756,0.0001054769,0.0001102208,0.000100185],"domain_scores_gemma":[0.9997411,0.00002098391,0.00001081681,0.0001378078,0.00001571061,0.00007354464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004627912,0.0001899737,0.00009994084,0.0003617115,0.0001938005,0.000009340988,0.00742686,0.6633555,0.07526425,0.0138911,0.001455431,0.2377059],"study_design_scores_gemma":[0.00450936,0.0008130996,0.01528851,0.0002647605,0.0002962846,0.00003190883,0.002434247,0.7637138,0.08090727,0.07536965,0.05370358,0.002667573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0774516,0.00001561181,0.9189681,0.001855373,0.000149764,0.00007379634,0.000007175889,0.0007505104,0.000727998],"genre_scores_gemma":[0.9980416,0.00009846177,0.001142397,0.0006193336,0.00004111226,0.000004558774,0.000007513235,0.00002277288,0.0000222093],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.92059,"threshold_uncertainty_score":0.3900652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04042371305013918,"score_gpt":0.2411348440739292,"score_spread":0.20071113102379,"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."}}