{"id":"W4368755539","doi":"10.1145/3588432.3591541","title":"CALM: Conditional Adversarial Latent Models  for Directable Virtual Characters","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Research Canada; Simon Fraser University","funders":"","keywords":"Computer science; Adversarial system; Representation (politics); Motion (physics); Character (mathematics); Artificial intelligence; Task (project management); Imitation; Trajectory; Control (management); Encoder; Key (lock); Engineering","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":[0.00106393,0.001230228,0.0007543277,0.0003716622,0.0002967977,0.0007781435,0.001732048,0.001234003,0.005133071],"category_scores_gemma":[0.003808899,0.0005512856,0.0008431142,0.0003025029,0.001208067,0.001278163,0.002035742,0.002619121,0.00125455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009445304,"about_ca_system_score_gemma":0.0007489799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003720549,"about_ca_topic_score_gemma":0.004844439,"domain_scores_codex":[0.9993916,0.0002573052,0.00001692321,0.0001439571,0.0001239184,0.00006632805],"domain_scores_gemma":[0.9987375,0.0008353565,0.0001081367,0.0001574039,0.00008496884,0.00007667728],"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":[0.00008680233,0.00004894318,0.0003621855,0.00006215154,0.00003760934,0.00006884431,0.00006017273,0.9361748,0.001648962,0.02576142,0.003305235,0.03238298],"study_design_scores_gemma":[0.000004975972,0.0000135295,0.0000259636,0.0000047699,0.00000213232,0.0000087494,0.000002354916,0.9921991,0.0002771052,0.006906764,0.0005509515,0.000003636398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005265625,0.0002205867,0.9913256,0.0002285647,0.00004329293,0.00004021039,0.0001602055,0.001020254,0.001695701],"genre_scores_gemma":[0.7080677,0.000576399,0.2696544,0.0006727261,0.0001410601,0.0005491127,0.00132029,0.0007808621,0.01823731],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005133071,"threshold_uncertainty_score":0.0171718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08461080874364349,"score_gpt":0.2810145797396992,"score_spread":0.1964037709960557,"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."}}