{"id":"W4391306906","doi":"10.1109/smc53992.2023.10394608","title":"Enhancing Human Action Recognition with Asymmetric Generalized Gaussian Mixture Model-Based Hidden Markov Models and Bounded Support","year":2023,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Hidden Markov model; Viterbi algorithm; Computer science; Robustness (evolution); Bounded function; Artificial intelligence; Gaussian; Mixture model; Forward algorithm; Machine learning; Pattern recognition (psychology); Gaussian process; Algorithm; Markov chain; Markov model; Variable-order Markov model; Mathematics","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":[0.0003277024,0.0002120196,0.0001986098,0.0007218594,0.0004270828,0.0003748315,0.0001881327,0.0001262833,0.00008386109],"category_scores_gemma":[0.000008918181,0.0001829988,0.00006011331,0.001061604,0.00003442706,0.001279632,0.00005763406,0.0001763312,0.00009589792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000671879,"about_ca_system_score_gemma":0.0001184941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005507478,"about_ca_topic_score_gemma":0.000177043,"domain_scores_codex":[0.9984056,0.00007874422,0.0002733537,0.0005461324,0.0003499823,0.0003461519],"domain_scores_gemma":[0.9992521,0.00004331149,0.0001277717,0.0002934168,0.0001336061,0.0001497853],"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":[0.0002743351,0.0005230812,0.0001969375,0.0004791602,0.0002618944,0.000186336,0.001946031,0.003033455,0.05996453,0.02242706,0.01815913,0.892548],"study_design_scores_gemma":[0.001569666,0.0002407206,0.0003532975,0.00005763571,0.00004033302,0.0000323893,0.00007619167,0.8869646,0.05327983,0.05674616,0.0001496828,0.0004894825],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2977607,0.00000703994,0.6926484,0.0004985323,0.0001133757,0.0002742833,0.000006716108,0.0007458094,0.007945194],"genre_scores_gemma":[0.9315843,0.0000293645,0.06473687,0.000735332,0.00009460597,0.0000714774,0.0002315666,0.00002689063,0.002489571],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8920586,"threshold_uncertainty_score":0.7462474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04946598297683552,"score_gpt":0.2827065772346036,"score_spread":0.2332405942577681,"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."}}