{"id":"W2963992477","doi":"10.1109/cvprw.2019.00119","title":"Variational Learning of Beta-Liouville Hidden Markov Models for Infrared Action Recognition","year":2019,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Hidden Markov model; Pattern recognition (psychology); Action recognition; Artificial intelligence; Computer science; Infrared; Action (physics); Domain (mathematical analysis); Sensitivity (control systems); Speech recognition; Machine learning; Mathematics; Physics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002277701,0.00007996532,0.0001191135,0.0001606719,0.00008213216,0.00005781128,0.0001425302,0.00006956418,0.0006007678],"category_scores_gemma":[0.00001965016,0.00007946969,0.00008222526,0.000161333,0.000007435068,0.001209094,0.00003817275,0.00008314197,0.0001549416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002998181,"about_ca_system_score_gemma":0.00004479719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001224239,"about_ca_topic_score_gemma":0.000002385321,"domain_scores_codex":[0.9991853,0.00004525548,0.0002268931,0.0002267102,0.0001894682,0.0001263759],"domain_scores_gemma":[0.9992996,0.0001310295,0.0001588592,0.0001370407,0.0002397261,0.00003367424],"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":[0.0001318474,0.0002742984,0.0004877278,0.0001991643,0.0001532148,6.117082e-7,0.0009537639,0.002920213,0.01323986,0.1243288,0.005453576,0.8518569],"study_design_scores_gemma":[0.001115403,0.0002452077,0.001176763,0.00003792399,0.00001857673,0.000006109759,0.0001387225,0.8401576,0.01780291,0.1367427,0.002319423,0.000238665],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05812124,0.000006013646,0.9048734,0.0001548246,0.0003379837,0.0003133973,0.000007750948,0.0001267248,0.03605865],"genre_scores_gemma":[0.8787398,0.00001443088,0.1141125,0.0001722445,0.0001074048,0.00005034015,0.0001447655,0.00001079974,0.006647735],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8516182,"threshold_uncertainty_score":0.6577987,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04395596095786145,"score_gpt":0.2597709055270149,"score_spread":0.2158149445691534,"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."}}