{"id":"W4396951633","doi":"10.1016/j.knosys.2024.111942","title":"Normality learning reinforcement for anomaly detection in surveillance videos","year":2024,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"China Scholarship Council; Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China","keywords":"Normality; Anomaly detection; Anomaly (physics); Artificial intelligence; Computer science; Reinforcement learning; Psychology; Social psychology; Physics","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":[0.001082641,0.0001515685,0.0001896796,0.0002722557,0.0001813687,0.0002900551,0.0003292134,0.00009750275,0.000003960936],"category_scores_gemma":[0.00003954267,0.0001483964,0.0001116115,0.0008304357,0.00002226481,0.000243389,0.00005167848,0.0001811753,0.00007140292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002620325,"about_ca_system_score_gemma":0.0001224634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002111154,"about_ca_topic_score_gemma":0.0001686015,"domain_scores_codex":[0.9985838,0.0001240729,0.00043189,0.0004567955,0.0001327489,0.0002706991],"domain_scores_gemma":[0.999104,0.0002302953,0.00008503693,0.0003813606,0.0001346579,0.0000646163],"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":[0.0001699576,0.0006409981,0.01472384,0.007059355,0.0001874866,0.00003855806,0.002970855,0.1195497,0.08659533,0.2375961,0.005379706,0.5250881],"study_design_scores_gemma":[0.0002034885,0.000147773,0.0006637762,0.0001129253,0.000002792154,0.000005895043,0.00002300708,0.8825375,0.01720924,0.0001211056,0.09878171,0.0001907246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007383234,0.0007642085,0.9873412,0.0001150813,0.0006715912,0.0008293756,0.00000348162,0.0009033442,0.001988543],"genre_scores_gemma":[0.9960727,0.000006521157,0.001280667,0.00001532947,0.0001539104,0.001152595,0.000006784963,0.00001643105,0.001295074],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9886895,"threshold_uncertainty_score":0.6051428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01658107596017541,"score_gpt":0.2767708898191404,"score_spread":0.260189813858965,"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."}}