{"id":"W2170932168","doi":"10.1016/j.cviu.2013.06.007","title":"An on-line, real-time learning method for detecting anomalies in videos using spatio-temporal compositions","year":2013,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":169,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Codebook; Artificial intelligence; Background subtraction; Computer vision; Video tracking; Probabilistic logic; Line (geometry); Pattern recognition (psychology); Tracking (education); Video processing; Pixel; 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":[0.0003966063,0.0001807806,0.000218245,0.0003462211,0.0006662147,0.000676448,0.000251588,0.00007235599,0.000014858],"category_scores_gemma":[0.00001106817,0.0001756086,0.00006334887,0.0003533033,0.00004740967,0.001011281,0.0001332268,0.0001715407,0.000006506964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001598067,"about_ca_system_score_gemma":0.00002004623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001550621,"about_ca_topic_score_gemma":0.000009325069,"domain_scores_codex":[0.9986607,0.0001352989,0.0003233673,0.0004904716,0.0001247282,0.0002653615],"domain_scores_gemma":[0.9991032,0.000290337,0.0001440566,0.00027232,0.00007882949,0.0001112561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001200774,0.0007182813,0.002094736,0.0001962963,0.00007436352,0.00002578824,0.004040177,0.0286607,0.4359092,0.172255,0.001155278,0.3547501],"study_design_scores_gemma":[0.0003321022,0.0005485243,0.0003172795,0.00007784569,0.000004312466,0.0000222259,0.0001814084,0.9859014,0.002693172,0.009626096,0.00008192747,0.0002137594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04030063,0.000005344411,0.9583037,0.0003233943,0.00005220194,0.0005021304,0.000001763474,0.0003326573,0.0001781435],"genre_scores_gemma":[0.4723857,0.000004590188,0.5274225,0.00008904737,0.00004293362,0.0000243162,0.000006543271,0.00001164011,0.00001271881],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9572406,"threshold_uncertainty_score":0.7161111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04988297504113703,"score_gpt":0.345789801825941,"score_spread":0.295906826784804,"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."}}