{"id":"W1983103633","doi":"10.1109/cvprw.2009.5206686","title":"Abnormal events detection based on spatio-temporal co-occurences","year":2009,"lang":"en","type":"article","venue":"2009 IEEE Conference on Computer Vision and Pattern Recognition","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":150,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Office of Naval Research; U.S. Department of Homeland Security; National Science Foundation","keywords":"Computer science; Background subtraction; Pixel; Artificial intelligence; Event (particle physics); Pattern recognition (psychology); Markov random field; Markov chain; Path (computing); Abnormality; Computer vision; Object detection; Contrast (vision); Image segmentation; Image (mathematics); Machine learning","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":[0.0002105191,0.0002557392,0.000193695,0.0002763676,0.0002875307,0.000256699,0.0003058535,0.0001392016,0.00007767673],"category_scores_gemma":[0.000003691687,0.0002289948,0.00008019566,0.0002387206,0.00003024873,0.0003776645,0.00002095989,0.0002452958,0.0001777728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003287737,"about_ca_system_score_gemma":0.0000325331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002224077,"about_ca_topic_score_gemma":0.0000140542,"domain_scores_codex":[0.9983922,0.0001220828,0.0003152422,0.0005931911,0.0003346707,0.0002426178],"domain_scores_gemma":[0.9991156,0.00006211229,0.0001904961,0.0003465099,0.0001385024,0.0001467206],"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":[0.00002733304,0.0001746392,0.0002170224,0.000005957364,0.000002828338,0.00000440256,0.00003117726,0.00005086032,0.0002299778,0.0001295263,0.0005922168,0.9985341],"study_design_scores_gemma":[0.0008178629,0.00420821,0.02962184,0.0002600201,0.000008532831,0.00002426627,0.000005558427,0.9434538,0.0145711,0.004805859,0.001688878,0.0005340847],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07732032,0.000004408689,0.9199808,0.000912503,0.0003332411,0.0003229632,0.00002374989,0.0003421789,0.000759797],"genre_scores_gemma":[0.9894961,0.0000287021,0.007591177,0.002585954,0.0001570434,0.00003279483,0.00006768187,0.000007604129,0.00003301452],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.998,"threshold_uncertainty_score":0.9338138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03495640912331117,"score_gpt":0.2899651683389382,"score_spread":0.255008759215627,"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."}}