{"id":"W2963111876","doi":"10.1109/wacv.2018.00188","title":"Plug-and-play CNN for crowd motion analysis: An application in abnormal event detection","year":2018,"lang":"en","type":"article","venue":"Institutional Research Information System (Università degli Studi di Trento)","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":197,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Leverage (statistics); Convolutional neural network; Artificial intelligence; Abnormality; Optical flow; Pattern recognition (psychology); Feature (linguistics); Event (particle physics); Feature extraction; Machine learning; Computer vision; Image (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":["sts"],"consensus_categories":[],"category_scores_codex":[0.001520775,0.0001499233,0.0001975465,0.001859335,0.001387357,0.0002485926,0.0005287912,0.0001323109,0.000003713131],"category_scores_gemma":[0.00003697565,0.000158999,0.00009823204,0.002993155,0.0002099447,0.004148519,0.0002156322,0.0001883625,0.00008428893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008524342,"about_ca_system_score_gemma":0.0001704172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004839789,"about_ca_topic_score_gemma":0.0005089257,"domain_scores_codex":[0.9979625,0.0001348357,0.0004579156,0.0003801049,0.0007065519,0.0003581331],"domain_scores_gemma":[0.99814,0.00007579333,0.0002053705,0.0004323132,0.0009829169,0.0001636423],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001632537,0.0002053647,0.005001255,0.0001375577,0.0002148572,0.000002338753,0.00329834,0.004773146,0.0003483286,0.6930285,0.00012078,0.2927063],"study_design_scores_gemma":[0.00114848,0.0003978247,0.1109868,0.0000421465,0.0000522332,0.00002403717,0.002523643,0.8672926,0.001081576,0.0005600703,0.01559319,0.0002973494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06149627,0.00001450466,0.9339998,0.0001768753,0.00009181519,0.0009743487,0.00002755388,0.0002251222,0.002993697],"genre_scores_gemma":[0.9959668,0.00000907411,0.003327819,0.00002331601,0.00009032198,0.000428788,0.00009581824,0.000004197424,0.00005386337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9344705,"threshold_uncertainty_score":0.9999127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04007682701033993,"score_gpt":0.3309510471245355,"score_spread":0.2908742201141956,"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."}}