{"id":"W2529760013","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":"preprint","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Leverage (statistics); Convolutional neural network; Abnormality; Artificial intelligence; Optical flow; Event (particle physics); Feature (linguistics); Pattern recognition (psychology); Computer vision; Machine learning; 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":[],"consensus_categories":[],"category_scores_codex":[0.0005913434,0.0002166236,0.0002705207,0.0005879126,0.0001758157,0.000203684,0.0005738376,0.0003226592,0.000005315655],"category_scores_gemma":[0.000007520559,0.0002207169,0.0001639708,0.0007149845,0.00004046633,0.0003344149,0.0003759457,0.0002311471,0.00001119609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001420335,"about_ca_system_score_gemma":0.00004555152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005496416,"about_ca_topic_score_gemma":0.000926111,"domain_scores_codex":[0.9981735,0.00005535533,0.0004703848,0.000919661,0.0001646845,0.000216384],"domain_scores_gemma":[0.9984821,0.00003017105,0.0002851487,0.000944424,0.0001667412,0.00009138008],"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":[0.00004048564,0.0004934133,0.002876562,0.0001364556,0.0002629888,5.559882e-7,0.000564906,0.01306581,0.003130263,0.03440184,0.0001503143,0.9448764],"study_design_scores_gemma":[0.0001455369,0.0001208147,0.0209074,0.000009071745,0.00009682625,0.000003137607,0.0000148755,0.9428034,0.01264542,0.02164892,0.001302085,0.000302492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02623751,0.00002086847,0.9715419,0.0001840469,0.00009186302,0.001149631,0.000008997328,0.0004664981,0.0002987269],"genre_scores_gemma":[0.9136543,0.00002569688,0.08372877,0.00007365392,0.000132943,0.00218592,0.00007802146,0.00001226176,0.0001084353],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9445739,"threshold_uncertainty_score":0.9000576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01407259528463308,"score_gpt":0.2918092099767843,"score_spread":0.2777366146921513,"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."}}