{"id":"W3199819356","doi":"10.1007/s44163-021-00004-2","title":"Exploring Convolutional Recurrent architectures for anomaly detection in videos: a comparative study","year":2021,"lang":"en","type":"article","venue":"Discover Artificial Intelligence","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Anomaly detection; Task (project management); Artificial intelligence; Deep learning; Focus (optics); Machine learning; Convolutional neural network; Anomaly (physics); Variety (cybernetics); Engineering","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":[0.0002181299,0.000141254,0.0001747039,0.0001466245,0.0002046802,0.000153357,0.0003224107,0.00002997722,0.00001125162],"category_scores_gemma":[0.00005698497,0.0001446075,0.00009226824,0.0007292238,0.00005127472,0.0002520179,0.0001323323,0.0001587062,0.00001908108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009255244,"about_ca_system_score_gemma":0.00009026992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001204173,"about_ca_topic_score_gemma":0.001314916,"domain_scores_codex":[0.9985565,0.00008504341,0.0004059216,0.0005325315,0.0001877829,0.0002322139],"domain_scores_gemma":[0.9992107,0.0001635482,0.0000873573,0.0003371745,0.0001481746,0.00005308235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002396543,0.003168167,0.001693979,0.00003898947,0.00008226813,0.00002679471,0.01853023,0.01261011,0.03796736,0.296872,0.00003432857,0.6287361],"study_design_scores_gemma":[0.00008981715,0.0005413668,0.0104036,0.00003576717,0.00001196942,0.00001326301,0.00411589,0.1405441,0.7598434,0.08334275,0.0006620829,0.0003959636],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.405716,0.00003448886,0.593423,0.0001207828,0.0001624695,0.0003998577,0.000006497159,0.00007060239,0.00006624086],"genre_scores_gemma":[0.9922749,0.000006812937,0.006534894,0.0000363434,0.00008050073,0.001034683,0.000003521826,0.000006578598,0.00002172379],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.721876,"threshold_uncertainty_score":0.5896921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2409233846886999,"score_gpt":0.368324819121254,"score_spread":0.1274014344325541,"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."}}