{"id":"W4293863405","doi":"10.1109/siu55565.2022.9864748","title":"Object-Centric Video Anomaly Detection with Covariance Features","year":2022,"lang":"en","type":"article","venue":"2022 30th Signal Processing and Communications Applications Conference (SIU)","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Stantec (Canada)","funders":"","keywords":"Artificial intelligence; Computer science; Anomaly detection; Pattern recognition (psychology); Object detection; Probabilistic logic; Benchmark (surveying); Covariance; Autoregressive model; Computer vision; Mixture model; Curse of dimensionality; Probability distribution; Mathematics; Statistics","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0003994629,0.0002554031,0.0002310379,0.0002952659,0.003929405,0.0004999962,0.002284639,0.00007235739,0.00006563697],"category_scores_gemma":[0.000006749992,0.0002597981,0.00005614975,0.002357971,0.0002857499,0.000516378,0.00105162,0.0007012212,0.00001280613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001383816,"about_ca_system_score_gemma":0.0003739722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001215602,"about_ca_topic_score_gemma":0.00007014669,"domain_scores_codex":[0.9979929,0.0001886412,0.0003902694,0.0007091268,0.000390547,0.0003285596],"domain_scores_gemma":[0.9971686,0.0001296151,0.0003747646,0.001846425,0.0003394945,0.0001411259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002766009,0.0004439687,0.0002828629,0.00004341217,0.00003707005,0.000001379191,0.0007146765,0.0002990649,0.007084084,0.1486489,0.0003700393,0.8420469],"study_design_scores_gemma":[0.001712632,0.001044738,0.00730873,0.0001031232,0.0002135221,0.0009213313,0.003666009,0.3911125,0.009887807,0.04692306,0.5348071,0.002299369],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001055063,0.002149877,0.9891044,0.002167098,0.00001479112,0.0008637526,0.00002739612,0.0006620884,0.003955551],"genre_scores_gemma":[0.9359246,0.0003298794,0.05664147,0.0003692647,0.00003006201,0.005973992,0.0000466596,0.0000236884,0.0006603019],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9348696,"threshold_uncertainty_score":0.9999854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01577737459011695,"score_gpt":0.2459433440754947,"score_spread":0.2301659694853777,"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."}}