{"id":"W4409356433","doi":"10.1109/tip.2025.3558089","title":"CRCL: Causal Representation Consistency Learning for Anomaly Detection in Surveillance Videos","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Ministry of Education-China Mobile Research Fund Project; National Key Research and Development Program of China; National Natural Science Foundation of China; Shanghai Key Basic Research Program","keywords":"Anomaly detection; Computer science; Artificial intelligence; Representation (politics); Consistency (knowledge bases); Pattern recognition (psychology); Computer vision; 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":[0.0002624454,0.0001409244,0.0001638655,0.0003953156,0.0005819293,0.0002344794,0.0002298042,0.00008718993,0.000004216292],"category_scores_gemma":[0.0000280523,0.0001592223,0.00008554599,0.001169663,0.00005731154,0.0006495667,0.000003272175,0.0002649715,0.000005432496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001217166,"about_ca_system_score_gemma":0.0001110794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000936346,"about_ca_topic_score_gemma":0.000151024,"domain_scores_codex":[0.9987529,0.0000666114,0.0003479294,0.0004872122,0.0001211207,0.0002242061],"domain_scores_gemma":[0.9992304,0.0001523661,0.0001215213,0.0002639956,0.000195598,0.00003611293],"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":[0.00005216836,0.0001580886,0.0002079114,0.0001104333,0.0000137213,0.000002160059,0.00024077,0.004652802,0.1062442,0.0003484184,0.00002994026,0.8879394],"study_design_scores_gemma":[0.000611819,0.0001164496,0.001686575,0.00009936436,0.00001357044,0.00001237654,0.0001355079,0.4011704,0.5928635,0.00234229,0.0006846827,0.000263445],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008218057,0.00005025708,0.9894128,0.0005229489,0.0001656535,0.0004779523,0.00000219469,0.0004966407,0.000653516],"genre_scores_gemma":[0.9578246,0.00001971489,0.04085703,0.0001086006,0.00001691126,0.0005664051,0.000001155563,0.00001228492,0.0005932234],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9496066,"threshold_uncertainty_score":0.6492896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01479561601664831,"score_gpt":0.298702768909442,"score_spread":0.2839071528927937,"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."}}