{"id":"W2061304929","doi":"10.1109/tits.2012.2228640","title":"Automated Real-Time Detection of Potentially Suspicious Behavior in Public Transport Areas","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Event (particle physics); Public security; Artificial intelligence; Video tracking; Computer vision; Geolocation; Object detection; Tracking (education); Matching (statistics); Public transport; Cognitive neuroscience of visual object recognition; Object (grammar); Fainting; Real-time computing; Data mining; Computer security; Pattern recognition (psychology); 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006206875,0.0003120865,0.0005018361,0.0007966097,0.0001206836,0.0001018669,0.0005004809,0.0002287411,0.00007851585],"category_scores_gemma":[0.000003886181,0.0003163949,0.0002702551,0.001197371,0.00006381921,0.0008602705,3.797106e-7,0.0002657035,0.0001286006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001204101,"about_ca_system_score_gemma":0.0001116954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003382469,"about_ca_topic_score_gemma":0.001064237,"domain_scores_codex":[0.9968275,0.0002673534,0.001296723,0.0005762177,0.0006080429,0.0004241753],"domain_scores_gemma":[0.9983893,0.0001511095,0.0003018132,0.0005791971,0.0004150759,0.0001634946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000255297,0.004445783,0.02082326,0.0007652956,0.0005573126,0.000227573,0.007382539,0.2634435,0.423463,0.002218988,0.00004638883,0.2763711],"study_design_scores_gemma":[0.002291804,0.001234147,0.4472375,0.000485547,0.0001940898,0.0000851784,0.0007300256,0.1971989,0.3483728,0.0002141755,0.0003129807,0.001642768],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3402167,0.00002150461,0.6573526,0.00004192808,0.0008620214,0.0007875629,0.0000249665,0.0005832782,0.0001094277],"genre_scores_gemma":[0.9968032,0.0000958594,0.002340379,0.00001503029,0.00002087198,0.000512441,0.00002206763,0.00003537503,0.0001548046],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6565865,"threshold_uncertainty_score":0.9999288,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0262737456427013,"score_gpt":0.2716540302220286,"score_spread":0.2453802845793273,"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."}}