{"id":"W2120607659","doi":"10.1109/crv.2006.14","title":"Automated Detection of Unusual Events on Stairs","year":2006,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Stairs; Hidden Markov model; Background subtraction; Computer science; Conditional random field; Segmentation; Affine transformation; Artificial intelligence; Set (abstract data type); Markov random field; Computation; Data set; Pattern recognition (psychology); Field (mathematics); Optical flow; Activity recognition; Subtraction; Computer vision; Image segmentation; Pixel; Image (mathematics); Algorithm; 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":[0.00005538664,0.00004837138,0.00005172418,0.0000791116,0.00005418192,0.00001050325,0.000174778,0.00003262113,0.000007290613],"category_scores_gemma":[0.00000224426,0.00004272023,0.00003175801,0.0003159632,0.00001082645,0.00008831583,0.0000323224,0.00003378363,0.00002687751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002284665,"about_ca_system_score_gemma":0.00000956385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001645695,"about_ca_topic_score_gemma":0.00001387186,"domain_scores_codex":[0.9995369,0.00001206878,0.0001329962,0.0001343689,0.0001066606,0.00007698926],"domain_scores_gemma":[0.9996528,0.00001345766,0.00005733711,0.0002197101,0.00004043723,0.00001627184],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001280615,0.0005416103,0.0007194648,0.00001474933,0.00001470396,0.000001413216,0.00003706492,0.0009124349,0.199232,0.66558,0.003920794,0.1290129],"study_design_scores_gemma":[0.0001200507,0.0001815522,0.0191149,0.000004415592,0.000001750765,0.000003534078,0.000005450546,0.1132802,0.855292,0.009416603,0.002487285,0.00009220607],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1011726,0.000002268107,0.8887712,0.00010156,0.00003542393,0.00009475895,8.334732e-7,0.001297866,0.00852349],"genre_scores_gemma":[0.9890419,7.907567e-7,0.01023204,0.00003318526,0.00001337206,0.00001865887,7.253092e-7,0.000002996905,0.0006563434],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8878693,"threshold_uncertainty_score":0.174208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006603018516616361,"score_gpt":0.2432736236971041,"score_spread":0.2366706051804878,"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."}}