{"id":"W3138357105","doi":"10.1016/j.dsp.2021.103030","title":"An improved scheme for multifeature-based foreground detection using challenging conditions","year":2021,"lang":"en","type":"article","venue":"Digital Signal Processing","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Artificial intelligence; Computer science; Pixel; Computer vision; Pattern recognition (psychology); Foreground detection; Feature (linguistics); Feature vector; Frame (networking); Diagonal; Mathematics; Background subtraction","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000256346,0.0001690734,0.0001763694,0.00009155282,0.0004993055,0.001379244,0.0002457495,0.00008936076,0.000002003171],"category_scores_gemma":[0.00008089009,0.0001745921,0.0001054967,0.0004021397,0.00003675719,0.002512281,0.00004015062,0.0001359848,0.000001100487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007637799,"about_ca_system_score_gemma":0.0002137576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003850201,"about_ca_topic_score_gemma":0.000008137382,"domain_scores_codex":[0.9987445,0.00003820649,0.0002144377,0.0004872763,0.0001710841,0.0003445149],"domain_scores_gemma":[0.9990554,0.0001435044,0.0001208479,0.0002385751,0.0003392738,0.0001024118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002139874,0.0001585593,0.0004985625,0.0001630367,0.00002164167,0.00001793156,0.0002087843,0.0036292,0.1652913,0.0004421019,0.000001059233,0.8295464],"study_design_scores_gemma":[0.0004713605,0.00006807122,0.0003508819,0.00006727932,0.000006180841,0.00002819697,0.00007039365,0.9498023,0.04547949,0.003286609,0.0001327526,0.0002365154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04806713,0.000228681,0.9510034,0.00006517676,0.0001143336,0.0001425899,0.00001211598,0.0002332743,0.0001332707],"genre_scores_gemma":[0.9031578,3.629678e-7,0.09648739,0.0001242858,0.0001371451,0.00002174939,0.00003867145,0.0000216658,0.00001089353],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9461731,"threshold_uncertainty_score":0.9996574,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03987047743835182,"score_gpt":0.3254237168377377,"score_spread":0.2855532393993859,"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."}}