{"id":"W1994634851","doi":"10.1109/tip.2014.2378053","title":"SuBSENSE: A Universal Change Detection Method With Local Adaptive Sensitivity","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":651,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; Polytechnique Montréal","funders":"Fonds de Recherche du Québec - Santé; Fonds de recherche du Québec – Nature et technologies; Université Laval","keywords":"Computer science; Artificial intelligence; Pixel; Segmentation; Background subtraction; Change detection; Computer vision; Noise (video); Sensitivity (control systems); Image segmentation; Frame (networking); Adaptation (eye); Frame rate; Analytics; Fidelity; Object detection; Pattern recognition (psychology); Image (mathematics); Data mining","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009869662,0.0002179807,0.0002288219,0.0002066181,0.0004458554,0.0001814398,0.0001659189,0.00008524246,0.000002913422],"category_scores_gemma":[0.000008357397,0.0001948786,0.00007176258,0.0008128394,0.0001168623,0.001325608,0.000002775443,0.0003669318,0.00001716488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009182678,"about_ca_system_score_gemma":0.00006868586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001531103,"about_ca_topic_score_gemma":0.0003712278,"domain_scores_codex":[0.998124,0.0005654758,0.0001499857,0.0005346447,0.0002940205,0.0003318931],"domain_scores_gemma":[0.9989626,0.0002884037,0.0001045227,0.0003283709,0.0002130772,0.0001030721],"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":[0.00008539109,0.00006688095,0.00000536312,0.00002688635,0.00001747278,0.00003294165,0.000739172,0.002227929,0.007350781,0.00004408103,7.307147e-7,0.9894024],"study_design_scores_gemma":[0.0005792085,0.0003299275,0.0005496033,0.00009964441,0.00003082776,0.0002186335,0.0001369597,0.7748713,0.2225111,0.0002332141,0.000109373,0.0003302374],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001849262,0.00001700774,0.9967939,0.0002505658,0.0002166079,0.0001520739,0.000002446812,0.0004066957,0.0003113919],"genre_scores_gemma":[0.660217,0.000002349047,0.3395346,0.0001451205,0.00004721167,0.00001514986,1.848125e-7,0.00001597346,0.00002240874],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9890721,"threshold_uncertainty_score":0.794692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02707902773261169,"score_gpt":0.2795606137100687,"score_spread":0.2524815859774571,"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."}}