{"id":"W2165927991","doi":"10.1109/avss.2008.19","title":"Evaluation of Background Subtraction Algorithms with Post-Processing","year":2008,"lang":"en","type":"article","venue":"","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":189,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Background subtraction; Computer science; Segmentation; Popularity; Artificial intelligence; Video processing; Computer vision; Image processing; Algorithm; Image segmentation; Image (mathematics); Pixel","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":[0.002018232,0.00007302679,0.0001061745,0.00007371543,0.0001013937,0.00003280597,0.000188532,0.00003246398,0.00002106543],"category_scores_gemma":[0.00004486447,0.0000549894,0.0000248859,0.000351128,0.00004025036,0.0007792668,0.00002202196,0.00006117898,0.000008971184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003878208,"about_ca_system_score_gemma":0.0002772845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008962696,"about_ca_topic_score_gemma":0.00003800987,"domain_scores_codex":[0.998576,0.0001707784,0.000147983,0.0002084774,0.0007599312,0.0001367597],"domain_scores_gemma":[0.9985689,0.00006145641,0.0001035865,0.0002475535,0.0009850899,0.00003341333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000112251,0.0000950481,0.005484592,0.00001439911,0.00002352576,0.000007219105,0.0006155309,0.001122606,0.002391471,0.0009583563,0.00004483314,0.9892312],"study_design_scores_gemma":[0.001216853,0.0003650956,0.5661801,0.000044277,0.00004194996,0.0003816866,0.000189106,0.4041198,0.02497721,0.001884749,0.0002809582,0.0003182162],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2724534,0.00008747957,0.7224883,0.0001721479,0.00009025435,0.00006995609,2.356213e-7,0.00006721257,0.004570995],"genre_scores_gemma":[0.7725759,0.000006592523,0.2272709,0.00006202835,0.00002708436,0.000003867871,0.00000121561,0.00000392762,0.00004847371],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.988913,"threshold_uncertainty_score":0.2242402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1206932855900337,"score_gpt":0.3496764280950583,"score_spread":0.2289831425050246,"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."}}