{"id":"W2164734564","doi":"10.1109/tpami.2007.1039","title":"Learning and Removing Cast Shadows through a Multidistribution Approach","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":138,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Robustness (evolution); Computer vision; Pixel; Shadow (psychology); Foreground detection; Mixture model; Statistical model; Gaussian; Gaussian process; Background subtraction; Pattern recognition (psychology)","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":[0.001084281,0.0002048062,0.0002981107,0.0002858139,0.0003668442,0.0001615306,0.0002128924,0.0000787767,0.00001554419],"category_scores_gemma":[0.00001575382,0.0001832976,0.000150542,0.001036639,0.00007106142,0.000302296,0.000008403516,0.0003921315,0.000005118349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003227425,"about_ca_system_score_gemma":0.00001023615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00131522,"about_ca_topic_score_gemma":0.0008380668,"domain_scores_codex":[0.9983853,0.0001492415,0.0003527489,0.0005854976,0.0002283424,0.0002988759],"domain_scores_gemma":[0.9991549,0.0002748363,0.0001120748,0.000285504,0.00006681566,0.0001059284],"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":[0.0000103693,0.00008415624,0.007800667,0.00001883711,0.0001966798,0.00001381306,0.0009252456,0.00786534,0.0003676727,0.0001194313,5.629181e-7,0.9825972],"study_design_scores_gemma":[0.0003154413,0.0003073935,0.02441251,0.00005591376,0.0004708039,0.0001628007,0.0006200321,0.8647041,0.1071806,0.0005626068,0.0003996716,0.0008080833],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01256249,0.0001879575,0.9866477,0.00009117523,0.0001016066,0.00009004673,0.000008673734,0.0001070104,0.0002033264],"genre_scores_gemma":[0.9643845,0.0003808631,0.03501235,0.0001145467,0.00001964475,0.000005591754,0.000005685911,0.000008596556,0.00006820476],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9817891,"threshold_uncertainty_score":0.7474661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02983047505234876,"score_gpt":0.3092939914860411,"score_spread":0.2794635164336924,"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."}}