{"id":"W2552818906","doi":"10.1109/cw.2016.40","title":"Occlusion Detection and Localization from Kinect Depth Images","year":2016,"lang":"en","type":"article","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer vision; Computer science; Occlusion; Face (sociological concept); Local binary patterns; RGB color model; Pixel; Facial recognition system; Orientation (vector space); Pattern recognition (psychology); Image (mathematics); Mathematics; Histogram","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":[0.00005263591,0.00004683552,0.00005102481,0.00006277386,0.00006606479,0.00006003018,0.00007558135,0.00002447128,0.0000925751],"category_scores_gemma":[0.00002545216,0.00002789639,0.00002091306,0.0001529376,0.00001371879,0.0003295749,0.00006711711,0.00001368148,0.00008502781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001188846,"about_ca_system_score_gemma":0.000004545127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001043636,"about_ca_topic_score_gemma":0.0001520164,"domain_scores_codex":[0.9995752,0.00002822155,0.00007038272,0.0001755516,0.00008533583,0.00006528233],"domain_scores_gemma":[0.9997448,0.00004310979,0.00002357937,0.0001109393,0.00003817918,0.0000393701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000001781731,0.0000109959,0.002772317,0.000001288114,0.000007774917,0.000001815706,0.00003136695,0.000005905191,0.09248656,0.0002552853,0.0002044956,0.9042204],"study_design_scores_gemma":[0.0008365947,0.00006933283,0.0419464,0.00004873204,0.00002284879,0.00001133887,0.0000340962,0.2893679,0.6542603,0.01000482,0.00309452,0.0003031291],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02137783,0.00002894426,0.9767208,0.0006261679,0.00005184532,0.00002352575,0.00000105804,0.0001157339,0.001054097],"genre_scores_gemma":[0.993578,0.0000895691,0.005726999,0.0002346043,0.00002014458,0.000001110362,0.000001048146,0.000002179636,0.000346403],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9722001,"threshold_uncertainty_score":0.1137582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008319057375487156,"score_gpt":0.216238190400125,"score_spread":0.2079191330246378,"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."}}