{"id":"W2142669007","doi":"10.1109/icassp.2009.4959723","title":"Component-wise pose normalization for pose-invariant face recognition","year":2009,"lang":"en","type":"article","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Normalization (sociology); Computer vision; Computer science; Facial recognition system; Invariant (physics); Pattern recognition (psychology); Three-dimensional face recognition; Component (thermodynamics); Face (sociological concept); Pose; Face detection; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002034693,0.0001210424,0.0001437559,0.0001597773,0.000146819,0.0001871046,0.0002702963,0.00005841078,0.0001329764],"category_scores_gemma":[0.00003988333,0.0001101889,0.0001220037,0.0003946941,0.00001056218,0.0006242006,0.00002890457,0.00004896846,0.0002403145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002852732,"about_ca_system_score_gemma":0.0000250795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001550655,"about_ca_topic_score_gemma":0.00001100479,"domain_scores_codex":[0.9990068,0.00004619961,0.0002385253,0.0003033292,0.0001810068,0.0002241063],"domain_scores_gemma":[0.9993432,0.00004821557,0.00008380842,0.0002300199,0.0001886901,0.000106089],"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":[0.00004477097,0.0006809451,0.00006322163,0.00003279104,0.00007493858,0.00001233322,0.0006669958,0.0005339505,0.0244045,0.03961256,0.01303687,0.9208361],"study_design_scores_gemma":[0.001799001,0.0003600436,0.001295545,0.00005531378,0.00006692944,0.00003205968,0.0001474706,0.9217064,0.03810893,0.02856394,0.007226162,0.00063822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00425575,0.00003029511,0.9856238,0.005039807,0.0001848834,0.0002464574,0.00001282491,0.0002731894,0.004332939],"genre_scores_gemma":[0.8436688,0.0001006822,0.1479926,0.006102694,0.0001668441,0.00002577785,0.0003352005,0.00001153325,0.001595794],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9211724,"threshold_uncertainty_score":0.4493374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02688457457050471,"score_gpt":0.2536719341695575,"score_spread":0.2267873595990528,"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."}}