{"id":"W2112651331","doi":"10.1109/cvpr.2005.116","title":"Creating Invariance to \"Nuisance Parameters\" in Face Recognition","year":2005,"lang":"en","type":"article","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Artificial intelligence; Feature vector; Facial recognition system; Pattern recognition (psychology); Face (sociological concept); Invariant (physics); Feature (linguistics); Computer vision; Computer science; Manifold (fluid mechanics); Metric (unit); Position (finance); Pose; Mathematics; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001605818,0.0005783751,0.000689648,0.0006896365,0.0003878026,0.000679364,0.0008713483,0.0008975891,0.001628184],"category_scores_gemma":[0.01038024,0.0003825942,0.0006908597,0.0006517253,0.001910367,0.002072895,0.001395027,0.00127298,0.001020127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003938572,"about_ca_system_score_gemma":0.0003020896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006898738,"about_ca_topic_score_gemma":0.0006369438,"domain_scores_codex":[0.9986132,0.0004689889,0.00006181671,0.0003485552,0.0003946951,0.0001126353],"domain_scores_gemma":[0.9956929,0.001817665,0.0003832993,0.001710415,0.0002960023,0.00009977649],"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":[0.0003395524,0.0001982729,0.003952892,0.0001498557,0.00009052885,0.0002325134,0.0004039443,0.07168823,0.1569953,0.0266728,0.002003073,0.7372731],"study_design_scores_gemma":[0.0000523538,0.0005660394,0.0126107,0.00003973538,0.00009137485,0.001788422,0.0001410423,0.7254715,0.1824964,0.06545989,0.01111067,0.0001717892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05490605,0.0002603521,0.9424864,0.0001715888,0.00004812624,0.00005426621,0.00006624417,0.0006263197,0.001380566],"genre_scores_gemma":[0.5658755,0.0005075278,0.430491,0.0001735636,0.0001473799,0.0001633448,0.0002689517,0.0002926379,0.002080031],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001628184,"threshold_uncertainty_score":0.008492529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03643778383574562,"score_gpt":0.2651174559778315,"score_spread":0.2286796721420859,"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."}}