{"id":"W2107109443","doi":"10.1109/iccv.1990.139627","title":"Matching range images of human faces","year":2002,"lang":"en","type":"article","venue":"","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":184,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Mathematics; Matching (statistics); Pattern recognition (psychology); Range (aeronautics); Gaussian; Computer vision; Computer science","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":[0.0005688673,0.0003539837,0.0007415748,0.002075639,0.0003479582,0.0009420454,0.0006268403,0.0009066473,0.005214211],"category_scores_gemma":[0.003973421,0.0004040629,0.0006363219,0.0009410416,0.0004901474,0.001660033,0.001177903,0.0004517288,0.001275457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003610448,"about_ca_system_score_gemma":0.0002525806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001181833,"about_ca_topic_score_gemma":0.0010783,"domain_scores_codex":[0.9992439,0.0001369686,0.00002495159,0.000257318,0.0002559869,0.00008096784],"domain_scores_gemma":[0.9995264,0.0001560325,0.00005606887,0.0001072043,0.0001218493,0.00003242573],"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":[0.0009224032,0.0001330707,0.002844624,0.0002562408,0.0001366008,0.0007469386,0.0005078381,0.03029291,0.1593725,0.02731136,0.007159688,0.7703159],"study_design_scores_gemma":[0.0001054004,0.0006249423,0.0249005,0.00008871494,0.0001272216,0.005063732,0.001193665,0.729661,0.1088726,0.114267,0.01494828,0.0001470189],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1763785,0.001007225,0.8082555,0.0003635392,0.0001443313,0.0002147592,0.0004164986,0.001489306,0.01173028],"genre_scores_gemma":[0.6608563,0.0007869878,0.3334324,0.0002084711,0.0001313841,0.00009975662,0.0007426023,0.0002524696,0.003489455],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005214211,"threshold_uncertainty_score":0.0174433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03635714811205545,"score_gpt":0.2865670021333295,"score_spread":0.250209854021274,"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."}}