{"id":"W2111484788","doi":"10.1109/rose.2011.6058545","title":"Improving alignment of faces for recognition","year":2011,"lang":"en","type":"article","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Pipeline (software); Landmark; Facial recognition system; Face (sociological concept); Feature extraction; Pattern recognition (psychology); Computer vision; Process (computing); Haar-like features; Similarity (geometry); Affine transformation; Face detection; Three-dimensional face recognition; Feature (linguistics); Task (project management); Image (mathematics)","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":[0.0001132499,0.00003815772,0.00006621938,0.00005502026,0.0000240764,0.00001292801,0.0001373785,0.00001678383,0.0001429747],"category_scores_gemma":[0.00001435528,0.00003121277,0.00006037056,0.00009153762,0.000009309925,0.0001716823,0.00003035351,0.0000113707,0.00002836818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005267118,"about_ca_system_score_gemma":0.000009505841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006053043,"about_ca_topic_score_gemma":0.000009659169,"domain_scores_codex":[0.9996177,0.000009362997,0.0001142486,0.0001161073,0.00006527802,0.00007730562],"domain_scores_gemma":[0.9997255,0.00001950961,0.00005637798,0.0001018983,0.00007006831,0.00002663216],"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":[0.000004433257,0.0001016048,0.0001143801,0.00003321225,0.0000346503,3.450542e-7,0.0006122331,0.000001040741,0.01367712,0.007119384,0.0003291023,0.9779725],"study_design_scores_gemma":[0.000399342,0.0001711806,0.0002138056,0.0000171512,0.00002735884,0.000001543301,0.0003557958,0.06103218,0.9198594,0.0173541,0.0004013502,0.0001667872],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01075334,0.00001060021,0.9818125,0.00007639993,0.00005260948,0.00008154064,0.000003407994,0.00004516508,0.007164474],"genre_scores_gemma":[0.6932424,0.000007826604,0.3062137,0.0001360617,0.000007908967,0.00001868028,0.000003262143,0.000002223867,0.0003679681],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9778057,"threshold_uncertainty_score":0.1565473,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06597402499990897,"score_gpt":0.2383015210308981,"score_spread":0.1723274960309891,"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."}}