{"id":"W2400826247","doi":"10.1109/icassp.2016.7472109","title":"Multiview learning via deep discriminative canonical correlation analysis","year":2016,"lang":"en","type":"article","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Discriminative model; Canonical correlation; Artificial intelligence; Computer science; Pattern recognition (psychology); Correlation; Transformation (genetics); Class (philosophy); Deep learning; Speech recognition; 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":[0.0001447944,0.00007069243,0.0001134798,0.0001156755,0.00009306612,0.00003795182,0.0001775096,0.00004114772,0.0003243426],"category_scores_gemma":[0.00007567449,0.00003988237,0.00008648578,0.000414833,0.00002216277,0.0005067258,0.00009325419,0.00006183913,0.0003646228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002975822,"about_ca_system_score_gemma":0.00001391689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005821371,"about_ca_topic_score_gemma":0.0001076621,"domain_scores_codex":[0.9992176,0.0001073066,0.0001339177,0.0002442757,0.0001591452,0.0001377782],"domain_scores_gemma":[0.9994491,0.0001974513,0.0000601291,0.0001618064,0.00007019108,0.00006135557],"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":[0.00000483552,0.00005107425,0.009396725,0.000003415693,0.00009422281,0.000004092366,0.0006704637,0.0006118128,0.003807179,0.004268595,0.0002029485,0.9808846],"study_design_scores_gemma":[0.0005105105,0.00008866579,0.04856285,0.00005383508,0.0001318892,0.000003253244,0.0001013996,0.9394213,0.006493151,0.002098329,0.00223753,0.0002972674],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009063512,0.00002364061,0.985872,0.000812993,0.00007487482,0.00005024137,3.292659e-7,0.0001061462,0.003996317],"genre_scores_gemma":[0.9828765,0.00002165226,0.01486242,0.00009297058,0.0000129389,0.000009835131,0.000003768541,0.000002675976,0.002117241],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9805874,"threshold_uncertainty_score":0.468661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01189760766001188,"score_gpt":0.2501691680244258,"score_spread":0.238271560364414,"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."}}