{"id":"W2604117447","doi":"10.1109/iccv.2017.403","title":"Temporal Non-volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition","year":2017,"lang":"en","type":"article","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Landmark; Artificial intelligence; Probabilistic logic; Generative model; Face (sociological concept); Invariant (physics); Embedding; Generative grammar; Inference; Pattern recognition (psychology); Deep learning; Algorithm; Machine learning; 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00036854,0.0001677094,0.0002285697,0.0001365097,0.0006683267,0.001403988,0.0008295561,0.00009176956,0.00005373521],"category_scores_gemma":[0.0001063249,0.0001405226,0.00007895646,0.0001513191,0.00005834726,0.0009659086,0.0007583935,0.0001297724,0.0001925596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001885682,"about_ca_system_score_gemma":0.00002660884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002810588,"about_ca_topic_score_gemma":0.00009120064,"domain_scores_codex":[0.9985718,0.00006017092,0.0002136471,0.0005672466,0.000296053,0.0002911531],"domain_scores_gemma":[0.9988762,0.00001628174,0.000128219,0.0006574797,0.00007726219,0.0002445793],"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":[0.00002647512,0.0003674845,0.00442843,0.00009820829,0.00008828891,0.0001339092,0.002543697,0.00005589719,0.003872553,0.0007276789,0.009473801,0.9781836],"study_design_scores_gemma":[0.002145378,0.0003224517,0.06478714,0.0003137019,0.0000851307,0.00005647359,0.0007684375,0.9021066,0.006216559,0.004907344,0.01666166,0.001629145],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05604679,0.00001794246,0.873745,0.00233556,0.0001979511,0.0004100605,0.00001148167,0.0001943804,0.06704079],"genre_scores_gemma":[0.8235843,0.00001383056,0.1704502,0.0003056223,0.00008473684,0.00003780727,0.00002787886,0.000009912931,0.005485763],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9765545,"threshold_uncertainty_score":0.9996327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04963075832118821,"score_gpt":0.2902676788491917,"score_spread":0.2406369205280035,"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."}}