{"id":"W4289260327","doi":"10.1016/j.cviu.2022.103524","title":"Wavelet-based multi-level generative adversarial networks for face aging","year":2022,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Face recognition and analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Generative grammar; Artificial intelligence; Face (sociological concept); Wavelet; Adversarial system; Computer science; Pattern recognition (psychology); Generative adversarial network; Machine learning; Computer vision; Deep learning","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":[0.0004093655,0.0001853029,0.0002248255,0.0002355168,0.001115787,0.0004712267,0.0003392857,0.00003486787,0.00003899593],"category_scores_gemma":[0.00001137522,0.0001793018,0.0001462073,0.0003699534,0.00005414028,0.0003912773,0.0004359006,0.0001864277,0.000002400011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000215857,"about_ca_system_score_gemma":0.00004649981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003736496,"about_ca_topic_score_gemma":0.000002941418,"domain_scores_codex":[0.9985569,0.0001437089,0.0002285995,0.0005250632,0.0002341354,0.0003116082],"domain_scores_gemma":[0.9992955,0.0002036611,0.0001072508,0.0002145846,0.00005607254,0.0001229026],"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":[0.0002449401,0.0008841813,0.00008835318,0.0001651819,0.0004604751,0.0001791041,0.005958536,0.1031577,0.008415183,0.06928897,0.04006902,0.7710884],"study_design_scores_gemma":[0.001910924,0.0001617011,0.00003142384,0.00002095048,0.00001473364,0.000008780798,0.0004725311,0.9953102,0.0002031853,0.0006220649,0.0009957835,0.0002476547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002417334,0.000076778,0.9969653,0.001702068,0.0005813989,0.0002369061,0.00001940984,0.0001222714,0.00005416211],"genre_scores_gemma":[0.4693855,0.00001216943,0.528502,0.001793274,0.0001201698,0.00002040616,0.00003860949,0.00001491622,0.000112971],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8921525,"threshold_uncertainty_score":0.8581842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08423428185763641,"score_gpt":0.2967172082141706,"score_spread":0.2124829263565342,"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."}}