{"id":"W2952627588","doi":"10.1609/aaai.v33i01.33019111","title":"Instance-Level Facial Attributes Transfer with Geometry-Aware Flow","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Face recognition and analysis","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Leverage (statistics); Face (sociological concept); Computer vision; Context (archaeology); Representation (politics); Pattern recognition (psychology)","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":[0.0003043478,0.0002681892,0.0003641062,0.0002167648,0.0001663632,0.0002921821,0.001672688,0.0001001587,0.0004284595],"category_scores_gemma":[0.00008163712,0.0001806764,0.0001749994,0.001413751,0.0001844651,0.0005993465,0.0001595394,0.0003159991,0.0003468901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004371595,"about_ca_system_score_gemma":0.0001207133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002365005,"about_ca_topic_score_gemma":0.00003015663,"domain_scores_codex":[0.9978736,0.00001430187,0.0004461007,0.0005822147,0.0006881814,0.0003956217],"domain_scores_gemma":[0.9985209,0.0000662055,0.0001560351,0.000310856,0.0008363122,0.0001097242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002326598,0.0004466118,0.003469914,0.0001225374,0.0001406281,0.000001918761,0.002236157,0.0005723058,0.04095975,0.5635846,0.0002473614,0.3879856],"study_design_scores_gemma":[0.000140016,0.0004596911,0.0005405563,0.000461273,0.00003989465,0.000008280726,0.00109221,0.1613219,0.812888,0.02203896,0.000427491,0.0005817722],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5445858,0.00002587154,0.4371518,0.006063761,0.0005370657,0.0008112809,0.00007990389,0.0002186645,0.01052586],"genre_scores_gemma":[0.9962319,0.00003414403,0.002677837,0.0002780721,0.00003640514,0.00001861623,0.000001872337,0.00001213982,0.0007090343],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7719282,"threshold_uncertainty_score":0.7367769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07835275067118748,"score_gpt":0.2599646286022749,"score_spread":0.1816118779310875,"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."}}