{"id":"W4409284266","doi":"10.1007/s00138-025-01687-8","title":"Emotion-aware face de-identification with generative adversarial networks","year":2025,"lang":"en","type":"article","venue":"Machine Vision and Applications","topic":"Face recognition and analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Adversarial system; Generative grammar; Identification (biology); Face (sociological concept); Computer science; Artificial intelligence; Noma; Speech recognition; Telecommunications; Linguistics; Philosophy","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":[0.0001322956,0.00009218152,0.00009580731,0.0001199006,0.0003426585,0.0001940259,0.0002016715,0.00004231554,0.00001971658],"category_scores_gemma":[0.000006098822,0.00007292674,0.00003373775,0.0006687326,0.00003914916,0.0001535902,0.00007212898,0.00009192672,0.00001761717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002316628,"about_ca_system_score_gemma":0.00003564256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002673285,"about_ca_topic_score_gemma":0.00002827179,"domain_scores_codex":[0.9993057,0.0000470037,0.0001480847,0.0002995935,0.00009107358,0.0001085585],"domain_scores_gemma":[0.9994768,0.00004414985,0.00006011073,0.0002751258,0.00008131281,0.0000625244],"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":[0.00001384065,0.0002646413,0.002335923,0.00002451587,0.00009373873,0.000001147162,0.0003218045,0.01737994,0.001164185,0.1637124,0.003296487,0.8113914],"study_design_scores_gemma":[0.0003279053,0.00001877562,0.004642941,0.00001601904,0.00002654518,0.000002699201,0.00007703942,0.9816812,0.0003584657,0.001789557,0.01095135,0.0001074612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001150368,0.0001150351,0.9937234,0.003747774,0.00002950144,0.0002200269,0.00000761804,0.0001035843,0.0009026924],"genre_scores_gemma":[0.9884113,0.0001235747,0.00908066,0.0006589375,0.00004109868,0.0001230424,0.00007161031,0.000004426512,0.001485348],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9872609,"threshold_uncertainty_score":0.2973866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004380545785906225,"score_gpt":0.2584465745580697,"score_spread":0.2540660287721634,"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."}}