{"id":"W4389170666","doi":"10.1007/978-3-031-47969-4_33","title":"I Got Your Emotion: Emotion Preserving Face De-identification Using Injection-Based Generative Adversarial Networks","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Face recognition and analysis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Artificial intelligence; Face (sociological concept); Identification (biology); Adversarial system; Expression (computer science); Image (mathematics); Generative grammar; Generative adversarial network; Pattern recognition (psychology); Facial expression; Facial recognition system; Computer vision","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00122887,0.0004326129,0.0004051428,0.001101409,0.0006162988,0.001019186,0.001592496,0.0003880446,0.00003455105],"category_scores_gemma":[0.0001581126,0.0004530387,0.0002183842,0.001567743,0.0002645052,0.0008248728,0.0005317748,0.0006879812,0.00004744733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006681649,"about_ca_system_score_gemma":0.0006577716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009220705,"about_ca_topic_score_gemma":0.000115645,"domain_scores_codex":[0.9964229,0.0001334488,0.0005928819,0.001405401,0.000876896,0.0005684081],"domain_scores_gemma":[0.997748,0.0002898034,0.000458798,0.0008856441,0.000453897,0.0001638697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003002103,0.00001637645,0.00003111044,0.00001773473,0.00001732247,0.00001316218,0.000415292,0.9011028,0.0002806474,0.0009411848,0.00001413244,0.09714724],"study_design_scores_gemma":[0.0002228066,0.00005409212,0.0001473581,0.0002757859,0.00002745308,0.00001901929,0.000001623684,0.9755814,0.001029485,0.02217082,0.00002824416,0.000441895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002431602,0.00006625506,0.9955316,0.0006583388,0.002533722,0.0003378484,0.000007187004,0.0002997708,0.0003221093],"genre_scores_gemma":[0.6344884,0.00007273182,0.3595302,0.001539008,0.002702234,0.00002549497,0.0001156877,0.0001095233,0.001416744],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6360015,"threshold_uncertainty_score":0.9997922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03998592489892649,"score_gpt":0.2744935013076215,"score_spread":0.234507576408695,"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."}}