{"id":"W4405906970","doi":"10.1109/tdsc.2024.3523289","title":"ADA-FInfer: Inferring Face Representations From Adaptive Select Frames for High-Visual-Quality Deepfake Detection","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Dependable and Secure Computing","topic":"Face recognition and analysis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Natural Science Foundation for Distinguished Young Scholars of Hunan Province; National Natural Science Foundation of China","keywords":"Computer science; Face (sociological concept); Quality (philosophy); Face detection; Artificial intelligence; Computer vision; Frame (networking); Facial recognition system; Machine learning; Human–computer interaction; Pattern recognition (psychology); Computer network","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":[0.0003133806,0.000233735,0.0002847184,0.0003001799,0.000672486,0.000557273,0.0001888878,0.0001398287,0.00002851558],"category_scores_gemma":[0.00002009301,0.0002346956,0.0001928445,0.0007026887,0.00003213156,0.0006085288,0.000008790675,0.000400541,0.0000276087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007262039,"about_ca_system_score_gemma":0.00006990542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006505971,"about_ca_topic_score_gemma":0.0006070302,"domain_scores_codex":[0.9981651,0.0001397894,0.0003906994,0.0007312999,0.0002542127,0.0003189312],"domain_scores_gemma":[0.998514,0.0009128258,0.00008329641,0.00023546,0.0001339379,0.000120484],"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":[0.00004867943,0.0002195441,0.00003170729,0.0001129142,0.0005786995,0.00001793694,0.002898513,0.1138339,0.00742152,0.002819881,0.00005998012,0.8719567],"study_design_scores_gemma":[0.0003520666,0.00015027,0.0001451845,0.0001183315,0.0000968722,0.00001135703,0.0003923956,0.9335641,0.0620326,0.002622989,0.0002203176,0.0002935348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.101702,0.0002443827,0.8963143,0.0002820323,0.000609377,0.0002477488,0.00005539457,0.0004792797,0.00006546955],"genre_scores_gemma":[0.9802532,0.0000634436,0.01929117,0.0001249632,0.00009719991,0.00003268343,0.00001355048,0.00002142138,0.0001023261],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8785512,"threshold_uncertainty_score":0.9570611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02537835622658948,"score_gpt":0.3025102243596083,"score_spread":0.2771318681330188,"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."}}