{"id":"W4293192750","doi":"10.1109/access.2022.3160828","title":"Masked Face Recognition From Synthesis to Reality","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Face recognition and analysis","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Ministry of Science and Technology, Taiwan; Ministry of Education, India; University of Calgary","keywords":"Softmax function; Computer science; Facial recognition system; Artificial intelligence; Face (sociological concept); Pattern recognition (psychology); Margin (machine learning); Benchmark (surveying); Embedding; Feature (linguistics); Computer vision; Deep learning; Speech recognition; Machine 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000279043,0.0001009126,0.0001588488,0.0001560235,0.0002709176,0.0002904963,0.00122374,0.00002473672,0.001213384],"category_scores_gemma":[0.00009298568,0.0001069819,0.00009266773,0.000869749,0.00001048078,0.0005331335,0.0004079942,0.0001220566,0.0003870672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007647809,"about_ca_system_score_gemma":0.00003329703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008798565,"about_ca_topic_score_gemma":0.00007766468,"domain_scores_codex":[0.9986123,0.0002110328,0.0001906836,0.0004349446,0.0003576833,0.0001933544],"domain_scores_gemma":[0.9990846,0.0002166287,0.00007790964,0.0004418818,0.00005959111,0.0001194235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004012029,0.0003357453,0.0009434954,0.00001621611,0.0001521762,0.00005851522,0.001218253,0.003578477,0.00689378,0.0001589133,0.04178675,0.9448175],"study_design_scores_gemma":[0.001747003,0.0003351201,0.03286142,0.0002269903,0.000442361,0.00004414862,0.002169994,0.2400183,0.5316272,0.07341114,0.1129707,0.00414561],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3318089,0.00002644207,0.6529689,0.009671224,0.0008921652,0.0002472282,0.0003508638,0.0003882402,0.003645954],"genre_scores_gemma":[0.9942747,0.00001010582,0.003026355,0.00221632,0.00006486121,0.0001740955,0.00002343241,0.000007962914,0.0002021182],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.940672,"threshold_uncertainty_score":0.9996997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0833087369586954,"score_gpt":0.3128499044629806,"score_spread":0.2295411675042852,"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."}}