{"id":"W2940838882","doi":"10.1109/btas.2018.8698589","title":"From Hard to Soft Biometrics Through DNN Transfer Learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Xunta de Galicia; Ministerio de Economía y Competitividad; AGE-WELL","keywords":"Biometrics; Computer science; Inference; Face (sociological concept); Cluster analysis; Artificial intelligence; Facial recognition system; Transfer of learning; Task (project management); Pattern recognition (psychology); Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001089896,0.00008238319,0.0001161781,0.0002268105,0.0001146711,0.0001824961,0.0003816586,0.00004056935,0.001118636],"category_scores_gemma":[0.00006745343,0.00006875793,0.00007837554,0.002050223,0.00002487793,0.0003106783,0.00007025481,0.0000710367,0.003640946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001645066,"about_ca_system_score_gemma":0.00001861307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000214716,"about_ca_topic_score_gemma":0.00002814286,"domain_scores_codex":[0.9991253,0.00003360064,0.0001273175,0.0003108416,0.0002161489,0.0001867688],"domain_scores_gemma":[0.999492,0.00007796565,0.00001009533,0.000215717,0.0001084655,0.00009570656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000008348034,0.000152087,0.001379969,0.000006800333,0.000163202,0.00001092198,0.007342327,0.0001570236,0.02517429,0.00712701,0.02053237,0.9379457],"study_design_scores_gemma":[0.0008100951,0.0004811634,0.002053112,0.0000395629,0.00005546699,0.000003837725,0.0007042937,0.1378079,0.1567315,0.005959413,0.6944846,0.0008690581],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04049559,0.00001948475,0.9489889,0.002440286,0.0001759597,0.00003547895,0.000002197706,0.000210671,0.007631477],"genre_scores_gemma":[0.8206205,0.00001703159,0.1707305,0.003518985,0.0002160363,0.000003908387,0.000005447504,0.00000787814,0.004879769],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9370766,"threshold_uncertainty_score":0.9997945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03918849240135464,"score_gpt":0.2743983535220023,"score_spread":0.2352098611206476,"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."}}