{"id":"W4406203409","doi":"10.61091/jcmcc123-12","title":"A Text-Free Training Method for Generating Face Images Based on Chinese Text","year":2024,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Face recognition and analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Science Foundation of Heilongjiang Province; National Natural Science Foundation of China","keywords":"Computer science; Generator (circuit theory); Face (sociological concept); Artificial intelligence; Embedding; Image (mathematics); Generative adversarial network; Natural language processing; Construct (python library); Word (group theory); Pattern recognition (psychology); Semantics (computer science); Word embedding; Feature (linguistics); Feature extraction; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003718788,0.0008356248,0.0003426936,0.0004830479,0.0002523291,0.0002652419,0.0008026046,0.0005066258,0.006587475],"category_scores_gemma":[0.000915483,0.0002258223,0.0006038685,0.0003192021,0.0003462239,0.0006281934,0.0004684839,0.000802675,0.002192787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003493383,"about_ca_system_score_gemma":0.0003985167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001801734,"about_ca_topic_score_gemma":0.002796603,"domain_scores_codex":[0.9998412,0.00002503596,0.000007067222,0.00006060619,0.00004734761,0.0000187582],"domain_scores_gemma":[0.9997635,0.00007562337,0.00001788341,0.00006112795,0.00006908153,0.00001269758],"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":[0.0003485306,0.0001652957,0.001501729,0.0003055495,0.00009858468,0.0005040062,0.0001630791,0.1289567,0.1116495,0.01091825,0.01561399,0.7297748],"study_design_scores_gemma":[0.0000251288,0.000144587,0.0008100715,0.00001499954,0.00002822598,0.0003515603,0.00002303792,0.9201085,0.06843469,0.003709485,0.006327731,0.00002199518],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03517734,0.0003202902,0.9526072,0.0001944757,0.0002218361,0.0002602526,0.0005565048,0.004492135,0.006170039],"genre_scores_gemma":[0.4657577,0.0004705434,0.5047687,0.0004546242,0.0001495556,0.0005941055,0.002522272,0.000553507,0.02472895],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006587475,"threshold_uncertainty_score":0.02203733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02124322088521962,"score_gpt":0.3005436982128094,"score_spread":0.2793004773275897,"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."}}