{"id":"W3137456946","doi":"10.1111/cgf.14202","title":"Action Unit Driven Facial Expression Synthesis from a Single Image with Patch Attentive GAN","year":2021,"lang":"en","type":"article","venue":"Computer Graphics Forum","topic":"Face recognition and analysis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"China Scholarship Council","keywords":"Computer science; Facial expression; Generator (circuit theory); Expression (computer science); Artificial intelligence; Image synthesis; Encoder; Discriminator; Action (physics); Image (mathematics); Generative grammar; Computer vision; Pattern recognition (psychology); Power (physics); Programming language","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":[0.00007038347,0.000212268,0.0002630514,0.0002055705,0.0002882322,0.0004085398,0.0004435852,0.00009924991,0.00006100579],"category_scores_gemma":[0.00001493484,0.0001867571,0.0001961844,0.0008844944,0.00007565329,0.0006485924,0.0002771507,0.0002040566,0.00005887628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002556337,"about_ca_system_score_gemma":0.0000590105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006095419,"about_ca_topic_score_gemma":0.0002796793,"domain_scores_codex":[0.9983065,0.000162566,0.0002148037,0.0006155975,0.0003683458,0.0003322384],"domain_scores_gemma":[0.9987518,0.0001515005,0.0001310934,0.0005179215,0.0003055006,0.0001422246],"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":[0.0001376842,0.002902516,0.07095586,0.0001305791,0.001538866,0.001294148,0.004177263,0.000528605,0.2257684,0.008452449,0.01119689,0.6729168],"study_design_scores_gemma":[0.001438136,0.000280991,0.01169002,0.000640793,0.0001949977,0.00005932478,0.0008808375,0.5397262,0.4271503,0.006675311,0.009999346,0.001263764],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1354574,0.00002909466,0.8623335,0.001407532,0.0002828934,0.00007462808,0.00002808559,0.0001832674,0.0002035741],"genre_scores_gemma":[0.9211726,0.00004688508,0.07781413,0.0006650641,0.0001196906,0.00001927802,0.00007577628,0.00002009476,0.00006652331],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7857152,"threshold_uncertainty_score":0.7615734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02677676266141265,"score_gpt":0.2383389987990851,"score_spread":0.2115622361376724,"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."}}