{"id":"W4206753990","doi":"10.23919/eusipco54536.2021.9616283","title":"End-to-End Generative Adversarial Face Hallucination Through Residual In Internal Dense Network","year":2021,"lang":"en","type":"article","venue":"2021 29th European Signal Processing Conference (EUSIPCO)","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia; Confederation College; Lakehead University","funders":"University of British Columbia","keywords":"Hallucinating; Discriminator; Artificial intelligence; Computer science; Face (sociological concept); Face hallucination; Residual; Pixel; Computer vision; Generator (circuit theory); Inpainting; Exploit; Pattern recognition (psychology); Image (mathematics); Facial recognition system; Face detection; Algorithm","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001026778,0.0005119338,0.0004942663,0.0001919547,0.0004207698,0.001367415,0.001605025,0.0001115738,0.0002662484],"category_scores_gemma":[0.0003901906,0.0005415618,0.00008138503,0.00146381,0.0001901524,0.00253011,0.001423471,0.0007886491,0.0001361977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002260766,"about_ca_system_score_gemma":0.001227354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003589257,"about_ca_topic_score_gemma":0.00008796564,"domain_scores_codex":[0.9951501,0.000905543,0.0007969574,0.001503341,0.0007924059,0.0008516924],"domain_scores_gemma":[0.9976024,0.0001564275,0.0004118411,0.0006563063,0.0009719994,0.0002010065],"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":[0.0001737645,0.0003332699,0.0004253628,0.0001492509,0.00005974433,0.002772232,0.01567804,0.006942772,0.06972872,0.01068919,0.002603311,0.8904443],"study_design_scores_gemma":[0.005388177,0.001214297,0.005571492,0.00671213,0.0001502241,0.001008281,0.002008314,0.707729,0.165643,0.0624077,0.03657461,0.005592764],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002395473,0.0007740332,0.9763094,0.001493705,0.0003093988,0.000265177,0.000007333103,0.0003714762,0.01807399],"genre_scores_gemma":[0.5370399,0.00003602474,0.4603444,0.0009784086,0.0004892056,0.00001827194,0.00002202542,0.00004827143,0.001023489],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8848516,"threshold_uncertainty_score":0.9997036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03458221915481585,"score_gpt":0.291294270939618,"score_spread":0.2567120517848022,"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."}}