{"id":"W3014210955","doi":"10.1109/iceic49074.2020.9051244","title":"MSG-CapsGAN: Multi-Scale Gradient Capsule GAN for Face Super Resolution","year":2020,"lang":"en","type":"article","venue":"2020 International Conference on Electronics, Information, and Communication (ICEIC)","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Discriminator; Computer science; Face (sociological concept); Artificial intelligence; Computer vision; Image resolution; Scale (ratio); Facial recognition system; Distortion (music); Image (mathematics); Process (computing); High resolution; Resolution (logic); Pattern recognition (psychology); Bandwidth (computing); Telecommunications; Detector; Physics","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":[0.0003013235,0.0002061228,0.0001783771,0.000107866,0.0003576972,0.0004579073,0.001585038,0.00008911088,0.00002190398],"category_scores_gemma":[0.0001923079,0.0002162901,0.00006019324,0.0002209901,0.00009652023,0.002728191,0.0002384562,0.0003268228,0.00004207699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001864916,"about_ca_system_score_gemma":0.0002154876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002511835,"about_ca_topic_score_gemma":0.00003939488,"domain_scores_codex":[0.9985129,0.00006584766,0.0005257879,0.0002860484,0.0003259718,0.000283507],"domain_scores_gemma":[0.99816,0.00005823168,0.0003239941,0.0005431292,0.0007900673,0.000124598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001479781,0.0002088686,0.0001620114,0.0001040958,0.00009228746,4.179922e-7,0.0151066,0.0006177953,0.01074664,0.9019933,0.009141579,0.06167838],"study_design_scores_gemma":[0.0007439301,0.0002192242,0.0002544031,0.00004604319,0.000008177637,0.0000075242,0.0004330786,0.9179804,0.005818449,0.01290301,0.06129321,0.0002925898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007207319,0.0004290878,0.9696896,0.02484359,0.00008861836,0.0004445377,0.00003019441,0.0003513581,0.003402274],"genre_scores_gemma":[0.7505181,0.002508714,0.242356,0.003783891,0.00004781914,0.0002052303,0.0003987719,0.00001443169,0.0001669933],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9173626,"threshold_uncertainty_score":0.8820055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0360749793373332,"score_gpt":0.288467157043592,"score_spread":0.2523921777062588,"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."}}