{"id":"W2894983638","doi":"10.1007/s00138-018-0983-2","title":"Two-stage local details restoration framework for face hallucination","year":2018,"lang":"en","type":"article","venue":"Machine Vision and Applications","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Hallucinating; Computer science; Artificial intelligence; Face hallucination; Computer vision; Image (mathematics); Position (finance); Residual; Constraint (computer-aided design); Locality; Face (sociological concept); Stage (stratigraphy); Pattern recognition (psychology); Face detection; Mathematics; Facial recognition system; Algorithm","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":[0.0001936266,0.00009857005,0.00008363031,0.0000798059,0.0003871761,0.0001582729,0.000300692,0.00004992441,0.000005347792],"category_scores_gemma":[0.00005814682,0.00008806992,0.00001902467,0.0002978444,0.000105377,0.000454592,0.0001216797,0.00008750928,0.00001621858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002681643,"about_ca_system_score_gemma":0.00002084659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007431803,"about_ca_topic_score_gemma":0.00001184441,"domain_scores_codex":[0.9992443,0.00001931209,0.0001591156,0.0003392395,0.0001137799,0.0001242534],"domain_scores_gemma":[0.9991938,0.00009525861,0.00009944132,0.0003962126,0.0001592681,0.00005595485],"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":[0.000004004153,0.00003366923,0.00001924922,0.00001113657,0.000001344567,6.695819e-8,0.00008628973,0.00001702811,0.003017302,0.4865282,0.0001354371,0.5101463],"study_design_scores_gemma":[0.0001834455,0.0001188411,0.000187038,0.00002037057,0.000003845292,0.000002476603,0.00001619136,0.7027783,0.006247559,0.2266944,0.06360807,0.0001393546],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009440753,0.000141707,0.9966126,0.001686129,0.00002790329,0.0004822089,0.000007441085,0.0003902368,0.0005573567],"genre_scores_gemma":[0.2860616,0.00001118345,0.7131726,0.000307528,0.00006324026,0.0002231692,0.00001118879,0.000007665246,0.0001418982],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7027614,"threshold_uncertainty_score":0.3591387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01662997987154306,"score_gpt":0.3646864681359201,"score_spread":0.348056488264377,"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."}}