{"id":"W4386141863","doi":"10.3390/electronics12173572","title":"Sub-Pixel Convolutional Neural Network for Image Super-Resolution Reconstruction","year":2023,"lang":"en","type":"article","venue":"Electronics","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Artificial intelligence; Bicubic interpolation; Convolutional neural network; Pixel; Feature (linguistics); Kernel (algebra); Image resolution; Pattern recognition (psychology); Iterative reconstruction; Interpolation (computer graphics); Convolution (computer science); Computation; Algorithm; Computer vision; Artificial neural network; Linear interpolation; Image (mathematics); Mathematics","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":[0.0003713697,0.0001393706,0.000130489,0.00009731733,0.0003380132,0.0001176809,0.0004531318,0.00007527728,0.000002393868],"category_scores_gemma":[0.0001072725,0.0001529159,0.00007392951,0.0007110268,0.00007819169,0.0009298627,0.0001229984,0.0002048265,0.00002739647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002055705,"about_ca_system_score_gemma":0.0001951056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.569648e-7,"about_ca_topic_score_gemma":0.000009169305,"domain_scores_codex":[0.9985114,0.00003884558,0.0002087716,0.0003918485,0.0001771802,0.0006719377],"domain_scores_gemma":[0.9992694,0.0001046412,0.0000902633,0.0002995823,0.0001845169,0.0000516284],"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":[0.00008128656,0.0000645478,0.0003271951,0.00007792481,0.00004509328,0.000008738254,0.0001465193,0.002966682,0.2368089,0.2110366,0.07127047,0.477166],"study_design_scores_gemma":[0.0002237634,0.0001313456,0.000203149,0.00001439142,0.000005420779,0.00008006224,0.000003137152,0.7911659,0.008088909,0.1799516,0.01992928,0.0002030197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006418639,0.001809252,0.9880372,0.001321741,0.0004306907,0.0002563185,0.000005071302,0.001631922,0.0000891243],"genre_scores_gemma":[0.03902689,0.0003572179,0.9593214,0.0002640081,0.000451727,0.0001891142,0.00006500531,0.00003514329,0.0002894389],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7881992,"threshold_uncertainty_score":0.6235731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0141280738140819,"score_gpt":0.2690271570725116,"score_spread":0.2548990832584297,"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."}}