{"id":"W3151671170","doi":"10.1109/tbc.2021.3068862","title":"UPDResNN: A Deep Light-Weight Image Upsampling and Deblurring Residual Neural Network","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Broadcasting","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Deblurring; Upsampling; Residual; Computer science; Artificial intelligence; Block (permutation group theory); Benchmark (surveying); Image restoration; Artificial neural network; Computer vision; Image (mathematics); Pattern recognition (psychology); Image processing; Algorithm; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.0002340116,0.0002698976,0.0002472717,0.0001321765,0.0008152393,0.000469451,0.0004038097,0.00008983006,0.00001189957],"category_scores_gemma":[0.00006704815,0.0002920906,0.00006060591,0.001037625,0.0000642254,0.001211475,0.00002700501,0.0005389838,0.00000827366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006173618,"about_ca_system_score_gemma":0.00008487154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008343669,"about_ca_topic_score_gemma":0.00001700601,"domain_scores_codex":[0.9979597,0.00009376834,0.0003611735,0.0007313166,0.0002798407,0.0005741509],"domain_scores_gemma":[0.9987357,0.0002120869,0.0001201092,0.0005087588,0.0002769098,0.0001464744],"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":[0.00005231048,0.0002252718,0.0001188742,0.0001882468,0.00008468665,0.0006892896,0.002264093,0.07892046,0.09894869,0.0009970957,0.0002755585,0.8172354],"study_design_scores_gemma":[0.000400226,0.00007740172,0.00005697042,0.000327818,0.00002956975,0.000603333,0.00007125529,0.8545336,0.1402998,0.002530991,0.0005466401,0.0005225065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003643752,0.0007341252,0.9930262,0.0005763106,0.0005261833,0.0001188095,0.000001655665,0.0009333654,0.0004396139],"genre_scores_gemma":[0.2365917,0.00004772547,0.7627507,0.000288345,0.0001651948,0.00002770387,6.853297e-7,0.00003392006,0.00009410039],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8167129,"threshold_uncertainty_score":0.9999532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01704015729329238,"score_gpt":0.2621407453221894,"score_spread":0.245100588028897,"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."}}