{"id":"W4283687192","doi":"10.1109/tip.2022.3184819","title":"Data Acquisition and Preparation for Dual-Reference Deep Learning of Image Super-Resolution","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Upsampling; Computer science; Artificial intelligence; Computer vision; Bicubic interpolation; Image resolution; Process (computing); Pixel; Image quality; Image (mathematics); Pattern recognition (psychology)","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":[],"consensus_categories":[],"category_scores_codex":[0.0005674188,0.0001833117,0.0001964304,0.0002450361,0.001145693,0.0002510254,0.0006055784,0.00004727225,0.00001510779],"category_scores_gemma":[0.00003552676,0.000209294,0.00003590637,0.0004758501,0.0001300631,0.003738749,0.00004790699,0.000347042,0.000001352045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009739096,"about_ca_system_score_gemma":0.0001153596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009084404,"about_ca_topic_score_gemma":0.000003803498,"domain_scores_codex":[0.9982308,0.0001144615,0.0003612149,0.0006822947,0.0003455788,0.0002656395],"domain_scores_gemma":[0.9987708,0.0001180151,0.0002542298,0.0005313545,0.0002729126,0.00005267488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002187941,0.0003318055,0.000004679087,0.0004389824,0.00001937283,0.000004921118,0.001817336,0.005259841,0.5583039,0.0002458916,0.00009137922,0.4332631],"study_design_scores_gemma":[0.0003905815,0.0003310759,0.00001509754,0.00006183927,0.00003044382,0.00005187203,0.000187069,0.9116879,0.08430857,0.002264437,0.0004395967,0.0002315495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001402662,0.0003283586,0.9969509,0.0002350309,0.0000844106,0.0003630451,0.00007037749,0.0004531977,0.0001119704],"genre_scores_gemma":[0.5058295,0.00002230209,0.4938533,0.00004096953,0.00001205222,0.0001466102,0.00003000846,0.00001665045,0.00004861112],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.906428,"threshold_uncertainty_score":0.8811859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03354670155997822,"score_gpt":0.3225540151899212,"score_spread":0.2890073136299429,"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."}}