{"id":"W2560998940","doi":"10.1109/crv.2016.51","title":"Genaralizing Generative Models: Application to Image Super-Resolution","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Receptive field; Computer science; Boltzmann machine; Generative model; Markov random field; Artificial intelligence; Restricted Boltzmann machine; Convolutional neural network; Scaling; Algorithm; Pattern recognition (psychology); Field (mathematics); Image (mathematics); Generative grammar; Artificial neural network; Mathematics; Image segmentation","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":[0.000141919,0.000106589,0.0000837764,0.00008838396,0.0001076932,0.00009368631,0.0005775781,0.00003270606,0.00000503594],"category_scores_gemma":[0.00003325101,0.00007241464,0.00002376712,0.000257236,0.00003240249,0.002103544,0.0002731825,0.00003480961,0.000104189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001060813,"about_ca_system_score_gemma":0.00002995024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001504837,"about_ca_topic_score_gemma":0.000004733199,"domain_scores_codex":[0.9990285,0.00002644766,0.0001482369,0.0004142842,0.0001610105,0.0002215272],"domain_scores_gemma":[0.9991978,0.00002667524,0.00003950304,0.0004881635,0.0001713267,0.00007646637],"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":[0.00000220915,0.00001430689,0.000004547565,0.00000245572,0.0000016346,7.563285e-7,0.0001875741,0.00007197725,0.7398831,0.128111,0.001702173,0.1300182],"study_design_scores_gemma":[0.00009436605,0.00003628951,0.00001514029,0.00001918108,0.000001174913,0.000005496324,0.000006529838,0.5138749,0.2915798,0.1918285,0.002349634,0.0001889801],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001912784,0.00004371502,0.9908649,0.00502646,0.00002872784,0.0002068453,0.000001143575,0.0009732482,0.002663706],"genre_scores_gemma":[0.1097088,0.000009861412,0.8889676,0.0007028208,0.00003670276,0.0001173431,5.856758e-7,0.00000911376,0.0004471805],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5138029,"threshold_uncertainty_score":0.2952983,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02459683277539483,"score_gpt":0.2908158909320845,"score_spread":0.2662190581566897,"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."}}