{"id":"W2963420948","doi":"10.1109/tip.2018.2847421","title":"Deep Blur Mapping: Exploiting High-Level Semantics by Deep Neural Networks","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Australian Research Council; Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Artificial intelligence; Computer science; Convolutional neural network; Benchmark (surveying); Deep learning; Computer vision; Semantics (computer science); Segmentation; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004713507,0.001138605,0.000599623,0.0006462064,0.0002534641,0.0007525116,0.0009600862,0.0007443354,0.001016361],"category_scores_gemma":[0.001762045,0.0003637088,0.0005509247,0.0005160138,0.0003526063,0.001918613,0.0008898561,0.001429901,0.0003153813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007589,"about_ca_system_score_gemma":0.0005885931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006589622,"about_ca_topic_score_gemma":0.008309273,"domain_scores_codex":[0.9998177,0.0000369851,0.000009886872,0.00004378126,0.00005332069,0.00003839359],"domain_scores_gemma":[0.9996401,0.0001309,0.00005760427,0.0000602666,0.00008489693,0.00002635031],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004008,0.0002425889,0.002381394,0.0002007147,0.0001272789,0.0001643221,0.0001673524,0.4236894,0.04076724,0.01027511,0.003579448,0.5180043],"study_design_scores_gemma":[0.000005174346,0.00002755095,0.0002522665,0.000006480399,0.00001041935,0.00001692553,0.000009267086,0.98993,0.004148715,0.005208721,0.0003796537,0.000004926972],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08813938,0.001102102,0.9058289,0.0003212928,0.00006606802,0.00004576262,0.0002129885,0.002719858,0.001563647],"genre_scores_gemma":[0.8344168,0.0005959944,0.161918,0.0001854655,0.00004869895,0.00004442106,0.0005333739,0.0001157658,0.002141543],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006589622,"threshold_uncertainty_score":0.01310253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02427187580338026,"score_gpt":0.2688095685042937,"score_spread":0.2445376927009134,"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."}}