{"id":"W2973555408","doi":"10.1109/tip.2019.2940678","title":"Perceptual Evaluation for Multi-Exposure Image Fusion of Dynamic Scenes","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Fusion Techniques","field":"Engineering","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Ghosting; Artificial intelligence; High dynamic range; Computer science; Computer vision; Image quality; High-dynamic-range imaging; Dynamic range; Image fusion; Image (mathematics); Pattern recognition (psychology)","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":[0.0002497864,0.000234072,0.0002520274,0.0002520374,0.0001339957,0.00004763802,0.0001522608,0.0001144964,0.0002469244],"category_scores_gemma":[0.00001654984,0.0002421471,0.000121472,0.0002532221,0.0000732062,0.0007741373,0.000001615106,0.0002179912,0.00003080973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001487485,"about_ca_system_score_gemma":0.00005384139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003217849,"about_ca_topic_score_gemma":0.000008310014,"domain_scores_codex":[0.998746,0.0000296022,0.0003695049,0.000297198,0.0003038862,0.000253813],"domain_scores_gemma":[0.9991376,0.00005037218,0.00008668508,0.0002672523,0.0004088439,0.00004927173],"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":[0.00002981027,0.00007350407,0.000002904555,0.0003696939,0.000008508735,2.761018e-7,0.0003232157,0.005936491,0.691183,2.927423e-7,0.00001455592,0.3020578],"study_design_scores_gemma":[0.0007224273,0.00009563624,0.00008530346,0.0001859125,0.00004376631,0.000003848432,0.0003254887,0.5671986,0.4310748,0.00004674391,0.00002407892,0.0001933972],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.103476,0.0002168207,0.8943499,0.00001628985,0.0002660879,0.0008954189,0.0000475336,0.0005325354,0.0001994476],"genre_scores_gemma":[0.7222592,0.00005283686,0.2772976,0.0000123688,0.00001264286,0.0001462261,0.00001005096,0.00006750599,0.0001415766],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6187832,"threshold_uncertainty_score":0.9874472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01849546200157333,"score_gpt":0.306444510359755,"score_spread":0.2879490483581816,"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."}}