{"id":"W2776574544","doi":"10.1109/tci.2017.2786138","title":"Multi-Exposure Image Fusion by Optimizing A Structural Similarity Index","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Computational Imaging","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":200,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Similarity (geometry); Algorithm; Image (mathematics); Image fusion; Transformation (genetics); Convergence (economics)","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","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002123629,0.0002574078,0.000186938,0.0001810435,0.001597569,0.001041108,0.001114396,0.00005433186,0.00003276853],"category_scores_gemma":[0.00001175734,0.000274651,0.0001182862,0.0001234521,0.0001608776,0.002500524,0.00002423663,0.0004021027,0.00002358883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001223388,"about_ca_system_score_gemma":0.00006977939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007833658,"about_ca_topic_score_gemma":0.000009308567,"domain_scores_codex":[0.9982314,0.00006762244,0.0003055478,0.000565976,0.0004883223,0.0003411812],"domain_scores_gemma":[0.9986731,0.00009600053,0.000216104,0.0006791461,0.0002337232,0.0001019388],"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":[0.0001299422,0.001213473,0.002242566,0.0001424608,0.0002405998,0.0002413249,0.002303296,0.2223332,0.2246241,0.0008380548,0.006100802,0.5395902],"study_design_scores_gemma":[0.0007705562,0.00003446821,0.002732678,0.00004357574,0.000008282973,0.00002865157,0.00001408494,0.9495782,0.0455041,0.0008879399,0.00008083721,0.0003165932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008339728,0.00002531958,0.9883181,0.001649585,0.0006257319,0.0002509766,0.00003191151,0.0005293794,0.0002292236],"genre_scores_gemma":[0.6214077,0.0000031932,0.3780804,0.0003434874,0.00002232227,0.00001991047,0.000005231388,0.00001484992,0.0001029119],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.727245,"threshold_uncertainty_score":0.9999959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01568332375594261,"score_gpt":0.2937431099667134,"score_spread":0.2780597862107708,"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."}}