{"id":"W4220959191","doi":"10.1016/j.displa.2022.102188","title":"Quality assessment of multi-exposure image fusion by synthesizing local and global intermediate references","year":2022,"lang":"en","type":"article","venue":"Displays","topic":"Advanced Image Fusion Techniques","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China","keywords":"Image quality; Domain (mathematical analysis); Artificial intelligence; Computer science; Perception; Image fusion; Human visual system model; Image (mathematics); Quality (philosophy); Fuse (electrical); Consistency (knowledge bases); Quality Score; Property (philosophy); Perspective (graphical); Computer vision; Pattern recognition (psychology); Fusion; Scale (ratio); Mathematics; Psychology; Engineering; Geography","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":[0.0002326219,0.0001253878,0.00019658,0.00002991365,0.00008101061,0.00001300638,0.0001538777,0.00003319159,0.0001003543],"category_scores_gemma":[0.00002501179,0.0001242797,0.00003429706,0.0001050199,0.00007809405,0.0001215778,0.0002290046,0.0001707339,8.839809e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001172535,"about_ca_system_score_gemma":0.00001129821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004114947,"about_ca_topic_score_gemma":0.00001496232,"domain_scores_codex":[0.9991226,0.00007277613,0.0002643284,0.0001750719,0.0002094044,0.0001558873],"domain_scores_gemma":[0.9996281,0.00006086606,0.00006615125,0.0001723742,0.00002313593,0.00004941216],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00005381418,0.0003131224,0.04224718,0.0006088061,0.00006487834,0.00003045834,0.0005975455,0.001752612,0.7447725,0.00127024,0.003024225,0.2052647],"study_design_scores_gemma":[0.002785877,0.0009844052,0.4313782,0.0003938507,0.00008991629,0.00005200853,0.008965527,0.3355164,0.2075673,0.002691742,0.0075324,0.002042346],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5567493,0.0005149009,0.4403425,0.00001853899,0.0001316927,0.0001622872,0.0004395875,0.0002565782,0.001384533],"genre_scores_gemma":[0.9862034,0.0001151714,0.01353594,0.00001876089,0.000006282234,0.00004448894,0.00004443526,0.00001400625,0.00001752693],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5372052,"threshold_uncertainty_score":0.506798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01520701213942007,"score_gpt":0.3088511164267696,"score_spread":0.2936441042873495,"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."}}