{"id":"W2294368874","doi":"10.1109/icip.2015.7351748","title":"Saliency weighted quality assessment of tone-mapped images","year":2015,"lang":"en","type":"article","venue":"","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Tone mapping; Artificial intelligence; Ranking (information retrieval); Metric (unit); Image quality; Computer science; Tone (literature); Computer vision; High dynamic range; Quality (philosophy); Image (mathematics); Range (aeronautics); Judgement; Quality Score; Pattern recognition (psychology); Dynamic range","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":[0.0009930211,0.0001132396,0.0001972898,0.00008871189,0.00002705693,0.00006108793,0.0008447635,0.00003742865,0.00005047964],"category_scores_gemma":[0.00004426448,0.00009340953,0.00004739451,0.0003188745,0.00005665094,0.0006678708,0.0003821511,0.00007520935,0.00002000274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006903303,"about_ca_system_score_gemma":0.0001577754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001531903,"about_ca_topic_score_gemma":0.000005058317,"domain_scores_codex":[0.9985013,0.0001331702,0.0003614541,0.0002892445,0.0005072487,0.0002075587],"domain_scores_gemma":[0.9987018,0.00005031482,0.0001476259,0.0007449541,0.0002672041,0.00008809181],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009376608,0.0007763641,0.01212368,0.00006600271,0.00004359993,0.0000152917,0.0008339985,0.000003187562,0.1380844,0.742021,0.05845333,0.04756978],"study_design_scores_gemma":[0.0006289123,0.000314305,0.01754213,0.00002307906,0.000005810758,0.000003449538,0.00008656649,0.007976213,0.9437883,0.02579502,0.003473761,0.0003624169],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009803227,0.0000258507,0.8816578,0.0006441248,0.0001458695,0.0001673869,0.000001378295,0.00046915,0.1070852],"genre_scores_gemma":[0.5578674,0.000004110222,0.4409803,0.0001234967,0.00001260034,0.00001338433,0.000001586791,0.000003504686,0.0009936531],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8057039,"threshold_uncertainty_score":0.380913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0564457346565031,"score_gpt":0.3992333884117835,"score_spread":0.3427876537552804,"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."}}