{"id":"W2011347706","doi":"10.1109/tip.2015.2411436","title":"Utilizing Image Scales Towards Totally Training Free Blind Image Quality Assessment","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Image quality; Histogram; Pattern recognition (psychology); Mathematics; Computer vision; Image (mathematics); Feature detection (computer vision); Image texture; Redundancy (engineering); Image histogram; Image resolution; Image gradient; Image processing; Computer science","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002637897,0.0005773716,0.0006448706,0.0004078234,0.0008342997,0.002332012,0.00167663,0.0001782921,0.00004741075],"category_scores_gemma":[0.0001033368,0.000577896,0.0003079182,0.0009882423,0.0003428547,0.005714235,0.00004691886,0.0009205823,0.00007839243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004622637,"about_ca_system_score_gemma":0.001507525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001764945,"about_ca_topic_score_gemma":0.0000768563,"domain_scores_codex":[0.9948,0.0004989664,0.00107124,0.001175451,0.00148597,0.0009683712],"domain_scores_gemma":[0.996727,0.0001924212,0.0003955568,0.001355265,0.0008118154,0.0005179279],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001670982,0.001462575,0.000009455142,0.0005206622,0.0001370711,0.0002036472,0.01459351,0.0004719441,0.0886528,0.001227562,0.000855702,0.8916979],"study_design_scores_gemma":[0.01927497,0.001662508,0.002288242,0.001603629,0.000413217,0.0005344312,0.03506228,0.4161466,0.4842908,0.03052939,0.002109371,0.00608453],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005462565,0.0001277802,0.9712203,0.003286358,0.0007152483,0.0004154044,0.0000405326,0.000765727,0.01796605],"genre_scores_gemma":[0.5596309,0.00001065721,0.4393993,0.0005037221,0.0001066785,0.00007908847,0.000004403183,0.00004333332,0.0002218938],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8856134,"threshold_uncertainty_score":0.9996672,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.143524082091928,"score_gpt":0.3979265098533554,"score_spread":0.2544024277614274,"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."}}