{"id":"W3190691568","doi":"10.1146/annurev-vision-100419-120301","title":"Quantifying Visual Image Quality: A Bayesian View","year":2021,"lang":"en","type":"review","venue":"Annual Review of Vision Science","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Vision science; Artificial intelligence; Image quality; Data science; Computer graphics; Image processing; Human visual system model; Quality (philosophy); Graphics; Bayesian probability; Bridging (networking); Machine vision; Human–computer interaction; Machine learning; Image (mathematics); Computer graphics (images)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005463286,0.001432844,0.002157922,0.006616935,0.0004018216,0.003294658,0.002756325,0.002687971,0.002714211],"category_scores_gemma":[0.01194993,0.0009369678,0.00108299,0.004078247,0.003665652,0.005613266,0.001770024,0.003379891,0.001304352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003010995,"about_ca_system_score_gemma":0.002506061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006989682,"about_ca_topic_score_gemma":0.00437639,"domain_scores_codex":[0.9977266,0.0006527889,0.0001636208,0.0003552086,0.001037458,0.00006420554],"domain_scores_gemma":[0.9938829,0.003967535,0.0003819555,0.0002561809,0.001393624,0.0001177677],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000547055,0.00004957941,0.00115955,0.005545058,0.0002934373,0.00009255642,0.0002048843,0.005895462,0.00171358,0.1472788,0.01277734,0.8249351],"study_design_scores_gemma":[0.00004122596,0.0002290807,0.006344718,0.008854553,0.0005843333,0.002754753,0.000358795,0.0215847,0.004703983,0.4364126,0.5178085,0.0003228534],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0008815225,0.8648311,0.117856,0.004746944,0.0004626289,0.00005557053,0.0001683387,0.0001433207,0.01085445],"genre_scores_gemma":[0.03346514,0.9089519,0.05102313,0.001839009,0.001354522,0.0001633293,0.0002421307,0.00007463909,0.00288627],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.006989682,"threshold_uncertainty_score":0.02889299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.112843283201557,"score_gpt":0.5393167826659025,"score_spread":0.4264734994643455,"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."}}