{"id":"W4392908914","doi":"10.1109/icassp48485.2024.10447233","title":"Boosting Image Quality Assessment Performance: Unsupervised Score Fusion by Deep Maximum a Posteriori Estimation","year":2024,"lang":"en","type":"article","venue":"","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of Waterloo","funders":"","keywords":"Computer science; Boosting (machine learning); Artificial intelligence; A priori and a posteriori; Machine learning; Maximum a posteriori estimation; Strengths and weaknesses; Image quality; Process (computing); Quality (philosophy); Image fusion; Pattern recognition (psychology); Image (mathematics); Fusion; Quality Score; Data mining; Statistics; Maximum likelihood; Mathematics; Engineering; Metric (unit)","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001373354,0.0002583154,0.0002475016,0.0001336514,0.0002954284,0.001401975,0.0006276575,0.00008391008,0.0001711335],"category_scores_gemma":[0.00003485388,0.0002203763,0.0001075471,0.0005082306,0.00004419216,0.002655011,0.0004808056,0.0002776922,0.0001840099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002212655,"about_ca_system_score_gemma":0.000215594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001453142,"about_ca_topic_score_gemma":0.000007552233,"domain_scores_codex":[0.9973831,0.0002075427,0.0005985562,0.0006676367,0.0007014463,0.0004417839],"domain_scores_gemma":[0.9988188,0.0001765747,0.00008841547,0.0006534491,0.000131747,0.0001310281],"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":[0.00001537703,0.000231955,0.001257086,0.001081189,0.00005316641,0.00005550512,0.002518197,0.0001057006,0.08408663,0.01630328,0.004625196,0.8896667],"study_design_scores_gemma":[0.0003583377,0.0001886485,0.007297111,0.0002076698,0.00001546502,0.00002435574,0.0002118121,0.9777122,0.01062975,0.001677112,0.001256645,0.0004208813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1158748,0.000215612,0.8730855,0.00260708,0.0005399875,0.0003093422,0.000006098323,0.0006571054,0.006704431],"genre_scores_gemma":[0.7639288,0.00004218644,0.2343432,0.0008779696,0.00007110019,0.00004031828,0.00006058594,0.00001978687,0.0006160687],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9776065,"threshold_uncertainty_score":0.9996347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03613297461971213,"score_gpt":0.3434529637545939,"score_spread":0.3073199891348818,"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."}}