{"id":"W3011133065","doi":"10.1109/tcsvt.2020.2980571","title":"PEA265: Perceptual Assessment of Video Compression Artifacts","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"Computer science; Video quality; Artificial intelligence; Mean opinion score; Coding (social sciences); Encoder; Video compression picture types; Motion compensation; Computer vision; Data compression; Convolutional neural network; Pattern recognition (psychology); Video processing; Metric (unit); Video tracking; Mathematics; Statistics","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":[0.0003108407,0.0002300008,0.0005115145,0.0002940684,0.0002620539,0.0001007679,0.0005485916,0.000201711,0.00001262084],"category_scores_gemma":[0.00001703035,0.0002093968,0.0001277178,0.0004591601,0.0001374897,0.0003468712,0.00001175905,0.0003105484,0.00001018233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005555758,"about_ca_system_score_gemma":0.000113917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004271354,"about_ca_topic_score_gemma":0.000006676342,"domain_scores_codex":[0.9980121,0.0001115843,0.000604113,0.0006010274,0.000324014,0.0003471418],"domain_scores_gemma":[0.9987137,0.0002160218,0.0002216407,0.0005191414,0.0001817461,0.0001477118],"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":[0.00008870845,0.001642093,0.0006205217,0.00268245,0.0006814146,0.00006656271,0.006132118,0.01217029,0.3520432,0.1692092,0.004389634,0.4502738],"study_design_scores_gemma":[0.006361233,0.006937186,0.001242421,0.0009141867,0.0002543536,0.0002581355,0.005647533,0.7540113,0.1851817,0.003016114,0.03437123,0.001804557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0233417,0.0001985013,0.9714246,0.003233971,0.0005277934,0.0007305059,0.00004236417,0.0003186855,0.0001818522],"genre_scores_gemma":[0.9967281,0.0000486126,0.002504361,0.0004298244,0.00003811296,0.0001753904,0.000001885806,0.00001821203,0.00005554086],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9733863,"threshold_uncertainty_score":0.8538954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05623126438343886,"score_gpt":0.3149737229336074,"score_spread":0.2587424585501685,"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."}}