{"id":"W4395097710","doi":"10.1109/jetcas.2024.3392868","title":"Enhancing Image Quality by Reducing Compression Artifacts Using Dynamic Window Swin Transformer","year":2024,"lang":"en","type":"article","venue":"IEEE Journal on Emerging and Selected Topics in Circuits and Systems","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Computer vision; Image compression; Compression artifact; Data compression; Pixel; Image quality; Transformer; Image processing; Engineering; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002795372,0.0005721306,0.0003828036,0.0005559543,0.0001377992,0.0004640911,0.0005179365,0.0002905894,0.001583022],"category_scores_gemma":[0.00093554,0.0001429816,0.0003502534,0.000311602,0.0002892896,0.0008660932,0.0005967942,0.0005519129,0.0003550569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003356028,"about_ca_system_score_gemma":0.0003631983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001739188,"about_ca_topic_score_gemma":0.002812173,"domain_scores_codex":[0.9998592,0.00001428632,0.00000783413,0.0000264072,0.00007472646,0.00001749786],"domain_scores_gemma":[0.9997048,0.00007278835,0.00005510604,0.00004600455,0.00009821419,0.00002320205],"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":[0.0004330034,0.0001738514,0.00155347,0.0001758874,0.00007467984,0.0002186979,0.00009408905,0.0473845,0.3380243,0.00321392,0.002573394,0.6060802],"study_design_scores_gemma":[0.00002888417,0.0002791636,0.003041234,0.00002909367,0.00009956979,0.0005112016,0.00004782416,0.7110154,0.277997,0.002148431,0.004773319,0.00002884981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1151778,0.0009726794,0.8786904,0.0001715202,0.00007875545,0.00007619341,0.00009573003,0.001889903,0.002847127],"genre_scores_gemma":[0.7471823,0.001156595,0.2459434,0.0002734442,0.00006997572,0.00005845837,0.0003088828,0.0003009588,0.004706064],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001739188,"threshold_uncertainty_score":0.005295694,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02602552822990455,"score_gpt":0.3309684342398261,"score_spread":0.3049429060099216,"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."}}