{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008723297,0.0002027743,0.0003160843,0.0002804866,0.0003250741,0.000877953,0.0002022869,0.0001001024,9.180131e-7],"category_scores_gemma":[0.00006029819,0.0001721309,0.0000353351,0.0004625817,0.00003631018,0.0008972238,0.00001421652,0.0006802877,3.871769e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001474372,"about_ca_system_score_gemma":0.00008333926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006942222,"about_ca_topic_score_gemma":0.000006607713,"domain_scores_codex":[0.9981235,0.000200241,0.0005982764,0.0004137749,0.0003046501,0.0003595074],"domain_scores_gemma":[0.9993465,0.0001170598,0.000145172,0.0001578617,0.0001138823,0.0001195513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003611003,0.00002701714,0.0000779398,0.0003141304,0.00001861547,0.00005626354,0.00233823,0.0002591531,0.8935487,0.0003361998,0.00003906827,0.102981],"study_design_scores_gemma":[0.0006372199,0.0002049136,0.0008664945,0.006668624,0.00002439485,0.001187915,0.0003306514,0.9299961,0.05472261,0.002851066,0.001732273,0.0007777209],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3576151,0.003983259,0.637131,0.0001858264,0.0006901638,0.0001050509,0.000001672908,0.000138865,0.0001490338],"genre_scores_gemma":[0.9923985,0.000579657,0.006725633,0.00004010835,0.0001432366,0.000003768624,0.000001125182,0.00001621939,0.00009175456],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.929737,"threshold_uncertainty_score":0.846612,"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."}}