{"id":"W4386159016","doi":"10.1109/icme55011.2023.00128","title":"Optimizing DNN based quality assessment metric for image compression: A novel rate control method","year":2023,"lang":"en","type":"article","venue":"","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Image quality; Image compression; Distortion (music); Coding (social sciences); Source code; Artificial intelligence; Metric (unit); Data compression; Bandwidth (computing); Data mining; Image (mathematics); Image processing; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001885176,0.001280529,0.0006147663,0.001051577,0.000273629,0.0010527,0.001403963,0.0006668806,0.001358453],"category_scores_gemma":[0.003969676,0.0003437934,0.0005543216,0.0006430154,0.0005896526,0.00158737,0.0008335729,0.001455434,0.0003753683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001283851,"about_ca_system_score_gemma":0.001287664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005868114,"about_ca_topic_score_gemma":0.00535109,"domain_scores_codex":[0.9989175,0.0001890398,0.00008358278,0.0002532413,0.0004950697,0.00006164701],"domain_scores_gemma":[0.9989317,0.0002831355,0.0001493249,0.0001095534,0.0004802308,0.00004603706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000257123,0.0001549994,0.001762228,0.0002428379,0.00009630257,0.0001286555,0.0001528797,0.3437095,0.0593454,0.01929966,0.003317964,0.5715324],"study_design_scores_gemma":[0.00001171053,0.00003746859,0.0002483648,0.00001433144,0.00001668235,0.00005969464,0.000008565222,0.9881306,0.00867422,0.001746466,0.001036428,0.00001544311],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005169403,0.0004654916,0.9925817,0.00009171635,0.00004567702,0.00006573264,0.00003624773,0.0003642743,0.001179762],"genre_scores_gemma":[0.3344246,0.001013431,0.6593376,0.0002352864,0.0001393522,0.000243346,0.0003121207,0.0003564729,0.003937745],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005868114,"threshold_uncertainty_score":0.01166791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1228985783435318,"score_gpt":0.4524937034081726,"score_spread":0.3295951250646408,"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."}}