{"id":"W7129358542","doi":"10.1109/icipw68931.2025.11386224","title":"Learning Single-Image Super-Resolution In The Jpeg Compressed Domain","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Speedup; JPEG; Pipeline (software); Discrete cosine transform; Overhead (engineering); Quantization (signal processing); Transform coding; Bottleneck; Decoding methods; Deep learning","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001670543,0.0004245045,0.0004035073,0.0004656845,0.0007214845,0.001377713,0.00285221,0.000192178,0.00004643876],"category_scores_gemma":[0.0005097963,0.0003461385,0.0001240438,0.002506769,0.0005145094,0.001922766,0.001106002,0.001174006,0.00004032245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002683158,"about_ca_system_score_gemma":0.0002329649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000105538,"about_ca_topic_score_gemma":0.00005098623,"domain_scores_codex":[0.9958863,0.000955064,0.0007572319,0.0009934371,0.0005588118,0.000849118],"domain_scores_gemma":[0.9977523,0.0006011214,0.0001975607,0.001132598,0.0002562863,0.0000601541],"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":[0.0001585357,0.002247258,0.001440176,0.0006303213,0.00005831166,0.0002694394,0.02134873,0.001642148,0.3806403,0.1635773,0.01012666,0.4178608],"study_design_scores_gemma":[0.001087062,0.0003914405,0.001002194,0.0009325143,0.00002313424,0.00003237884,0.001750687,0.8359707,0.02187657,0.1071713,0.02905682,0.0007051384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001940486,0.001098342,0.9382483,0.009788518,0.0002797988,0.0005766558,8.600493e-7,0.0006447582,0.0474223],"genre_scores_gemma":[0.4847645,0.00004941579,0.5121683,0.001392718,0.00003884155,0.00004851358,0.000002501512,0.0000150332,0.001520186],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8343286,"threshold_uncertainty_score":0.9998991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01636139269561146,"score_gpt":0.287439332175859,"score_spread":0.2710779394802476,"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."}}