{"id":"W2278490765","doi":"10.1109/tip.2016.2526910","title":"Data-Driven Soft Decoding of Compressed Images in Dual Transform-Pixel Domain","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Fundamental Research Funds for the Central Universities; Major State Basic Research Development Program of China; National Natural Science Foundation of China","keywords":"JPEG; Discrete cosine transform; Artificial intelligence; Computer science; Pixel; Computer vision; Quantization (signal processing); Decoding methods; Transform coding; Iterative reconstruction; Image restoration; Data compression; Compression artifact; Pattern recognition (psychology); Image compression; Image processing; Image (mathematics); Algorithm","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":[0.0005908264,0.0005371558,0.0006054487,0.0003520172,0.0002409028,0.0007419034,0.000569158,0.0007755447,0.001775183],"category_scores_gemma":[0.003349847,0.0002269014,0.000282414,0.0003824508,0.0006881419,0.0008094384,0.0009712828,0.0009672974,0.0007338494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003457799,"about_ca_system_score_gemma":0.0009324102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001324043,"about_ca_topic_score_gemma":0.002387815,"domain_scores_codex":[0.9995236,0.00008749348,0.00002632403,0.00008255924,0.0002306888,0.00004935539],"domain_scores_gemma":[0.9988396,0.0005921631,0.0001006777,0.0001633107,0.0002586455,0.0000456414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008677458,0.0001787512,0.001186925,0.000406045,0.00008082222,0.0004939473,0.00032578,0.3979195,0.1410655,0.05669056,0.003587118,0.3971974],"study_design_scores_gemma":[0.00001716074,0.00005432069,0.0001399944,0.00001671021,0.000008377152,0.0001198281,0.00002430839,0.9612569,0.02970412,0.007645115,0.001002093,0.00001112103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03000491,0.0002109024,0.9666901,0.0002403265,0.00006830934,0.00003361737,0.000077167,0.0004525937,0.00222205],"genre_scores_gemma":[0.5871225,0.0003871713,0.4042284,0.0003253414,0.0001121803,0.0001065618,0.0004226818,0.000185072,0.007110051],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001775183,"threshold_uncertainty_score":0.00593853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03864517759502456,"score_gpt":0.3120226260947185,"score_spread":0.273377448499694,"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."}}