{"id":"W2108373964","doi":"10.1142/s0219467809003551","title":"PECSI: A PRACTICAL PERCEPTUALLY-ENHANCED COMPRESSION FRAMEWORK FOR STILL IMAGES","year":2009,"lang":"en","type":"article","venue":"International Journal of Image and Graphics","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Upsampling; Image compression; Computer science; Artificial intelligence; Computer vision; Quantization (signal processing); Image quality; Compression (physics); Data compression; Perception; Data compression ratio; Texture compression; Encoding (memory); Image (mathematics); Image processing","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":[],"consensus_categories":[],"category_scores_codex":[0.0005092408,0.0001234183,0.0001936262,0.0002011466,0.00007476353,0.0004403614,0.0005837805,0.00007046951,0.00001414893],"category_scores_gemma":[0.000519394,0.00009966168,0.0001523981,0.0001092281,0.00007170756,0.001423092,0.00008835784,0.0003383929,0.000001874176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002346385,"about_ca_system_score_gemma":0.00009609606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002403585,"about_ca_topic_score_gemma":5.213786e-7,"domain_scores_codex":[0.9985782,0.00007428994,0.0004353981,0.0001797446,0.0005670779,0.0001652779],"domain_scores_gemma":[0.9978242,0.0004777887,0.0003618706,0.0001551545,0.001070069,0.000110944],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005884146,0.001283868,0.000211659,0.00004168652,0.0003452656,0.0005216763,0.005558557,0.00002026036,0.06734036,0.7080832,0.02077611,0.1952289],"study_design_scores_gemma":[0.003348112,0.002106896,0.01979523,0.0006650105,0.00008969547,0.001187033,0.0009008615,0.007955913,0.03973894,0.9085603,0.01500448,0.000647501],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008838794,0.0002108563,0.9667009,0.02344825,0.0004904396,0.00008255291,0.0000068106,0.00001860133,0.0002028025],"genre_scores_gemma":[0.576158,0.0004362291,0.4202481,0.002807309,0.0003154978,0.000001633319,0.000001906083,0.000004475254,0.00002680689],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5673193,"threshold_uncertainty_score":0.4246415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03312077197588812,"score_gpt":0.3944696626569971,"score_spread":0.3613488906811089,"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."}}