{"id":"W2118788844","doi":"10.1109/83.855428","title":"A perceptually lossless, model-based, texture compression technique","year":2000,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Lossless compression; Artificial intelligence; Computer science; Computer vision; Pattern recognition (psychology); Data compression; Texture compression; Wavelet; Image compression; Texture synthesis; Binary code; Texture filtering; Binary number; Image texture; Binary image; Wavelet transform; Mathematics; Image processing; Image (mathematics)","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"],"consensus_categories":[],"category_scores_codex":[0.0001834462,0.0002678687,0.0002022276,0.000317841,0.000566064,0.0005117815,0.0007673028,0.0001486697,0.0001158647],"category_scores_gemma":[0.000001195124,0.0002537948,0.0001316856,0.0007697158,0.00011045,0.0009340334,0.000004385357,0.0003887783,0.00002242364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004845542,"about_ca_system_score_gemma":0.0001698685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006970696,"about_ca_topic_score_gemma":0.000002914222,"domain_scores_codex":[0.9983694,0.00006564065,0.0003221755,0.0005725354,0.0003670829,0.0003031717],"domain_scores_gemma":[0.9990479,0.00002922953,0.00008114776,0.0005342686,0.0001883909,0.0001190316],"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":[0.00002973802,0.0005347967,0.000001716411,0.0001151925,0.000008412432,0.0000154844,0.0006263092,0.02436385,0.01038914,0.0008661537,0.0005045889,0.9625446],"study_design_scores_gemma":[0.0002213915,0.00007751611,0.000004585638,0.0002415445,0.000008659979,0.00001771855,0.000005527445,0.9159567,0.08012532,0.002506138,0.0005367993,0.000298129],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003562628,0.00006596513,0.9966137,0.0002962898,0.00005911804,0.0003252715,0.000007543902,0.001265678,0.001010177],"genre_scores_gemma":[0.7393962,0.0000435645,0.259403,0.0007144639,0.00002150962,0.0001230939,0.000002220374,0.00002832741,0.0002676382],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9622465,"threshold_uncertainty_score":0.9999914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01500319070623827,"score_gpt":0.2832409412373124,"score_spread":0.2682377505310741,"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."}}