{"id":"W2064428286","doi":"10.1109/tip.2012.2231090","title":"Perceptual Video Coding Based on SSIM-Inspired Divisive Normalization","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Macroblock; Normalization (sociology); Computer science; Artificial intelligence; Discrete cosine transform; Computer vision; Coding (social sciences); Context-adaptive variable-length coding; Pattern recognition (psychology); Algorithm; Mathematics; Context-adaptive binary arithmetic coding; Data compression; Decoding methods","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":[0.0004648588,0.0002656537,0.000207482,0.000297052,0.0007729084,0.0005279111,0.0004214521,0.00008909491,0.00007678231],"category_scores_gemma":[0.00001893567,0.0002590553,0.0001193435,0.0006165923,0.00007835835,0.003178104,0.000004690354,0.0003135656,0.0001392178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001827426,"about_ca_system_score_gemma":0.0001529436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001837395,"about_ca_topic_score_gemma":0.000003900199,"domain_scores_codex":[0.9979295,0.0001649646,0.0003545019,0.0004264972,0.0005724202,0.000552077],"domain_scores_gemma":[0.998911,0.0001445769,0.0001462811,0.0004351174,0.000180599,0.0001824112],"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":[0.0001376794,0.002685491,0.0001784583,0.0004936515,0.00005629448,0.00002897306,0.01703597,0.02300074,0.04617745,0.0009445508,0.0006291665,0.9086316],"study_design_scores_gemma":[0.001081439,0.0002442695,0.0007498317,0.0003412659,0.00005379206,0.00001476653,0.0005739799,0.7990024,0.1966733,0.00009893532,0.0005010915,0.0006649361],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002035358,0.0000353606,0.9943958,0.0008495372,0.0005355568,0.0002106405,0.000007467052,0.0003733988,0.001556891],"genre_scores_gemma":[0.9500867,0.000006589491,0.04773749,0.001829584,0.000110995,0.00005458981,0.00000422277,0.00002719237,0.0001425921],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9480514,"threshold_uncertainty_score":0.9999862,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02952650906352391,"score_gpt":0.302428470009144,"score_spread":0.2729019609456201,"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."}}