{"id":"W2133251102","doi":"10.1109/tip.2005.864165","title":"Quality-aware images","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":291,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Image quality; Computer vision; Digital watermarking; Quantization (signal processing); Decoding methods; Image (mathematics); Pattern recognition (psychology); Image processing; Transform coding; Information hiding; Wavelet; Wavelet transform; Discrete cosine transform; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001825502,0.0001845061,0.0001574046,0.0002260045,0.0004883495,0.000347446,0.0004801094,0.00006372971,0.000006416196],"category_scores_gemma":[0.00000152386,0.0001738037,0.0001146646,0.000526679,0.000101877,0.001500535,0.000002975669,0.0002420176,0.00001415872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003295246,"about_ca_system_score_gemma":0.00003711138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003424008,"about_ca_topic_score_gemma":0.000005861255,"domain_scores_codex":[0.9987211,0.00005844689,0.0002780468,0.0003974844,0.000244821,0.0003000816],"domain_scores_gemma":[0.9993148,0.0000486619,0.00009857881,0.0003762514,0.0001142075,0.00004749195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003580502,0.0005110157,0.0000702067,0.0002019231,0.00001727551,0.00005370246,0.0003840255,0.001220976,0.07505111,0.001277154,0.0006115785,0.9205652],"study_design_scores_gemma":[0.0003882887,0.00007404172,0.0004273785,0.000145989,0.00001194114,0.00004156394,0.00003437394,0.009186012,0.9642153,0.02396335,0.0009455106,0.0005663042],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007373951,0.00007952465,0.9948207,0.0003047689,0.0001461106,0.0001043117,0.000007450421,0.001260081,0.002539643],"genre_scores_gemma":[0.7600801,0.000007706373,0.2394117,0.0001296431,0.00003292799,0.00003299334,9.365738e-7,0.00001378592,0.0002902033],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9199989,"threshold_uncertainty_score":0.7087508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01561779813647675,"score_gpt":0.2873651539594971,"score_spread":0.2717473558230203,"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."}}