{"id":"W2086277433","doi":"10.1109/tmm.2013.2291658","title":"Adaptive Watermarking and Tree Structure Based Image Quality Estimation","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"Communications Research Centre Canada; University of Ottawa","funders":"","keywords":"Watermark; Digital watermarking; Computer science; Artificial intelligence; Image quality; Set partitioning in hierarchical trees; Distortion (music); Tree (set theory); Additive white Gaussian noise; Gaussian noise; Pattern recognition (psychology); Image compression; Computer vision; Image processing; Mathematics; Image (mathematics); White noise","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":[0.0001825416,0.000190907,0.0001766913,0.0001968713,0.000242344,0.00009294921,0.000283051,0.00009947303,0.000007459126],"category_scores_gemma":[0.000009413006,0.0001667868,0.00007424042,0.0002001659,0.0001108096,0.0005776904,0.000003038927,0.0002418503,0.000003675995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002685147,"about_ca_system_score_gemma":0.00001418638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002525659,"about_ca_topic_score_gemma":0.0000271611,"domain_scores_codex":[0.9987888,0.0001697285,0.0002212302,0.0003831227,0.0002125562,0.0002245562],"domain_scores_gemma":[0.9990896,0.0002627399,0.00008462965,0.0004120328,0.00005564805,0.00009535841],"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":[0.00006086233,0.00007346978,0.00005180536,0.00002778208,0.00001919876,0.000003223048,0.0007505924,0.002759401,0.02297407,0.0002727593,0.0000163388,0.9729905],"study_design_scores_gemma":[0.0004633439,0.0001117865,0.001285313,0.00003578779,0.00001038563,0.000003823452,0.000006794527,0.7501602,0.2440183,0.003605186,0.00008218261,0.0002169433],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009575387,0.000005866457,0.9891931,0.000185435,0.0002600314,0.0001768116,0.00001855542,0.0004585466,0.0001262408],"genre_scores_gemma":[0.5785713,0.000002916927,0.4212778,0.0001025468,0.00001342311,0.00001434988,0.000002326956,0.000007188974,0.000008173311],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9727736,"threshold_uncertainty_score":0.680137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01532327245440409,"score_gpt":0.2658326711455773,"score_spread":0.2505093986911733,"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."}}