{"id":"W2811207102","doi":"10.1109/tmm.2018.2851447","title":"A Channel-Dependent Statistical Watermark Detector for Color Images","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Watermark; Digital watermarking; Computer science; Detector; Robustness (evolution); RGB color model; Artificial intelligence; Channel (broadcasting); Computer vision; RGB color space; Color image; Pattern recognition (psychology); Image (mathematics); Image processing; Telecommunications","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001860954,0.0002115578,0.0001922405,0.000200673,0.0003519624,0.00008939091,0.0005292132,0.0001066494,0.00002679249],"category_scores_gemma":[0.00001174512,0.0001819388,0.0001124604,0.000186655,0.0002015982,0.0003423667,0.000004565104,0.0001747074,0.00005639408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004266598,"about_ca_system_score_gemma":0.00002942572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001419098,"about_ca_topic_score_gemma":0.00001759918,"domain_scores_codex":[0.9985855,0.0000575475,0.0002422754,0.000469816,0.0002212362,0.0004236075],"domain_scores_gemma":[0.9988968,0.0003197218,0.00005745244,0.0004347365,0.0001442602,0.0001469844],"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":[0.001317649,0.001466061,0.0000215687,0.000161523,0.0003076723,0.00009016669,0.00512141,0.001255014,0.1009239,0.0008004295,0.004511679,0.8840229],"study_design_scores_gemma":[0.00086608,0.0008888705,0.00009755116,0.00003234667,0.00002414288,0.00001682477,0.00001399289,0.1247339,0.8688578,0.002750012,0.001372491,0.0003459701],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001590266,0.0000078762,0.9956276,0.0001902355,0.001154891,0.00053732,0.0001955352,0.0006219396,0.00007436456],"genre_scores_gemma":[0.6948261,0.00001119132,0.3044538,0.000144206,0.0001004107,0.0002830262,0.000002984508,0.00001686146,0.0001613588],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8836769,"threshold_uncertainty_score":0.7419247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01705086314740194,"score_gpt":0.2761206773815466,"score_spread":0.2590698142341446,"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."}}