{"id":"W2562583884","doi":"10.1109/crv.2016.12","title":"Robust Non-saliency Guided Watermarking","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Digital watermarking; Robustness (evolution); Artificial intelligence; Watermark; Computer science; Human visual system model; Brightness; Embedding; Pixel; Computer vision; Salient; Pattern recognition (psychology); Exploit; Image (mathematics); Computer security","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":[0.0002239155,0.0001447591,0.0001256474,0.0001401659,0.000127742,0.00008085208,0.001036685,0.00005570376,0.0000253129],"category_scores_gemma":[0.00001236853,0.00007971774,0.000083265,0.0002469301,0.00005432111,0.0009440561,0.0003380958,0.00005028406,0.00004597475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002262007,"about_ca_system_score_gemma":0.00001455419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000849708,"about_ca_topic_score_gemma":0.000001554811,"domain_scores_codex":[0.9988254,0.00003028549,0.0002223357,0.0003778007,0.0001801938,0.0003639822],"domain_scores_gemma":[0.9990814,0.00005017755,0.00005873679,0.0006751168,0.00005690365,0.0000776125],"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":[0.00001363305,0.0001256571,0.01302117,0.00002975268,0.00004174126,0.000115391,0.0006973288,0.00002597226,0.1152759,0.2835409,0.02397706,0.5631354],"study_design_scores_gemma":[0.001204257,0.0002327147,0.009460168,0.0003302372,0.00000938898,0.0001411401,0.00001204571,0.004892137,0.7119528,0.1892644,0.08116957,0.001331163],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005256735,0.00001103904,0.9667243,0.00116556,0.0002310423,0.00009937698,5.763235e-7,0.0009250836,0.02558628],"genre_scores_gemma":[0.7258253,0.00003018956,0.2725261,0.0003233066,0.00004398936,0.00001705237,3.321909e-7,0.000008150221,0.001225627],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7205685,"threshold_uncertainty_score":0.3250795,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02998849587401215,"score_gpt":0.2490483056136876,"score_spread":0.2190598097396755,"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."}}