{"id":"W3133028619","doi":"10.1109/icmla51294.2020.00172","title":"Image Watermarking with Region of Interest Determination Using Deep Neural Networks","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Digital watermarking; Robustness (evolution); Computer science; Transparency (behavior); Artificial intelligence; Watermark; Embedding; Artificial neural network; Discrete cosine transform; Computer vision; Deep neural networks; Image (mathematics); Pattern recognition (psychology); 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":[0.00006119665,0.0001186723,0.0001374324,0.00007389765,0.00006670698,0.0000708049,0.0004464515,0.00004036924,0.000001180671],"category_scores_gemma":[0.000006251079,0.0000884839,0.00004910793,0.00031785,0.00006439048,0.0008364989,0.0001843445,0.0001083068,1.717525e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001066307,"about_ca_system_score_gemma":0.000004380571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006704968,"about_ca_topic_score_gemma":0.000004538625,"domain_scores_codex":[0.9992481,0.00004753248,0.0001922459,0.0002468935,0.00008529913,0.0001798897],"domain_scores_gemma":[0.9994889,0.00002640371,0.0001285341,0.0002282738,0.00006934538,0.0000585114],"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":[0.0006671352,0.0002416917,0.03355138,0.0005284849,0.0001217307,0.001470411,0.009831224,0.01644539,0.08613558,0.02761222,0.0002421483,0.8231526],"study_design_scores_gemma":[0.0001289274,0.0001465566,0.0002099506,0.00003478117,0.000005351261,0.00006068992,0.00001512261,0.9801303,0.01861178,0.0005003277,0.00002643163,0.000129758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06051781,0.00001482894,0.9386432,0.0002529927,0.00004168108,0.0001002555,1.051639e-7,0.0002529459,0.0001762139],"genre_scores_gemma":[0.7202348,0.000002921109,0.2795327,0.0001915304,0.00002730684,0.000002080086,8.746889e-7,0.000006606353,0.000001188076],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9636849,"threshold_uncertainty_score":0.3608268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04776475278249906,"score_gpt":0.2614722999997102,"score_spread":0.2137075472172111,"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."}}