{"id":"W2002447637","doi":"10.1145/2043674.2043698","title":"Hiding depth map into stereo image in JPEG format using reversible watermarking","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Communications Research Centre Canada; University of Ottawa","funders":"","keywords":"Digital watermarking; Computer vision; Artificial intelligence; Computer science; Stereo image; JPEG; JPEG 2000; Depth map; Image (mathematics); Information hiding; Computer graphics (images); Image processing; Image compression","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":[0.0003780028,0.0001972672,0.0001976554,0.000426635,0.0001738649,0.0001268362,0.0009203541,0.00007934691,0.00001706445],"category_scores_gemma":[0.000005983138,0.0001710748,0.00008619804,0.0004373039,0.00005297767,0.002809334,0.0006091014,0.0001792242,0.000012789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008277356,"about_ca_system_score_gemma":0.00001972684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002670539,"about_ca_topic_score_gemma":0.00005473437,"domain_scores_codex":[0.9985854,0.00006710596,0.0003332534,0.0003715972,0.0001680934,0.0004745198],"domain_scores_gemma":[0.9992307,0.00002481086,0.00009842534,0.000527874,0.0000417593,0.00007647584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003345726,0.0008323507,0.2773494,0.001294192,0.0001783023,0.00180119,0.1020973,0.00007264224,0.2037071,0.1493532,0.002952367,0.2600273],"study_design_scores_gemma":[0.001005269,0.0001842818,0.003823593,0.0006590922,0.00001625424,0.0001339053,0.0005281843,0.06156605,0.7432377,0.1833947,0.004053281,0.001397765],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06500916,0.00004889743,0.9201267,0.00004749817,0.0002324118,0.0001782319,2.931223e-7,0.0005198807,0.01383694],"genre_scores_gemma":[0.5298125,0.00001055222,0.4700048,0.0001048694,0.00001244644,0.000005320581,6.805482e-7,0.000008397225,0.00004052966],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5395306,"threshold_uncertainty_score":0.6976227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0420835214981784,"score_gpt":0.2666788399980955,"score_spread":0.2245953184999171,"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."}}