{"id":"W4210825863","doi":"10.1109/tmm.2022.3149641","title":"Encoded Feature Enhancement in Watermarking Network for Distortion in Real Scenes","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Watermark; Digital watermarking; Robustness (evolution); Distortion (music); Artificial intelligence; Encoder; Phase distortion; Image quality; Noise (video); Feature (linguistics); Algorithm; Pattern recognition (psychology); Computer vision; Image (mathematics); Telecommunications; Bandwidth (computing)","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":[0.0003656101,0.0001533728,0.0001724509,0.0002990031,0.0002882064,0.0000289523,0.000403066,0.00005979042,0.00001008074],"category_scores_gemma":[0.000001730591,0.0001579774,0.00009476225,0.0005603163,0.0000269376,0.0002675435,0.000007162888,0.0003458146,8.886109e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002255755,"about_ca_system_score_gemma":0.00002788899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006886708,"about_ca_topic_score_gemma":0.0002638067,"domain_scores_codex":[0.9986589,0.0001164784,0.0002523398,0.000388842,0.0002155663,0.0003678959],"domain_scores_gemma":[0.9994524,0.0001191208,0.00007045804,0.000295455,0.00001932336,0.00004326173],"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":[0.0006966816,0.001171854,0.002651784,0.00007217542,0.00003961581,0.00006745669,0.007720773,0.2509626,0.01432158,0.0003783141,0.0006100601,0.7213071],"study_design_scores_gemma":[0.004968394,0.001295991,0.007339859,0.0003167963,0.00002950672,0.00002243995,0.0002031695,0.717186,0.2464605,0.01048534,0.01025028,0.001441741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02724138,0.00004216564,0.9706169,0.0002556493,0.001046068,0.0005473839,0.00001482564,0.0001791104,0.00005650293],"genre_scores_gemma":[0.8697956,0.0000801924,0.1289504,0.00009174766,0.00003810763,0.0009342546,0.00001143684,0.00001194301,0.00008637417],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8425542,"threshold_uncertainty_score":0.6442133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01730875617166179,"score_gpt":0.2646660447423372,"score_spread":0.2473572885706755,"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."}}