{"id":"W2963502975","doi":"10.1109/cvpr.2019.00439","title":"Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Inpainting; Computer science; Artificial intelligence; Encoder; Pixel; Computer vision; Focus (optics); Residual; Frame (networking); Deep learning; Video decoder; Coherence (philosophical gambling strategy); Pattern recognition (psychology); Image (mathematics); Algorithm; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005214809,0.000867742,0.0007321681,0.0003362613,0.0002501288,0.0006236212,0.001061831,0.0007701981,0.001321155],"category_scores_gemma":[0.001574816,0.0004354931,0.0006709743,0.0003086751,0.0006003844,0.0009823986,0.001085775,0.001198781,0.0003986763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006323351,"about_ca_system_score_gemma":0.0005313709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004029082,"about_ca_topic_score_gemma":0.004714405,"domain_scores_codex":[0.9997681,0.00003781397,0.00001377968,0.00007202775,0.00006911176,0.00003918453],"domain_scores_gemma":[0.9995652,0.0001572425,0.00008859422,0.00008683393,0.00006356506,0.00003858568],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003313603,0.0001048342,0.0008206766,0.0001100056,0.0000822379,0.0002642794,0.0001687993,0.7356625,0.05940922,0.01174899,0.002740969,0.1885562],"study_design_scores_gemma":[0.000004501156,0.00002479469,0.00007008888,0.000002835772,0.000006392456,0.00002821679,0.000003363176,0.9937901,0.004188865,0.001627246,0.0002498202,0.000003805261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03762838,0.0004210537,0.959338,0.0001630737,0.0000405102,0.00002811385,0.00007229717,0.001233053,0.001075474],"genre_scores_gemma":[0.7939578,0.000458411,0.1976976,0.0001716259,0.00007890046,0.00008975722,0.000279991,0.0002098956,0.007055924],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004029082,"threshold_uncertainty_score":0.008011281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01602982401692345,"score_gpt":0.2442405746136241,"score_spread":0.2282107505967007,"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."}}