{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000284325,0.0002330603,0.0002240148,0.0001638048,0.00005811747,0.0008137894,0.0005461,0.0002241852,0.000009302172],"category_scores_gemma":[0.0001494727,0.0002281486,0.00005429914,0.0001982489,0.00006544335,0.0008894466,0.001085387,0.0003724965,0.0001134044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008010082,"about_ca_system_score_gemma":0.00009462643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001126969,"about_ca_topic_score_gemma":0.00004657724,"domain_scores_codex":[0.9982664,0.00004395195,0.0003029208,0.0007838313,0.0003770125,0.0002259108],"domain_scores_gemma":[0.9987523,0.0001007231,0.0002503825,0.0006551672,0.0001269737,0.000114484],"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":[0.00001028367,0.00002862648,0.001524136,0.00008224593,0.00002128982,0.000002955946,0.0003521396,0.0004154807,0.00006794951,0.002206625,0.002675185,0.9926131],"study_design_scores_gemma":[0.0008230895,0.0002129781,0.0007024912,0.0005565287,0.0000210253,0.00005879166,0.00004263043,0.9333738,0.00877166,0.04907526,0.005381847,0.0009798832],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04544513,0.0004954598,0.9429123,0.0003524399,0.00324289,0.0004495157,0.000002881294,0.000282122,0.006817282],"genre_scores_gemma":[0.934707,0.00005660314,0.06398348,0.0001297351,0.00009459921,0.00004197257,0.00005626331,0.00001556994,0.0009147798],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9916332,"threshold_uncertainty_score":0.9303629,"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."}}