{"id":"W2106933745","doi":"10.1109/tip.2011.2170699","title":"Polyview Fusion: A Strategy to Enhance Video-Denoising Algorithms","year":2011,"lang":"en","type":"letter","venue":"IEEE Transactions on Image Processing","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Video denoising; Noise reduction; Computer science; Algorithm; Artificial intelligence; Merge (version control); Peak signal-to-noise ratio; Computer vision; Pattern recognition (psychology); Video processing; Video tracking; Image (mathematics); Multiview Video Coding","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":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007603832,0.0008867575,0.0008449185,0.0008522475,0.0009482166,0.001749134,0.002068544,0.000708226,0.000164043],"category_scores_gemma":[0.00002040864,0.0008711457,0.0003765518,0.001495588,0.0001459331,0.001884536,0.000021416,0.003024951,0.0005564257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002100775,"about_ca_system_score_gemma":0.0005594246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001254724,"about_ca_topic_score_gemma":0.000006429419,"domain_scores_codex":[0.994796,0.0004369793,0.0008588733,0.001757268,0.0009949402,0.001155896],"domain_scores_gemma":[0.997304,0.0002126951,0.0003721175,0.001357997,0.0004924726,0.000260775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000261415,0.00009697541,2.205838e-8,0.0004280658,0.00004137002,0.000840437,0.0009405763,0.0001047538,0.009033286,0.000002767165,0.03308269,0.9554029],"study_design_scores_gemma":[0.001393818,0.001659709,0.000005880223,0.007310341,0.0005670494,0.001438287,0.00009071433,0.01858427,0.7409033,0.004443339,0.2176701,0.005933176],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001137289,0.0009904578,0.9457738,0.04861196,0.001359798,0.0004932365,0.00001939371,0.000646131,0.002093809],"genre_scores_gemma":[0.002685114,0.0001326162,0.660876,0.3244372,0.001885394,0.0002021148,0.00000840394,0.0002296478,0.009543457],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9494697,"threshold_uncertainty_score":0.9993739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03465933831098905,"score_gpt":0.3154189116549646,"score_spread":0.2807595733439755,"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."}}