{"id":"W3034863454","doi":"10.1109/tip.2020.2999209","title":"Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Google","keywords":"Video denoising; Pixel; Noise reduction; Artificial intelligence; Computer science; Computer vision; Non-local means; Regularization (linguistics); Total variation denoising; Pattern recognition (psychology); Image restoration; Image denoising; Image (mathematics); Image processing; Video processing; Video tracking","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003534505,0.0002252812,0.0002412328,0.0001506785,0.001029385,0.001040747,0.000212765,0.00007380825,0.00000760137],"category_scores_gemma":[0.00008881358,0.0002339772,0.00006952528,0.0003610077,0.0001439623,0.001699619,0.000008567362,0.0003421956,0.000005730104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000278499,"about_ca_system_score_gemma":0.0001083057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003764185,"about_ca_topic_score_gemma":0.00001280206,"domain_scores_codex":[0.9984751,0.0001222863,0.0003042359,0.0005743284,0.000217079,0.0003070169],"domain_scores_gemma":[0.9990959,0.0002339452,0.000143029,0.0001476759,0.0001941573,0.0001852701],"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":[0.0001027049,0.0000487781,0.00002527999,0.0002491262,0.00001986803,0.00001652274,0.004256544,0.0005073143,0.100555,0.00002899105,0.00003685576,0.894153],"study_design_scores_gemma":[0.00184856,0.0004315941,0.00009206676,0.0002022545,0.00008283203,0.00008377103,0.000255333,0.8261117,0.1681966,0.001227314,0.0009437533,0.0005241968],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01023611,0.0002212948,0.9865267,0.002260106,0.000119319,0.0002653545,0.000005348183,0.0002636945,0.000102082],"genre_scores_gemma":[0.5972754,0.00001652437,0.4021491,0.0003716323,0.00007091196,0.00002405219,0.000002037728,0.00002289247,0.0000674967],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8936288,"threshold_uncertainty_score":0.9999962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02356500177631189,"score_gpt":0.2814389139877679,"score_spread":0.2578739122114561,"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."}}