{"id":"W2800412484","doi":"10.1016/j.neucom.2018.04.046","title":"MF-LRTC: Multi-filters guided low-rank tensor coding for image restoration","year":2018,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Deblurring; Artificial intelligence; Computer science; Pattern recognition (psychology); Rank (graph theory); Neural coding; Redundancy (engineering); Coding (social sciences); Tensor (intrinsic definition); Image restoration; Structure tensor; Image (mathematics); Mathematics; Computer vision; Image processing","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":[0.0001260638,0.0001811422,0.000173918,0.0001058295,0.0001940019,0.00009704768,0.0001675906,0.00006776075,0.000003295467],"category_scores_gemma":[0.00009533575,0.0001962622,0.00007251559,0.0001322703,0.00003995972,0.0001324863,0.00004017286,0.0001267841,0.0000197853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003776898,"about_ca_system_score_gemma":0.000008081616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006284695,"about_ca_topic_score_gemma":0.000002579879,"domain_scores_codex":[0.9990202,0.00002654076,0.0002710653,0.0002569791,0.0001057566,0.0003195067],"domain_scores_gemma":[0.9993919,0.00008895907,0.0000635532,0.0002483797,0.0001543233,0.00005291867],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001693924,0.00002480311,0.00008979641,0.00005123795,0.00001884154,0.00001740461,0.0003440799,0.005535472,0.9476566,0.0001527824,0.02320366,0.02288836],"study_design_scores_gemma":[0.000361376,0.00007415976,0.0008315795,0.0001185247,0.0000115527,0.00001634686,0.00001391027,0.7487667,0.2462421,0.00009207136,0.003258934,0.0002127998],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3726155,0.00002130918,0.6230798,0.00008933877,0.000614925,0.0004363654,0.000002813645,0.001893076,0.001246912],"genre_scores_gemma":[0.882439,0.000004022633,0.1165219,0.0003123935,0.0006310516,0.000008255867,0.000005801202,0.00005249742,0.00002507545],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7432312,"threshold_uncertainty_score":0.8003342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04025375119954876,"score_gpt":0.2883419456752768,"score_spread":0.2480881944757281,"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."}}