Matches in SemOpenAlex for { <https://semopenalex.org/work/W2464641472> ?p ?o ?g. }
- W2464641472 endingPage "5701" @default.
- W2464641472 startingPage "5687" @default.
- W2464641472 abstract "The celebrated sparse representation model has led to remarkable results in various signal processing tasks in the last decade. However, despite its initial purpose of serving as a global prior for entire signals, it has been commonly used for modeling low dimensional patches due to the computational constraints it entails when deployed with learned dictionaries. A way around this problem has been recently proposed, adopting a convolutional sparse representation model. This approach assumes that the global dictionary is a concatenation of banded Circulant matrices. While several works have presented algorithmic solutions to the global pursuit problem under this new model, very few truly-effective guarantees are known for the success of such methods. In this work, we address the theoretical aspects of the convolutional sparse model providing the first meaningful answers to questions of uniqueness of solutions and success of pursuit algorithms, both greedy and convex relaxations, in ideal and noisy regimes. To this end, we generalize mathematical quantities, such as the $ell_0$ norm, mutual coherence, Spark and RIP to their counterparts in the convolutional setting, intrinsically capturing local measures of the global model. On the algorithmic side, we demonstrate how to solve the global pursuit problem by using simple local processing, thus offering a first of its kind bridge between global modeling of signals and their patch-based local treatment." @default.
- W2464641472 created "2016-07-22" @default.
- W2464641472 creator A5018100130 @default.
- W2464641472 creator A5020279598 @default.
- W2464641472 creator A5086776097 @default.
- W2464641472 date "2017-11-01" @default.
- W2464641472 modified "2023-10-18" @default.
- W2464641472 title "Working Locally Thinking Globally: Theoretical Guarantees for Convolutional Sparse Coding" @default.
- W2464641472 cites W1523302144 @default.
- W2464641472 cites W167933998 @default.
- W2464641472 cites W1829781029 @default.
- W2464641472 cites W1946953458 @default.
- W2464641472 cites W1976709621 @default.
- W2464641472 cites W1999905919 @default.
- W2464641472 cites W2005876975 @default.
- W2464641472 cites W2027805700 @default.
- W2464641472 cites W2048878808 @default.
- W2464641472 cites W2067808985 @default.
- W2464641472 cites W2075230492 @default.
- W2464641472 cites W2078204800 @default.
- W2464641472 cites W2097323375 @default.
- W2464641472 cites W2102380305 @default.
- W2464641472 cites W2103844245 @default.
- W2464641472 cites W2108625419 @default.
- W2464641472 cites W2115429828 @default.
- W2464641472 cites W2115706991 @default.
- W2464641472 cites W2116148865 @default.
- W2464641472 cites W2117259536 @default.
- W2464641472 cites W2128659236 @default.
- W2464641472 cites W2129131372 @default.
- W2464641472 cites W2136235822 @default.
- W2464641472 cites W2138548210 @default.
- W2464641472 cites W2140050933 @default.
- W2464641472 cites W2147656689 @default.
- W2464641472 cites W2151693816 @default.
- W2464641472 cites W2154332973 @default.
- W2464641472 cites W2159766410 @default.
- W2464641472 cites W2160547390 @default.
- W2464641472 cites W2172275395 @default.
- W2464641472 cites W2184334976 @default.
- W2464641472 cites W2190662802 @default.
- W2464641472 cites W2202656999 @default.
- W2464641472 cites W2293078015 @default.
- W2464641472 cites W2592358735 @default.
- W2464641472 cites W3104720471 @default.
- W2464641472 cites W4206310440 @default.
- W2464641472 cites W4235713725 @default.
- W2464641472 cites W4250297470 @default.
- W2464641472 cites W4292363360 @default.
- W2464641472 doi "https://doi.org/10.1109/tsp.2017.2733447" @default.
- W2464641472 hasPublicationYear "2017" @default.
- W2464641472 type Work @default.
- W2464641472 sameAs 2464641472 @default.
- W2464641472 citedByCount "95" @default.
- W2464641472 countsByYear W24646414722016 @default.
- W2464641472 countsByYear W24646414722017 @default.
- W2464641472 countsByYear W24646414722018 @default.
- W2464641472 countsByYear W24646414722019 @default.
- W2464641472 countsByYear W24646414722020 @default.
- W2464641472 countsByYear W24646414722021 @default.
- W2464641472 countsByYear W24646414722022 @default.
- W2464641472 countsByYear W24646414722023 @default.
- W2464641472 crossrefType "journal-article" @default.
- W2464641472 hasAuthorship W2464641472A5018100130 @default.
- W2464641472 hasAuthorship W2464641472A5020279598 @default.
- W2464641472 hasAuthorship W2464641472A5086776097 @default.
- W2464641472 hasBestOaLocation W24646414722 @default.
- W2464641472 hasConcept C105795698 @default.
- W2464641472 hasConcept C11413529 @default.
- W2464641472 hasConcept C114614502 @default.
- W2464641472 hasConcept C115973184 @default.
- W2464641472 hasConcept C124066611 @default.
- W2464641472 hasConcept C126255220 @default.
- W2464641472 hasConcept C154945302 @default.
- W2464641472 hasConcept C199360897 @default.
- W2464641472 hasConcept C2781181686 @default.
- W2464641472 hasConcept C2781215313 @default.
- W2464641472 hasConcept C33923547 @default.
- W2464641472 hasConcept C41008148 @default.
- W2464641472 hasConcept C45900066 @default.
- W2464641472 hasConcept C77637269 @default.
- W2464641472 hasConcept C80444323 @default.
- W2464641472 hasConcept C81363708 @default.
- W2464641472 hasConcept C87619178 @default.
- W2464641472 hasConceptScore W2464641472C105795698 @default.
- W2464641472 hasConceptScore W2464641472C11413529 @default.
- W2464641472 hasConceptScore W2464641472C114614502 @default.
- W2464641472 hasConceptScore W2464641472C115973184 @default.
- W2464641472 hasConceptScore W2464641472C124066611 @default.
- W2464641472 hasConceptScore W2464641472C126255220 @default.
- W2464641472 hasConceptScore W2464641472C154945302 @default.
- W2464641472 hasConceptScore W2464641472C199360897 @default.
- W2464641472 hasConceptScore W2464641472C2781181686 @default.
- W2464641472 hasConceptScore W2464641472C2781215313 @default.
- W2464641472 hasConceptScore W2464641472C33923547 @default.
- W2464641472 hasConceptScore W2464641472C41008148 @default.
- W2464641472 hasConceptScore W2464641472C45900066 @default.
- W2464641472 hasConceptScore W2464641472C77637269 @default.