Matches in SemOpenAlex for { <https://semopenalex.org/work/W2808086194> ?p ?o ?g. }
- W2808086194 abstract "We propose an algorithm for rotational sparse coding along with an efficient implementation using steerability. Sparse coding (also called dictionary learning) is an important technique in image processing, useful in inverse problems, compression, and analysis; however, the usual formulation fails to capture an important aspect of the structure of images: images are formed from building blocks, e.g., edges, lines, or points, that appear at different locations, orientations, and scales. The sparse coding problem can be reformulated to explicitly account for these transforms, at the cost of increased computation. In this work, we propose an algorithm for a rotational version of sparse coding that is based on K-SVD with additional rotation operations. We then propose a method to accelerate these rotations by learning the dictionary in a steerable basis. Our experiments on patch coding and texture classification demonstrate that the proposed algorithm is fast enough for practical use and compares favorably to standard sparse coding." @default.
- W2808086194 created "2018-06-21" @default.
- W2808086194 creator A5006151881 @default.
- W2808086194 creator A5007157109 @default.
- W2808086194 creator A5027830035 @default.
- W2808086194 creator A5043355848 @default.
- W2808086194 date "2018-06-12" @default.
- W2808086194 modified "2023-09-25" @default.
- W2808086194 title "Fast Rotational Sparse Coding" @default.
- W2808086194 cites W1260645847 @default.
- W2808086194 cites W130490334 @default.
- W2808086194 cites W1496441095 @default.
- W2808086194 cites W1586885484 @default.
- W2808086194 cites W1686810756 @default.
- W2808086194 cites W1835905048 @default.
- W2808086194 cites W1963932623 @default.
- W2808086194 cites W1966364402 @default.
- W2808086194 cites W1971146872 @default.
- W2808086194 cites W2005876975 @default.
- W2808086194 cites W2008732654 @default.
- W2808086194 cites W2012707786 @default.
- W2808086194 cites W2028031899 @default.
- W2808086194 cites W2031586513 @default.
- W2808086194 cites W2042583427 @default.
- W2808086194 cites W2066941820 @default.
- W2808086194 cites W2094366314 @default.
- W2808086194 cites W2107474339 @default.
- W2808086194 cites W2107790757 @default.
- W2808086194 cites W2108598243 @default.
- W2808086194 cites W2115429828 @default.
- W2808086194 cites W2127565671 @default.
- W2808086194 cites W2128638419 @default.
- W2808086194 cites W2128659236 @default.
- W2808086194 cites W2138658730 @default.
- W2808086194 cites W2141376824 @default.
- W2808086194 cites W2159988601 @default.
- W2808086194 cites W2160547390 @default.
- W2808086194 cites W2167188281 @default.
- W2808086194 cites W2168668658 @default.
- W2808086194 cites W2183341477 @default.
- W2808086194 cites W2194775991 @default.
- W2808086194 cites W2202656999 @default.
- W2808086194 cites W2293457052 @default.
- W2808086194 cites W2296399167 @default.
- W2808086194 cites W2320738207 @default.
- W2808086194 cites W2481877944 @default.
- W2808086194 cites W2566365295 @default.
- W2808086194 cites W2625143103 @default.
- W2808086194 cites W2769152880 @default.
- W2808086194 cites W2922145533 @default.
- W2808086194 cites W2952071070 @default.
- W2808086194 cites W2953139536 @default.
- W2808086194 cites W2963446712 @default.
- W2808086194 cites W2963542991 @default.
- W2808086194 cites W2964034664 @default.
- W2808086194 cites W3100063120 @default.
- W2808086194 cites W3102779874 @default.
- W2808086194 cites W819977924 @default.
- W2808086194 hasPublicationYear "2018" @default.
- W2808086194 type Work @default.
- W2808086194 sameAs 2808086194 @default.
- W2808086194 citedByCount "1" @default.
- W2808086194 countsByYear W28080861942020 @default.
- W2808086194 crossrefType "posted-content" @default.
- W2808086194 hasAuthorship W2808086194A5006151881 @default.
- W2808086194 hasAuthorship W2808086194A5007157109 @default.
- W2808086194 hasAuthorship W2808086194A5027830035 @default.
- W2808086194 hasAuthorship W2808086194A5043355848 @default.
- W2808086194 hasConcept C105795698 @default.
- W2808086194 hasConcept C11413529 @default.
- W2808086194 hasConcept C121332964 @default.
- W2808086194 hasConcept C124066611 @default.
- W2808086194 hasConcept C153180895 @default.
- W2808086194 hasConcept C154771677 @default.
- W2808086194 hasConcept C154945302 @default.
- W2808086194 hasConcept C163716315 @default.
- W2808086194 hasConcept C179518139 @default.
- W2808086194 hasConcept C207467116 @default.
- W2808086194 hasConcept C2524010 @default.
- W2808086194 hasConcept C33923547 @default.
- W2808086194 hasConcept C41008148 @default.
- W2808086194 hasConcept C45374587 @default.
- W2808086194 hasConcept C56372850 @default.
- W2808086194 hasConcept C62520636 @default.
- W2808086194 hasConcept C77637269 @default.
- W2808086194 hasConceptScore W2808086194C105795698 @default.
- W2808086194 hasConceptScore W2808086194C11413529 @default.
- W2808086194 hasConceptScore W2808086194C121332964 @default.
- W2808086194 hasConceptScore W2808086194C124066611 @default.
- W2808086194 hasConceptScore W2808086194C153180895 @default.
- W2808086194 hasConceptScore W2808086194C154771677 @default.
- W2808086194 hasConceptScore W2808086194C154945302 @default.
- W2808086194 hasConceptScore W2808086194C163716315 @default.
- W2808086194 hasConceptScore W2808086194C179518139 @default.
- W2808086194 hasConceptScore W2808086194C207467116 @default.
- W2808086194 hasConceptScore W2808086194C2524010 @default.
- W2808086194 hasConceptScore W2808086194C33923547 @default.
- W2808086194 hasConceptScore W2808086194C41008148 @default.
- W2808086194 hasConceptScore W2808086194C45374587 @default.
- W2808086194 hasConceptScore W2808086194C56372850 @default.