Matches in SemOpenAlex for { <https://semopenalex.org/work/W2778749674> ?p ?o ?g. }
- W2778749674 abstract "To compress large datasets of high-dimensional descriptors, modern quantization schemes learn multiple codebooks and then represent individual descriptors as combinations of codewords. Once the codebooks are learned, these schemes encode descriptors independently. In contrast to that, we present a new coding scheme that arranges dataset descriptors into a set of arborescence graphs, and then encodes non-root descriptors by quantizing their displacements with respect to their parent nodes. By optimizing the structure of arborescences, our coding scheme can decrease the quantization error considerably, while incurring only minimal overhead on the memory footprint and the speed of nearest neighbor search in the compressed dataset compared to the independent quantization. The advantage of the proposed scheme is demonstrated in a series of experiments with datasets of SIFT and deep descriptors." @default.
- W2778749674 created "2018-01-05" @default.
- W2778749674 creator A5019807610 @default.
- W2778749674 creator A5083458209 @default.
- W2778749674 date "2017-10-01" @default.
- W2778749674 modified "2023-09-25" @default.
- W2778749674 title "AnnArbor: Approximate Nearest Neighbors Using Arborescence Coding" @default.
- W2778749674 cites W138284169 @default.
- W2778749674 cites W1833123814 @default.
- W2778749674 cites W1911745671 @default.
- W2778749674 cites W1977182282 @default.
- W2778749674 cites W1980628172 @default.
- W2778749674 cites W1987488988 @default.
- W2778749674 cites W2003187482 @default.
- W2778749674 cites W2039742379 @default.
- W2778749674 cites W2039743183 @default.
- W2778749674 cites W2100205678 @default.
- W2778749674 cites W2111006384 @default.
- W2778749674 cites W2112038332 @default.
- W2778749674 cites W2119913432 @default.
- W2778749674 cites W2124509324 @default.
- W2778749674 cites W2126683703 @default.
- W2778749674 cites W2133995768 @default.
- W2778749674 cites W2148554573 @default.
- W2778749674 cites W2151103935 @default.
- W2778749674 cites W2158023586 @default.
- W2778749674 cites W2468923260 @default.
- W2778749674 cites W2913932916 @default.
- W2778749674 doi "https://doi.org/10.1109/iccv.2017.523" @default.
- W2778749674 hasPublicationYear "2017" @default.
- W2778749674 type Work @default.
- W2778749674 sameAs 2778749674 @default.
- W2778749674 citedByCount "3" @default.
- W2778749674 countsByYear W27787496742018 @default.
- W2778749674 crossrefType "proceedings-article" @default.
- W2778749674 hasAuthorship W2778749674A5019807610 @default.
- W2778749674 hasAuthorship W2778749674A5083458209 @default.
- W2778749674 hasConcept C104317684 @default.
- W2778749674 hasConcept C105795698 @default.
- W2778749674 hasConcept C111919701 @default.
- W2778749674 hasConcept C113238511 @default.
- W2778749674 hasConcept C11413529 @default.
- W2778749674 hasConcept C116738811 @default.
- W2778749674 hasConcept C127759330 @default.
- W2778749674 hasConcept C153180895 @default.
- W2778749674 hasConcept C154945302 @default.
- W2778749674 hasConcept C179518139 @default.
- W2778749674 hasConcept C185592680 @default.
- W2778749674 hasConcept C199833920 @default.
- W2778749674 hasConcept C28855332 @default.
- W2778749674 hasConcept C33923547 @default.
- W2778749674 hasConcept C41008148 @default.
- W2778749674 hasConcept C52622490 @default.
- W2778749674 hasConcept C55493867 @default.
- W2778749674 hasConcept C61265191 @default.
- W2778749674 hasConcept C66746571 @default.
- W2778749674 hasConcept C74912251 @default.
- W2778749674 hasConceptScore W2778749674C104317684 @default.
- W2778749674 hasConceptScore W2778749674C105795698 @default.
- W2778749674 hasConceptScore W2778749674C111919701 @default.
- W2778749674 hasConceptScore W2778749674C113238511 @default.
- W2778749674 hasConceptScore W2778749674C11413529 @default.
- W2778749674 hasConceptScore W2778749674C116738811 @default.
- W2778749674 hasConceptScore W2778749674C127759330 @default.
- W2778749674 hasConceptScore W2778749674C153180895 @default.
- W2778749674 hasConceptScore W2778749674C154945302 @default.
- W2778749674 hasConceptScore W2778749674C179518139 @default.
- W2778749674 hasConceptScore W2778749674C185592680 @default.
- W2778749674 hasConceptScore W2778749674C199833920 @default.
- W2778749674 hasConceptScore W2778749674C28855332 @default.
- W2778749674 hasConceptScore W2778749674C33923547 @default.
- W2778749674 hasConceptScore W2778749674C41008148 @default.
- W2778749674 hasConceptScore W2778749674C52622490 @default.
- W2778749674 hasConceptScore W2778749674C55493867 @default.
- W2778749674 hasConceptScore W2778749674C61265191 @default.
- W2778749674 hasConceptScore W2778749674C66746571 @default.
- W2778749674 hasConceptScore W2778749674C74912251 @default.
- W2778749674 hasLocation W27787496741 @default.
- W2778749674 hasOpenAccess W2778749674 @default.
- W2778749674 hasPrimaryLocation W27787496741 @default.
- W2778749674 hasRelatedWork W138284169 @default.
- W2778749674 hasRelatedWork W1911745671 @default.
- W2778749674 hasRelatedWork W1977182282 @default.
- W2778749674 hasRelatedWork W2012592962 @default.
- W2778749674 hasRelatedWork W2056092456 @default.
- W2778749674 hasRelatedWork W2076439560 @default.
- W2778749674 hasRelatedWork W2086504823 @default.
- W2778749674 hasRelatedWork W2121841352 @default.
- W2778749674 hasRelatedWork W2124509324 @default.
- W2778749674 hasRelatedWork W2132234208 @default.
- W2778749674 hasRelatedWork W2133995768 @default.
- W2778749674 hasRelatedWork W2135172998 @default.
- W2778749674 hasRelatedWork W2148554573 @default.
- W2778749674 hasRelatedWork W2171572695 @default.
- W2778749674 hasRelatedWork W2293155043 @default.
- W2778749674 hasRelatedWork W2468923260 @default.
- W2778749674 hasRelatedWork W2554385338 @default.
- W2778749674 hasRelatedWork W2593864460 @default.
- W2778749674 hasRelatedWork W2732156181 @default.
- W2778749674 hasRelatedWork W2775212345 @default.