Matches in SemOpenAlex for { <https://semopenalex.org/work/W2197084977> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2197084977 abstract "Binary coding or hashing techniques are recognized to accomplish efficient near neighbor search, and have thus attracted broad interests in the recent vision and learning studies. However, such studies have rarely been dedicated to Maximum Inner Product Search (MIPS), which plays a critical role in various vision applications. In this paper, we investigate learning binary codes to exclusively handle the MIPS problem. Inspired by the latest advance in asymmetric hashing schemes, we propose an asymmetric binary code learning framework based on inner product fitting. Specifically, two sets of coding functions are learned such that the inner products between their generated binary codes can reveal the inner products between original data vectors. We also propose an alternative simpler objective which maximizes the correlations between the inner products of the produced binary codes and raw data vectors. In both objectives, the binary codes and coding functions are simultaneously learned without continuous relaxations, which is the key to achieving high-quality binary codes. We evaluate the proposed method, dubbed Asymmetric Inner-product Binary Coding (AIBC), relying on the two objectives on several large-scale image datasets. Both of them are superior to the state-of-the-art binary coding and hashing methods in performing MIPS tasks." @default.
- W2197084977 created "2016-06-24" @default.
- W2197084977 creator A5001453528 @default.
- W2197084977 creator A5049692788 @default.
- W2197084977 creator A5052993469 @default.
- W2197084977 creator A5071037763 @default.
- W2197084977 creator A5074492050 @default.
- W2197084977 date "2015-12-01" @default.
- W2197084977 modified "2023-10-18" @default.
- W2197084977 title "Learning Binary Codes for Maximum Inner Product Search" @default.
- W2197084977 cites W1524680991 @default.
- W2197084977 cites W1910300841 @default.
- W2197084977 cites W1969241115 @default.
- W2197084977 cites W1972036246 @default.
- W2197084977 cites W1974647172 @default.
- W2197084977 cites W1977182282 @default.
- W2197084977 cites W2017814585 @default.
- W2197084977 cites W2019464758 @default.
- W2197084977 cites W2067952552 @default.
- W2197084977 cites W2074668987 @default.
- W2197084977 cites W2111006384 @default.
- W2197084977 cites W2124509324 @default.
- W2197084977 cites W2126210882 @default.
- W2197084977 cites W2144892774 @default.
- W2197084977 cites W2148554573 @default.
- W2197084977 cites W2153273131 @default.
- W2197084977 cites W2162006472 @default.
- W2197084977 cites W2163808566 @default.
- W2197084977 cites W2164585733 @default.
- W2197084977 cites W2171149307 @default.
- W2197084977 cites W2171790913 @default.
- W2197084977 cites W2220860909 @default.
- W2197084977 cites W2912236665 @default.
- W2197084977 cites W3106512200 @default.
- W2197084977 doi "https://doi.org/10.1109/iccv.2015.472" @default.
- W2197084977 hasPublicationYear "2015" @default.
- W2197084977 type Work @default.
- W2197084977 sameAs 2197084977 @default.
- W2197084977 citedByCount "126" @default.
- W2197084977 countsByYear W21970849772015 @default.
- W2197084977 countsByYear W21970849772016 @default.
- W2197084977 countsByYear W21970849772017 @default.
- W2197084977 countsByYear W21970849772018 @default.
- W2197084977 countsByYear W21970849772019 @default.
- W2197084977 countsByYear W21970849772020 @default.
- W2197084977 countsByYear W21970849772021 @default.
- W2197084977 countsByYear W21970849772022 @default.
- W2197084977 countsByYear W21970849772023 @default.
- W2197084977 crossrefType "proceedings-article" @default.
- W2197084977 hasAuthorship W2197084977A5001453528 @default.
- W2197084977 hasAuthorship W2197084977A5049692788 @default.
- W2197084977 hasAuthorship W2197084977A5052993469 @default.
- W2197084977 hasAuthorship W2197084977A5071037763 @default.
- W2197084977 hasAuthorship W2197084977A5074492050 @default.
- W2197084977 hasConcept C105795698 @default.
- W2197084977 hasConcept C11413529 @default.
- W2197084977 hasConcept C179518139 @default.
- W2197084977 hasConcept C33923547 @default.
- W2197084977 hasConcept C38652104 @default.
- W2197084977 hasConcept C41008148 @default.
- W2197084977 hasConcept C48372109 @default.
- W2197084977 hasConcept C63435697 @default.
- W2197084977 hasConcept C80444323 @default.
- W2197084977 hasConcept C94375191 @default.
- W2197084977 hasConcept C99138194 @default.
- W2197084977 hasConceptScore W2197084977C105795698 @default.
- W2197084977 hasConceptScore W2197084977C11413529 @default.
- W2197084977 hasConceptScore W2197084977C179518139 @default.
- W2197084977 hasConceptScore W2197084977C33923547 @default.
- W2197084977 hasConceptScore W2197084977C38652104 @default.
- W2197084977 hasConceptScore W2197084977C41008148 @default.
- W2197084977 hasConceptScore W2197084977C48372109 @default.
- W2197084977 hasConceptScore W2197084977C63435697 @default.
- W2197084977 hasConceptScore W2197084977C80444323 @default.
- W2197084977 hasConceptScore W2197084977C94375191 @default.
- W2197084977 hasConceptScore W2197084977C99138194 @default.
- W2197084977 hasLocation W21970849771 @default.
- W2197084977 hasOpenAccess W2197084977 @default.
- W2197084977 hasPrimaryLocation W21970849771 @default.
- W2197084977 hasRelatedWork W1996787397 @default.
- W2197084977 hasRelatedWork W2014463444 @default.
- W2197084977 hasRelatedWork W2055498716 @default.
- W2197084977 hasRelatedWork W2088296667 @default.
- W2197084977 hasRelatedWork W2111298487 @default.
- W2197084977 hasRelatedWork W2134880816 @default.
- W2197084977 hasRelatedWork W2510680828 @default.
- W2197084977 hasRelatedWork W2963758661 @default.
- W2197084977 hasRelatedWork W3023219121 @default.
- W2197084977 hasRelatedWork W4308157887 @default.
- W2197084977 isParatext "false" @default.
- W2197084977 isRetracted "false" @default.
- W2197084977 magId "2197084977" @default.
- W2197084977 workType "article" @default.