Matches in SemOpenAlex for { <https://semopenalex.org/work/W2524717549> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2524717549 abstract "In the literature of cross-modal search, most methods employ linear models to pursue hash codes that preserve data similarity, in terms of Euclidean distance, both within-modal and across-modal. However, data can be quite different across modalities. It is known that the behavior of Euclidean distance/similarity between datapoints can be drastically different in linear spaces of different dimensionality. In this paper, we identify this of dimensionality problem in cross-modal search that may harm most of distance-based methods. We propose a semi-supervised nonlinear probabilistic cross-modal hashing method, namely Neighborhood-Preserving Hashing (NPH), to alleviate the negative effect due to the variation of issue. Inspired by tSNE cite{tSNE_van2008visualizing}, rather than preserve pairwise data distances, we propose to learn hash codes that preserve neighborhood relationship of datapoints via matching their conditional distribution derived from distance to that of datapoints of multi-modalities. Experimental results on three real-world datasets demonstrate that the proposed method outperforms the state-of-the-art distance-based semi-supervised cross-modal hashing methods as well as many fully-supervised ones." @default.
- W2524717549 created "2016-10-07" @default.
- W2524717549 creator A5001498982 @default.
- W2524717549 creator A5070194869 @default.
- W2524717549 date "2016-10-01" @default.
- W2524717549 modified "2023-09-26" @default.
- W2524717549 title "Neighborhood-Preserving Hashing for Large-Scale Cross-Modal Search" @default.
- W2524717549 cites W1922199343 @default.
- W2524717549 cites W1970055505 @default.
- W2524717549 cites W1976258951 @default.
- W2524717549 cites W2007972815 @default.
- W2524717549 cites W2014812507 @default.
- W2524717549 cites W2015175493 @default.
- W2524717549 cites W2039805092 @default.
- W2524717549 cites W2044195942 @default.
- W2524717549 cites W2057228822 @default.
- W2524717549 cites W2064797228 @default.
- W2524717549 cites W2070272652 @default.
- W2524717549 cites W2087193308 @default.
- W2524717549 cites W2106277773 @default.
- W2524717549 cites W2145607950 @default.
- W2524717549 cites W2159373756 @default.
- W2524717549 cites W2162006472 @default.
- W2524717549 cites W2171790913 @default.
- W2524717549 doi "https://doi.org/10.1145/2964284.2967241" @default.
- W2524717549 hasPublicationYear "2016" @default.
- W2524717549 type Work @default.
- W2524717549 sameAs 2524717549 @default.
- W2524717549 citedByCount "4" @default.
- W2524717549 countsByYear W25247175492017 @default.
- W2524717549 countsByYear W25247175492019 @default.
- W2524717549 countsByYear W25247175492022 @default.
- W2524717549 crossrefType "proceedings-article" @default.
- W2524717549 hasAuthorship W2524717549A5001498982 @default.
- W2524717549 hasAuthorship W2524717549A5070194869 @default.
- W2524717549 hasConcept C116058348 @default.
- W2524717549 hasConcept C122907437 @default.
- W2524717549 hasConcept C138111711 @default.
- W2524717549 hasConcept C185592680 @default.
- W2524717549 hasConcept C188027245 @default.
- W2524717549 hasConcept C205649164 @default.
- W2524717549 hasConcept C2778755073 @default.
- W2524717549 hasConcept C38652104 @default.
- W2524717549 hasConcept C41008148 @default.
- W2524717549 hasConcept C56856351 @default.
- W2524717549 hasConcept C58640448 @default.
- W2524717549 hasConcept C67388219 @default.
- W2524717549 hasConcept C71139939 @default.
- W2524717549 hasConcept C99138194 @default.
- W2524717549 hasConceptScore W2524717549C116058348 @default.
- W2524717549 hasConceptScore W2524717549C122907437 @default.
- W2524717549 hasConceptScore W2524717549C138111711 @default.
- W2524717549 hasConceptScore W2524717549C185592680 @default.
- W2524717549 hasConceptScore W2524717549C188027245 @default.
- W2524717549 hasConceptScore W2524717549C205649164 @default.
- W2524717549 hasConceptScore W2524717549C2778755073 @default.
- W2524717549 hasConceptScore W2524717549C38652104 @default.
- W2524717549 hasConceptScore W2524717549C41008148 @default.
- W2524717549 hasConceptScore W2524717549C56856351 @default.
- W2524717549 hasConceptScore W2524717549C58640448 @default.
- W2524717549 hasConceptScore W2524717549C67388219 @default.
- W2524717549 hasConceptScore W2524717549C71139939 @default.
- W2524717549 hasConceptScore W2524717549C99138194 @default.
- W2524717549 hasLocation W25247175491 @default.
- W2524717549 hasOpenAccess W2524717549 @default.
- W2524717549 hasPrimaryLocation W25247175491 @default.
- W2524717549 hasRelatedWork W102859714 @default.
- W2524717549 hasRelatedWork W2044784665 @default.
- W2524717549 hasRelatedWork W2076162755 @default.
- W2524717549 hasRelatedWork W2105130984 @default.
- W2524717549 hasRelatedWork W2149143947 @default.
- W2524717549 hasRelatedWork W2156435549 @default.
- W2524717549 hasRelatedWork W2160675239 @default.
- W2524717549 hasRelatedWork W2334522381 @default.
- W2524717549 hasRelatedWork W2390631617 @default.
- W2524717549 hasRelatedWork W2811247857 @default.
- W2524717549 isParatext "false" @default.
- W2524717549 isRetracted "false" @default.
- W2524717549 magId "2524717549" @default.
- W2524717549 workType "article" @default.