Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951808862> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2951808862 abstract "With the dramatic increase of multi-media data on the Internet, cross-modal retrieval has become an important and valuable task in searching systems. The key challenge of this task is how to build the correlation between multi-modal data. Most existing approaches only focus on dealing with paired data. They use pairwise relationship of multi-modal data for exploring the correlation between them. However, in practice, unpaired data are more common on the Internet but few methods pay attention to them. To utilize both paired and unpaired data, we propose a one-stream framework triplet fusion network hashing (TFNH), which mainly consists of two parts. The first part is a triplet network which is used to handle both kinds of data, with the help of zero padding operation. The second part consists of two data classifiers, which are used to bridge the gap between paired and unpaired data. In addition, we embed manifold learning into the framework for preserving both inter and intra modal similarity, exploring the relationship between unpaired and paired data and bridging the gap between them in learning process. Extensive experiments show that the proposed approach outperforms several state-of-the-art methods on two datasets in paired scenario. We further evaluate its ability of handling unpaired scenario and robustness in regard to pairwise constraint. The results show that even we discard 50% data under the setting in [19], the performance of TFNH is still better than that of other unpaired approaches and that only 70% pairwise relationships are preserved, TFNH can still outperform almost all paired approaches." @default.
- W2951808862 created "2019-06-27" @default.
- W2951808862 creator A5007783188 @default.
- W2951808862 creator A5021687717 @default.
- W2951808862 creator A5038516431 @default.
- W2951808862 creator A5051404919 @default.
- W2951808862 creator A5061132699 @default.
- W2951808862 creator A5086045569 @default.
- W2951808862 date "2019-06-05" @default.
- W2951808862 modified "2023-10-16" @default.
- W2951808862 title "Triplet Fusion Network Hashing for Unpaired Cross-Modal Retrieval" @default.
- W2951808862 cites W1835419070 @default.
- W2951808862 cites W1922199343 @default.
- W2951808862 cites W1964073652 @default.
- W2951808862 cites W1970055505 @default.
- W2951808862 cites W1974647172 @default.
- W2951808862 cites W1976258951 @default.
- W2951808862 cites W1996219872 @default.
- W2951808862 cites W1996936615 @default.
- W2951808862 cites W2029205712 @default.
- W2951808862 cites W2049993534 @default.
- W2951808862 cites W2051666324 @default.
- W2951808862 cites W2064797228 @default.
- W2951808862 cites W2076511276 @default.
- W2951808862 cites W2086958058 @default.
- W2951808862 cites W2100235303 @default.
- W2951808862 cites W2153273131 @default.
- W2951808862 cites W2155803963 @default.
- W2951808862 cites W2159373756 @default.
- W2951808862 cites W2162670057 @default.
- W2951808862 cites W2210322478 @default.
- W2951808862 cites W2266728343 @default.
- W2951808862 cites W2345649690 @default.
- W2951808862 cites W2591669147 @default.
- W2951808862 cites W2740755807 @default.
- W2951808862 cites W2748725735 @default.
- W2951808862 cites W2765440071 @default.
- W2951808862 cites W2808336545 @default.
- W2951808862 cites W2808464100 @default.
- W2951808862 cites W2963187862 @default.
- W2951808862 cites W2963775347 @default.
- W2951808862 cites W3106512200 @default.
- W2951808862 doi "https://doi.org/10.1145/3323873.3325041" @default.
- W2951808862 hasPublicationYear "2019" @default.
- W2951808862 type Work @default.
- W2951808862 sameAs 2951808862 @default.
- W2951808862 citedByCount "11" @default.
- W2951808862 countsByYear W29518088622020 @default.
- W2951808862 countsByYear W29518088622021 @default.
- W2951808862 countsByYear W29518088622022 @default.
- W2951808862 countsByYear W29518088622023 @default.
- W2951808862 crossrefType "proceedings-article" @default.
- W2951808862 hasAuthorship W2951808862A5007783188 @default.
- W2951808862 hasAuthorship W2951808862A5021687717 @default.
- W2951808862 hasAuthorship W2951808862A5038516431 @default.
- W2951808862 hasAuthorship W2951808862A5051404919 @default.
- W2951808862 hasAuthorship W2951808862A5061132699 @default.
- W2951808862 hasAuthorship W2951808862A5086045569 @default.
- W2951808862 hasBestOaLocation W29518088621 @default.
- W2951808862 hasConcept C138885662 @default.
- W2951808862 hasConcept C154945302 @default.
- W2951808862 hasConcept C158525013 @default.
- W2951808862 hasConcept C188027245 @default.
- W2951808862 hasConcept C192562407 @default.
- W2951808862 hasConcept C23123220 @default.
- W2951808862 hasConcept C38652104 @default.
- W2951808862 hasConcept C41008148 @default.
- W2951808862 hasConcept C41895202 @default.
- W2951808862 hasConcept C71139939 @default.
- W2951808862 hasConcept C99138194 @default.
- W2951808862 hasConceptScore W2951808862C138885662 @default.
- W2951808862 hasConceptScore W2951808862C154945302 @default.
- W2951808862 hasConceptScore W2951808862C158525013 @default.
- W2951808862 hasConceptScore W2951808862C188027245 @default.
- W2951808862 hasConceptScore W2951808862C192562407 @default.
- W2951808862 hasConceptScore W2951808862C23123220 @default.
- W2951808862 hasConceptScore W2951808862C38652104 @default.
- W2951808862 hasConceptScore W2951808862C41008148 @default.
- W2951808862 hasConceptScore W2951808862C41895202 @default.
- W2951808862 hasConceptScore W2951808862C71139939 @default.
- W2951808862 hasConceptScore W2951808862C99138194 @default.
- W2951808862 hasFunder F4320321001 @default.
- W2951808862 hasLocation W29518088621 @default.
- W2951808862 hasOpenAccess W2951808862 @default.
- W2951808862 hasPrimaryLocation W29518088621 @default.
- W2951808862 hasRelatedWork W2101955803 @default.
- W2951808862 hasRelatedWork W2115485936 @default.
- W2951808862 hasRelatedWork W2119214692 @default.
- W2951808862 hasRelatedWork W2144190808 @default.
- W2951808862 hasRelatedWork W2357241418 @default.
- W2951808862 hasRelatedWork W2366644548 @default.
- W2951808862 hasRelatedWork W2376314740 @default.
- W2951808862 hasRelatedWork W2384888906 @default.
- W2951808862 hasRelatedWork W2469626427 @default.
- W2951808862 hasRelatedWork W2909016198 @default.
- W2951808862 isParatext "false" @default.
- W2951808862 isRetracted "false" @default.
- W2951808862 magId "2951808862" @default.
- W2951808862 workType "article" @default.