FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2799696601> ?p ?o ?g. }

• W2799696601 endingPage "82" @default.
• W2799696601 startingPage "74" @default.
• W2799696601 abstract "Person re-identification (PReID), which aims to re-identity a pedestrian from multiple non-overlapping cameras, has been significantly improved by deep learning system. There exist two popular deep frameworks used for PReID, i.e., identification and triplet models. Since these two frameworks have different loss functions, they have their own advantages and disadvantages. To combine the both advantages of two frameworks, in this paper, we propose using the triplet and Online Instance Matching (OIM) losses to train the carefully designed network. Given a triplet input images, the combined model can output the identities of the input images and learn a corresponding similarity measurement simultaneously. Experiments on CUHK01, CUHK03, Market-1501, and DukeMTMC-reID datasets demonstrate that the proposed model outperforms the compared state-of-the-art methods in most cases." @default.
• W2799696601 created "2018-05-17" @default.
• W2799696601 creator A5007724310 @default.
• W2799696601 creator A5060381913 @default.
• W2799696601 creator A5081080536 @default.
• W2799696601 creator A5087166824 @default.
• W2799696601 date "2019-05-01" @default.
• W2799696601 modified "2023-10-17" @default.
• W2799696601 title "A deep model with combined losses for person re-identification" @default.
• W2799696601 cites W1411285485 @default.
• W2799696601 cites W1518138188 @default.
• W2799696601 cites W166429404 @default.
• W2799696601 cites W1920259731 @default.
• W2799696601 cites W1928419358 @default.
• W2799696601 cites W1971955426 @default.
• W2799696601 cites W1977737282 @default.
• W2799696601 cites W1978201669 @default.
• W2799696601 cites W1979260620 @default.
• W2799696601 cites W1991209141 @default.
• W2799696601 cites W1991452654 @default.
• W2799696601 cites W2001012564 @default.
• W2799696601 cites W2058232500 @default.
• W2799696601 cites W2065350495 @default.
• W2799696601 cites W2090123586 @default.
• W2799696601 cites W2106442491 @default.
• W2799696601 cites W2108598243 @default.
• W2799696601 cites W2126262069 @default.
• W2799696601 cites W2135442311 @default.
• W2799696601 cites W2150248355 @default.
• W2799696601 cites W2161710599 @default.
• W2799696601 cites W2194775991 @default.
• W2799696601 cites W2300840837 @default.
• W2799696601 cites W2326772079 @default.
• W2799696601 cites W2414767909 @default.
• W2799696601 cites W2433217581 @default.
• W2799696601 cites W2474013209 @default.
• W2799696601 cites W2475284720 @default.
• W2799696601 cites W2491664569 @default.
• W2799696601 cites W2497344197 @default.
• W2799696601 cites W2502225121 @default.
• W2799696601 cites W2503931548 @default.
• W2799696601 cites W2526833393 @default.
• W2799696601 cites W2738406610 @default.
• W2799696601 cites W2963574614 @default.
• W2799696601 cites W3098057481 @default.
• W2799696601 cites W3099224353 @default.
• W2799696601 cites W4232920930 @default.
• W2799696601 cites W46454230 @default.
• W2799696601 doi "https://doi.org/10.1016/j.cogsys.2018.04.003" @default.
• W2799696601 hasPublicationYear "2019" @default.
• W2799696601 type Work @default.
• W2799696601 sameAs 2799696601 @default.
• W2799696601 citedByCount "28" @default.
• W2799696601 countsByYear W27996966012019 @default.
• W2799696601 countsByYear W27996966012020 @default.
• W2799696601 countsByYear W27996966012021 @default.
• W2799696601 countsByYear W27996966012022 @default.
• W2799696601 countsByYear W27996966012023 @default.
• W2799696601 crossrefType "journal-article" @default.
• W2799696601 hasAuthorship W2799696601A5007724310 @default.
• W2799696601 hasAuthorship W2799696601A5060381913 @default.
• W2799696601 hasAuthorship W2799696601A5081080536 @default.
• W2799696601 hasAuthorship W2799696601A5087166824 @default.
• W2799696601 hasConcept C103278499 @default.
• W2799696601 hasConcept C104122410 @default.
• W2799696601 hasConcept C105795698 @default.
• W2799696601 hasConcept C108583219 @default.
• W2799696601 hasConcept C115961682 @default.
• W2799696601 hasConcept C116834253 @default.
• W2799696601 hasConcept C119857082 @default.
• W2799696601 hasConcept C121332964 @default.
• W2799696601 hasConcept C153180895 @default.
• W2799696601 hasConcept C154945302 @default.
• W2799696601 hasConcept C165064840 @default.
• W2799696601 hasConcept C24890656 @default.
• W2799696601 hasConcept C2778355321 @default.
• W2799696601 hasConcept C31972630 @default.
• W2799696601 hasConcept C33923547 @default.
• W2799696601 hasConcept C41008148 @default.
• W2799696601 hasConcept C59822182 @default.
• W2799696601 hasConcept C86803240 @default.
• W2799696601 hasConceptScore W2799696601C103278499 @default.
• W2799696601 hasConceptScore W2799696601C104122410 @default.
• W2799696601 hasConceptScore W2799696601C105795698 @default.
• W2799696601 hasConceptScore W2799696601C108583219 @default.
• W2799696601 hasConceptScore W2799696601C115961682 @default.
• W2799696601 hasConceptScore W2799696601C116834253 @default.
• W2799696601 hasConceptScore W2799696601C119857082 @default.
• W2799696601 hasConceptScore W2799696601C121332964 @default.
• W2799696601 hasConceptScore W2799696601C153180895 @default.
• W2799696601 hasConceptScore W2799696601C154945302 @default.
• W2799696601 hasConceptScore W2799696601C165064840 @default.
• W2799696601 hasConceptScore W2799696601C24890656 @default.
• W2799696601 hasConceptScore W2799696601C2778355321 @default.
• W2799696601 hasConceptScore W2799696601C31972630 @default.
• W2799696601 hasConceptScore W2799696601C33923547 @default.
• W2799696601 hasConceptScore W2799696601C41008148 @default.
• W2799696601 hasConceptScore W2799696601C59822182 @default.

• next