FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949660180> ?p ?o ?g. }

• W2949660180 abstract "Person re-identification has achieved great progress with deep convolutional neural networks. However, most previous methods focus on learning individual appearance feature embedding, and it is hard for the models to handle difficult situations with different illumination, large pose variance and occlusion. In this work, we take a step further and consider employing context information for person search. For a probe-gallery pair, we first propose a contextual instance expansion module, which employs a relative attention module to search and filter useful context information in the scene. We also build a graph learning framework to effectively employ context pairs to update target similarity. These two modules are built on top of a joint detection and instance feature learning framework, which improves the discriminativeness of the learned features. The proposed framework achieves state-of-the-art performance on two widely used person search datasets." @default.
• W2949660180 created "2019-06-27" @default.
• W2949660180 creator A5014362734 @default.
• W2949660180 creator A5019708391 @default.
• W2949660180 creator A5039837606 @default.
• W2949660180 creator A5048907728 @default.
• W2949660180 creator A5059372397 @default.
• W2949660180 creator A5068293265 @default.
• W2949660180 date "2019-04-03" @default.
• W2949660180 modified "2023-09-28" @default.
• W2949660180 title "Learning Context Graph for Person Search" @default.
• W2949660180 cites W1518138188 @default.
• W2949660180 cites W1709635438 @default.
• W2949660180 cites W1949591461 @default.
• W2949660180 cites W1979260620 @default.
• W2949660180 cites W2042127251 @default.
• W2949660180 cites W2046835352 @default.
• W2949660180 cites W2068042582 @default.
• W2949660180 cites W2079972027 @default.
• W2949660180 cites W2085161844 @default.
• W2949660180 cites W2108598243 @default.
• W2949660180 cites W2163605009 @default.
• W2949660180 cites W2194775991 @default.
• W2949660180 cites W2204750386 @default.
• W2949660180 cites W2258844511 @default.
• W2949660180 cites W2300840837 @default.
• W2949660180 cites W2475284720 @default.
• W2949660180 cites W2519803806 @default.
• W2949660180 cites W2520757991 @default.
• W2949660180 cites W2583528645 @default.
• W2949660180 cites W2591711955 @default.
• W2949660180 cites W2596839961 @default.
• W2949660180 cites W2606377603 @default.
• W2949660180 cites W2613718673 @default.
• W2949660180 cites W2622829582 @default.
• W2949660180 cites W2725422033 @default.
• W2949660180 cites W2755066373 @default.
• W2949660180 cites W2757028014 @default.
• W2949660180 cites W2766657036 @default.
• W2949660180 cites W2770468159 @default.
• W2949660180 cites W2788552534 @default.
• W2949660180 cites W2798874329 @default.
• W2949660180 cites W2802152130 @default.
• W2949660180 cites W2806331055 @default.
• W2949660180 cites W2883638665 @default.
• W2949660180 cites W2884030607 @default.
• W2949660180 cites W2886356788 @default.
• W2949660180 cites W2888096830 @default.
• W2949660180 cites W2897666265 @default.
• W2949660180 cites W2962938888 @default.
• W2949660180 cites W2963371610 @default.
• W2949660180 cites W2963438548 @default.
• W2949660180 cites W2963574614 @default.
• W2949660180 cites W2963639915 @default.
• W2949660180 cites W2963656477 @default.
• W2949660180 cites W2963787027 @default.
• W2949660180 cites W2963901085 @default.
• W2949660180 cites W2964015378 @default.
• W2949660180 cites W3098711604 @default.
• W2949660180 cites W2800174643 @default.
• W2949660180 doi "https://doi.org/10.48550/arxiv.1904.01830" @default.
• W2949660180 hasPublicationYear "2019" @default.
• W2949660180 type Work @default.
• W2949660180 sameAs 2949660180 @default.
• W2949660180 citedByCount "1" @default.
• W2949660180 countsByYear W29496601802021 @default.
• W2949660180 crossrefType "posted-content" @default.
• W2949660180 hasAuthorship W2949660180A5014362734 @default.
• W2949660180 hasAuthorship W2949660180A5019708391 @default.
• W2949660180 hasAuthorship W2949660180A5039837606 @default.
• W2949660180 hasAuthorship W2949660180A5048907728 @default.
• W2949660180 hasAuthorship W2949660180A5059372397 @default.
• W2949660180 hasAuthorship W2949660180A5068293265 @default.
• W2949660180 hasBestOaLocation W29496601801 @default.
• W2949660180 hasConcept C103278499 @default.
• W2949660180 hasConcept C106131492 @default.
• W2949660180 hasConcept C108583219 @default.
• W2949660180 hasConcept C115961682 @default.
• W2949660180 hasConcept C119857082 @default.
• W2949660180 hasConcept C120665830 @default.
• W2949660180 hasConcept C121332964 @default.
• W2949660180 hasConcept C132525143 @default.
• W2949660180 hasConcept C138885662 @default.
• W2949660180 hasConcept C151730666 @default.
• W2949660180 hasConcept C153180895 @default.
• W2949660180 hasConcept C154945302 @default.
• W2949660180 hasConcept C192209626 @default.
• W2949660180 hasConcept C2776401178 @default.
• W2949660180 hasConcept C2779343474 @default.
• W2949660180 hasConcept C2779597229 @default.
• W2949660180 hasConcept C31972630 @default.
• W2949660180 hasConcept C41008148 @default.
• W2949660180 hasConcept C41608201 @default.
• W2949660180 hasConcept C41895202 @default.
• W2949660180 hasConcept C59404180 @default.
• W2949660180 hasConcept C75564084 @default.
• W2949660180 hasConcept C80444323 @default.
• W2949660180 hasConcept C81363708 @default.
• W2949660180 hasConcept C86803240 @default.
• W2949660180 hasConceptScore W2949660180C103278499 @default.

• next