FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280491878> ?p ?o ?g. }

• W4280491878 endingPage "2672" @default.
• W4280491878 startingPage "2656" @default.
• W4280491878 abstract "Video surveillance is an indispensable part of the smart city for public safety and security. Person Re-Identification (Re-ID), as one of elementary learning tasks for video surveillance, is to track and identify a given pedestrian in a multi-camera scene. In general, most existing methods has firstly adopted a CNN based detector to obtain the cropped pedestrian image, it then aims to learn a specific distance metric for retrieval. However, unlabeled gallery images are generally overlooked and not utilized in the training. On the other hands, Manifold Embedding (ME) has well been applied to Person Re-ID as it is good to characterize the geometry of database associated with the query data. However, ME has its limitation to be scalable to large-scale data due to the huge computational complexity for graph construction and ranking. To handle this problem, we in this paper propose a novel scalable manifold embedding approach for Person Re-ID task. The new method is to incorporate both graph weight construction and manifold regularized term in the same framework. The graph we developed is discriminative and doubly-stochastic so that the side information has been considered so that it can enhance the clustering performances. The doubly-stochastic property can also guarantee the graph is highly robust and less sensitive to the parameters. Meriting from such a graph, we then incorporate the graph construction, the subspace learning method in the unified loss term. Therefore, the subspace results can be utilized into the graph construction, and the updated graph can in turn incorporate discriminative information for graph embedding. Extensive simulations is conducted based on three benchmark Person Re-ID datasets and the results verify that the proposed method can achieve better ranking performance compared with other state-of-the-art graph-based methods." @default.
• W4280491878 created "2022-05-22" @default.
• W4280491878 creator A5000776140 @default.
• W4280491878 creator A5020240685 @default.
• W4280491878 creator A5054304362 @default.
• W4280491878 creator A5061195038 @default.
• W4280491878 creator A5083581319 @default.
• W4280491878 creator A5086102702 @default.
• W4280491878 date "2022-05-11" @default.
• W4280491878 modified "2023-10-06" @default.
• W4280491878 title "Person re-identification via semi-supervised adaptive graph embedding" @default.
• W4280491878 cites W1982607940 @default.
• W4280491878 cites W1993603321 @default.
• W4280491878 cites W2001141328 @default.
• W4280491878 cites W2010379776 @default.
• W4280491878 cites W2018398888 @default.
• W4280491878 cites W2019863495 @default.
• W4280491878 cites W2035331133 @default.
• W4280491878 cites W2051549110 @default.
• W4280491878 cites W2053186076 @default.
• W4280491878 cites W2095469431 @default.
• W4280491878 cites W2156338447 @default.
• W4280491878 cites W2167665791 @default.
• W4280491878 cites W2313529869 @default.
• W4280491878 cites W2573268259 @default.
• W4280491878 cites W2604983939 @default.
• W4280491878 cites W2790153128 @default.
• W4280491878 cites W2891318845 @default.
• W4280491878 cites W2964247799 @default.
• W4280491878 cites W2970707935 @default.
• W4280491878 cites W297461772 @default.
• W4280491878 cites W3000783662 @default.
• W4280491878 cites W3033138310 @default.
• W4280491878 cites W3034457627 @default.
• W4280491878 cites W3082582306 @default.
• W4280491878 cites W3097321610 @default.
• W4280491878 cites W3100948281 @default.
• W4280491878 cites W3105077954 @default.
• W4280491878 cites W3128220219 @default.
• W4280491878 cites W3137790494 @default.
• W4280491878 cites W3176837226 @default.
• W4280491878 cites W3199999289 @default.
• W4280491878 cites W4229706427 @default.
• W4280491878 cites W71666767 @default.
• W4280491878 cites W745184511 @default.
• W4280491878 doi "https://doi.org/10.1007/s10489-022-03570-9" @default.
• W4280491878 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35578618" @default.
• W4280491878 hasPublicationYear "2022" @default.
• W4280491878 type Work @default.
• W4280491878 citedByCount "3" @default.
• W4280491878 countsByYear W42804918782022 @default.
• W4280491878 countsByYear W42804918782023 @default.
• W4280491878 crossrefType "journal-article" @default.
• W4280491878 hasAuthorship W4280491878A5000776140 @default.
• W4280491878 hasAuthorship W4280491878A5020240685 @default.
• W4280491878 hasAuthorship W4280491878A5054304362 @default.
• W4280491878 hasAuthorship W4280491878A5061195038 @default.
• W4280491878 hasAuthorship W4280491878A5083581319 @default.
• W4280491878 hasAuthorship W4280491878A5086102702 @default.
• W4280491878 hasBestOaLocation W42804918781 @default.
• W4280491878 hasConcept C119857082 @default.
• W4280491878 hasConcept C124101348 @default.
• W4280491878 hasConcept C132525143 @default.
• W4280491878 hasConcept C153180895 @default.
• W4280491878 hasConcept C154945302 @default.
• W4280491878 hasConcept C2779172887 @default.
• W4280491878 hasConcept C32834561 @default.
• W4280491878 hasConcept C41008148 @default.
• W4280491878 hasConcept C41608201 @default.
• W4280491878 hasConcept C48044578 @default.
• W4280491878 hasConcept C73555534 @default.
• W4280491878 hasConcept C75564084 @default.
• W4280491878 hasConcept C77088390 @default.
• W4280491878 hasConcept C80444323 @default.
• W4280491878 hasConcept C97931131 @default.
• W4280491878 hasConceptScore W4280491878C119857082 @default.
• W4280491878 hasConceptScore W4280491878C124101348 @default.
• W4280491878 hasConceptScore W4280491878C132525143 @default.
• W4280491878 hasConceptScore W4280491878C153180895 @default.
• W4280491878 hasConceptScore W4280491878C154945302 @default.
• W4280491878 hasConceptScore W4280491878C2779172887 @default.
• W4280491878 hasConceptScore W4280491878C32834561 @default.
• W4280491878 hasConceptScore W4280491878C41008148 @default.
• W4280491878 hasConceptScore W4280491878C41608201 @default.
• W4280491878 hasConceptScore W4280491878C48044578 @default.
• W4280491878 hasConceptScore W4280491878C73555534 @default.
• W4280491878 hasConceptScore W4280491878C75564084 @default.
• W4280491878 hasConceptScore W4280491878C77088390 @default.
• W4280491878 hasConceptScore W4280491878C80444323 @default.
• W4280491878 hasConceptScore W4280491878C97931131 @default.
• W4280491878 hasFunder F4320321001 @default.
• W4280491878 hasIssue "3" @default.
• W4280491878 hasLocation W42804918781 @default.
• W4280491878 hasLocation W42804918782 @default.
• W4280491878 hasLocation W42804918783 @default.
• W4280491878 hasOpenAccess W4280491878 @default.
• W4280491878 hasPrimaryLocation W42804918781 @default.
• W4280491878 hasRelatedWork W2082479932 @default.

• next