Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912573985> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2912573985 endingPage "314" @default.
- W2912573985 startingPage "303" @default.
- W2912573985 abstract "This paper tackles the challenging problem of multi-shot person re-identification with Convolutional Neural Network (CNN). As no prior information about how importance each instance plays, it is non-trivial to exploit the interaction information shared by the multi-shot images to help identification. Traditional CNN is in single-shot architecture, then how to utilize the interaction information provided by multi-shot images becomes an important problem to solve. Furthermore, as data augmentation methods are not strictly label-preserving, it increases the difficulty to select discriminative instance for CNN training. In this paper, we propose a weakly supervised CNN framework named Multi-Instance Convolutional Neural Network (MICNN) to solve the aforementioned problem. We develop two paradigms, i.e., Embedding-Space paradigm and Instance-Space paradigm, which re-formulate the person re-identification problem as a multi-instance verification problem with part-based features extracted by neural network. We respectively devise a specific bag-level loss function which incorporates the characteristics of the multi-instance problem for each paradigm. Experiments show that the proposed IS method outperforms many related state-of-the-art techniques on four benchmark datasets: CUHK03, SYSUm, RAiD and Market-1501." @default.
- W2912573985 created "2019-02-21" @default.
- W2912573985 creator A5075877965 @default.
- W2912573985 creator A5083973158 @default.
- W2912573985 creator A5086178628 @default.
- W2912573985 creator A5087248518 @default.
- W2912573985 date "2019-04-01" @default.
- W2912573985 modified "2023-09-30" @default.
- W2912573985 title "Multi-Instance Convolutional Neural Network for multi-shot person re-identification" @default.
- W2912573985 cites W2010792435 @default.
- W2912573985 cites W2149648623 @default.
- W2912573985 cites W2344858100 @default.
- W2912573985 cites W2415640507 @default.
- W2912573985 cites W2531897166 @default.
- W2912573985 cites W2586899202 @default.
- W2912573985 cites W2590927326 @default.
- W2912573985 cites W2743223260 @default.
- W2912573985 cites W2809898047 @default.
- W2912573985 doi "https://doi.org/10.1016/j.neucom.2019.01.076" @default.
- W2912573985 hasPublicationYear "2019" @default.
- W2912573985 type Work @default.
- W2912573985 sameAs 2912573985 @default.
- W2912573985 citedByCount "7" @default.
- W2912573985 countsByYear W29125739852019 @default.
- W2912573985 countsByYear W29125739852020 @default.
- W2912573985 countsByYear W29125739852021 @default.
- W2912573985 countsByYear W29125739852022 @default.
- W2912573985 countsByYear W29125739852023 @default.
- W2912573985 crossrefType "journal-article" @default.
- W2912573985 hasAuthorship W2912573985A5075877965 @default.
- W2912573985 hasAuthorship W2912573985A5083973158 @default.
- W2912573985 hasAuthorship W2912573985A5086178628 @default.
- W2912573985 hasAuthorship W2912573985A5087248518 @default.
- W2912573985 hasConcept C116834253 @default.
- W2912573985 hasConcept C119857082 @default.
- W2912573985 hasConcept C13280743 @default.
- W2912573985 hasConcept C153180895 @default.
- W2912573985 hasConcept C154945302 @default.
- W2912573985 hasConcept C185798385 @default.
- W2912573985 hasConcept C205649164 @default.
- W2912573985 hasConcept C41008148 @default.
- W2912573985 hasConcept C41608201 @default.
- W2912573985 hasConcept C59822182 @default.
- W2912573985 hasConcept C81363708 @default.
- W2912573985 hasConcept C86803240 @default.
- W2912573985 hasConcept C97931131 @default.
- W2912573985 hasConceptScore W2912573985C116834253 @default.
- W2912573985 hasConceptScore W2912573985C119857082 @default.
- W2912573985 hasConceptScore W2912573985C13280743 @default.
- W2912573985 hasConceptScore W2912573985C153180895 @default.
- W2912573985 hasConceptScore W2912573985C154945302 @default.
- W2912573985 hasConceptScore W2912573985C185798385 @default.
- W2912573985 hasConceptScore W2912573985C205649164 @default.
- W2912573985 hasConceptScore W2912573985C41008148 @default.
- W2912573985 hasConceptScore W2912573985C41608201 @default.
- W2912573985 hasConceptScore W2912573985C59822182 @default.
- W2912573985 hasConceptScore W2912573985C81363708 @default.
- W2912573985 hasConceptScore W2912573985C86803240 @default.
- W2912573985 hasConceptScore W2912573985C97931131 @default.
- W2912573985 hasFunder F4320321001 @default.
- W2912573985 hasFunder F4320323086 @default.
- W2912573985 hasFunder F4320335787 @default.
- W2912573985 hasLocation W29125739851 @default.
- W2912573985 hasOpenAccess W2912573985 @default.
- W2912573985 hasPrimaryLocation W29125739851 @default.
- W2912573985 hasRelatedWork W1972656095 @default.
- W2912573985 hasRelatedWork W2024160000 @default.
- W2912573985 hasRelatedWork W2061273563 @default.
- W2912573985 hasRelatedWork W2285052147 @default.
- W2912573985 hasRelatedWork W2729514902 @default.
- W2912573985 hasRelatedWork W2743258233 @default.
- W2912573985 hasRelatedWork W2773500201 @default.
- W2912573985 hasRelatedWork W2998168123 @default.
- W2912573985 hasRelatedWork W4287995534 @default.
- W2912573985 hasRelatedWork W4319301798 @default.
- W2912573985 hasVolume "337" @default.
- W2912573985 isParatext "false" @default.
- W2912573985 isRetracted "false" @default.
- W2912573985 magId "2912573985" @default.
- W2912573985 workType "article" @default.