Matches in SemOpenAlex for { <https://semopenalex.org/work/W2962921588> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2962921588 endingPage "829" @default.
- W2962921588 startingPage "811" @default.
- W2962921588 abstract "In this paper, we study the problem of transfer learning with the attribute data. In the transfer learning problem, we want to leverage the data of the auxiliary and the target domains to build an effective model for the classification problem in the target domain. Meanwhile, the attributes are naturally stable cross different domains. This strongly motives us to learn effective domain transfer attribute representations. To this end, we proposed to embed the attributes of the data to a common space using the powerful convolutional neural network (CNN) model. The convolutional representations of the data points are mapped to the corresponding attributes so that they can be effective embedding of the attributes. We also represent the data of different domains by a domain-independent CNN, ant a domain-specific CNN and combine their outputs with the attribute embedding to build the classification model. An joint learning framework is constructed to minimise the classification errors, the attribute mapping error, the mismatching of the domain-independent representations cross different domains, and to encourage the neighbourhood smoothness of representations in the target domain. The minimisation problem is solved by an iterative algorithm based on gradient descent. Experiments over benchmark data-sets of person re-identification, bankruptcy prediction and spam email detection show the effectiveness of the proposed method." @default.
- W2962921588 created "2019-07-30" @default.
- W2962921588 creator A5003240878 @default.
- W2962921588 creator A5031857164 @default.
- W2962921588 date "2018-05-18" @default.
- W2962921588 modified "2023-09-27" @default.
- W2962921588 title "Domain transfer convolutional attribute embedding" @default.
- W2962921588 cites W2062510133 @default.
- W2962921588 cites W2086735993 @default.
- W2962921588 cites W2088801701 @default.
- W2962921588 cites W2343952097 @default.
- W2962921588 cites W2587293726 @default.
- W2962921588 cites W2592051407 @default.
- W2962921588 cites W2592215117 @default.
- W2962921588 cites W2592680600 @default.
- W2962921588 cites W2611250037 @default.
- W2962921588 cites W2616725845 @default.
- W2962921588 cites W2617208058 @default.
- W2962921588 cites W2622202994 @default.
- W2962921588 cites W2654355181 @default.
- W2962921588 cites W2661392252 @default.
- W2962921588 cites W2708785142 @default.
- W2962921588 cites W2721356266 @default.
- W2962921588 cites W2732937366 @default.
- W2962921588 cites W2735302890 @default.
- W2962921588 cites W2735326783 @default.
- W2962921588 cites W2743316710 @default.
- W2962921588 cites W760855798 @default.
- W2962921588 doi "https://doi.org/10.1080/0952813x.2018.1467499" @default.
- W2962921588 hasPublicationYear "2018" @default.
- W2962921588 type Work @default.
- W2962921588 sameAs 2962921588 @default.
- W2962921588 citedByCount "1" @default.
- W2962921588 countsByYear W29629215882018 @default.
- W2962921588 crossrefType "journal-article" @default.
- W2962921588 hasAuthorship W2962921588A5003240878 @default.
- W2962921588 hasAuthorship W2962921588A5031857164 @default.
- W2962921588 hasBestOaLocation W29629215882 @default.
- W2962921588 hasConcept C119857082 @default.
- W2962921588 hasConcept C124101348 @default.
- W2962921588 hasConcept C134306372 @default.
- W2962921588 hasConcept C150899416 @default.
- W2962921588 hasConcept C153083717 @default.
- W2962921588 hasConcept C153180895 @default.
- W2962921588 hasConcept C153258448 @default.
- W2962921588 hasConcept C154945302 @default.
- W2962921588 hasConcept C33923547 @default.
- W2962921588 hasConcept C36503486 @default.
- W2962921588 hasConcept C41008148 @default.
- W2962921588 hasConcept C41608201 @default.
- W2962921588 hasConcept C50644808 @default.
- W2962921588 hasConcept C81363708 @default.
- W2962921588 hasConceptScore W2962921588C119857082 @default.
- W2962921588 hasConceptScore W2962921588C124101348 @default.
- W2962921588 hasConceptScore W2962921588C134306372 @default.
- W2962921588 hasConceptScore W2962921588C150899416 @default.
- W2962921588 hasConceptScore W2962921588C153083717 @default.
- W2962921588 hasConceptScore W2962921588C153180895 @default.
- W2962921588 hasConceptScore W2962921588C153258448 @default.
- W2962921588 hasConceptScore W2962921588C154945302 @default.
- W2962921588 hasConceptScore W2962921588C33923547 @default.
- W2962921588 hasConceptScore W2962921588C36503486 @default.
- W2962921588 hasConceptScore W2962921588C41008148 @default.
- W2962921588 hasConceptScore W2962921588C41608201 @default.
- W2962921588 hasConceptScore W2962921588C50644808 @default.
- W2962921588 hasConceptScore W2962921588C81363708 @default.
- W2962921588 hasFunder F4320321001 @default.
- W2962921588 hasFunder F4320327557 @default.
- W2962921588 hasIssue "6" @default.
- W2962921588 hasLocation W29629215881 @default.
- W2962921588 hasLocation W29629215882 @default.
- W2962921588 hasLocation W29629215883 @default.
- W2962921588 hasOpenAccess W2962921588 @default.
- W2962921588 hasPrimaryLocation W29629215881 @default.
- W2962921588 hasRelatedWork W2738221750 @default.
- W2962921588 hasRelatedWork W2972069047 @default.
- W2962921588 hasRelatedWork W3012393889 @default.
- W2962921588 hasRelatedWork W3038075430 @default.
- W2962921588 hasRelatedWork W3091976719 @default.
- W2962921588 hasRelatedWork W3135818718 @default.
- W2962921588 hasRelatedWork W3153891452 @default.
- W2962921588 hasRelatedWork W4312501200 @default.
- W2962921588 hasRelatedWork W4313050734 @default.
- W2962921588 hasRelatedWork W4366224123 @default.
- W2962921588 hasVolume "30" @default.
- W2962921588 isParatext "false" @default.
- W2962921588 isRetracted "false" @default.
- W2962921588 magId "2962921588" @default.
- W2962921588 workType "article" @default.