Matches in SemOpenAlex for { <https://semopenalex.org/work/W3105649115> ?p ?o ?g. }
- W3105649115 endingPage "12" @default.
- W3105649115 startingPage "1" @default.
- W3105649115 abstract "Despite recent remarkable progress, person re-identification (ReID) still suffers from a shortage of annotated training data. To deal with this problem, there has been a boost of interest in developing various data augmentation methods. In this paper, we are devoted to developing an end-to-end joint representation learning framework for the ReID task on the basis of a novel data augmentation strategy. Specifically, we regard the original training dataset as a source domain and generate the counterpart augmented domains through image channel shuffling. Accordingly, we design a symmetric classification network for ReID learning. By investigating the domain-level and identity-level relationship between domains, we use the idea of negative transfer and structural consistency to optimize the network for learning discriminative feature embeddings. Comprehensive experiments on some benchmark datasets demonstrate the effectiveness and robustness of our proposed approach. Source code is released at: https://github.com/flychen321/negative_transfer_reid." @default.
- W3105649115 created "2020-11-23" @default.
- W3105649115 creator A5021979312 @default.
- W3105649115 creator A5031308675 @default.
- W3105649115 creator A5040099999 @default.
- W3105649115 creator A5070818899 @default.
- W3105649115 date "2021-03-01" @default.
- W3105649115 modified "2023-09-29" @default.
- W3105649115 title "A negative transfer approach to person re-identification via domain augmentation" @default.
- W3105649115 cites W2204750386 @default.
- W3105649115 cites W2311508968 @default.
- W3105649115 cites W2549396809 @default.
- W3105649115 cites W2586899202 @default.
- W3105649115 cites W2766623491 @default.
- W3105649115 cites W2898047322 @default.
- W3105649115 cites W2914162688 @default.
- W3105649115 cites W2950059123 @default.
- W3105649115 cites W2962859295 @default.
- W3105649115 cites W2963000559 @default.
- W3105649115 cites W2963118547 @default.
- W3105649115 cites W2963180826 @default.
- W3105649115 cites W2963240485 @default.
- W3105649115 cites W2963289251 @default.
- W3105649115 cites W2963438548 @default.
- W3105649115 cites W2963506340 @default.
- W3105649115 cites W2963842104 @default.
- W3105649115 cites W2964140013 @default.
- W3105649115 cites W2964186374 @default.
- W3105649115 cites W2968039979 @default.
- W3105649115 cites W2970868824 @default.
- W3105649115 cites W2979920800 @default.
- W3105649115 cites W2979931389 @default.
- W3105649115 cites W2980827638 @default.
- W3105649115 cites W2981393440 @default.
- W3105649115 cites W2989938675 @default.
- W3105649115 cites W3009246260 @default.
- W3105649115 cites W3013975023 @default.
- W3105649115 cites W3035186652 @default.
- W3105649115 cites W3035355460 @default.
- W3105649115 doi "https://doi.org/10.1016/j.ins.2020.11.004" @default.
- W3105649115 hasPublicationYear "2021" @default.
- W3105649115 type Work @default.
- W3105649115 sameAs 3105649115 @default.
- W3105649115 citedByCount "9" @default.
- W3105649115 countsByYear W31056491152020 @default.
- W3105649115 countsByYear W31056491152021 @default.
- W3105649115 countsByYear W31056491152022 @default.
- W3105649115 countsByYear W31056491152023 @default.
- W3105649115 crossrefType "journal-article" @default.
- W3105649115 hasAuthorship W3105649115A5021979312 @default.
- W3105649115 hasAuthorship W3105649115A5031308675 @default.
- W3105649115 hasAuthorship W3105649115A5040099999 @default.
- W3105649115 hasAuthorship W3105649115A5070818899 @default.
- W3105649115 hasConcept C104317684 @default.
- W3105649115 hasConcept C111919701 @default.
- W3105649115 hasConcept C116834253 @default.
- W3105649115 hasConcept C119857082 @default.
- W3105649115 hasConcept C13280743 @default.
- W3105649115 hasConcept C134306372 @default.
- W3105649115 hasConcept C138885662 @default.
- W3105649115 hasConcept C150899416 @default.
- W3105649115 hasConcept C154945302 @default.
- W3105649115 hasConcept C167927819 @default.
- W3105649115 hasConcept C171041071 @default.
- W3105649115 hasConcept C177264268 @default.
- W3105649115 hasConcept C185592680 @default.
- W3105649115 hasConcept C185798385 @default.
- W3105649115 hasConcept C199360897 @default.
- W3105649115 hasConcept C205649164 @default.
- W3105649115 hasConcept C2776760102 @default.
- W3105649115 hasConcept C2779178101 @default.
- W3105649115 hasConcept C33923547 @default.
- W3105649115 hasConcept C36503486 @default.
- W3105649115 hasConcept C41008148 @default.
- W3105649115 hasConcept C41895202 @default.
- W3105649115 hasConcept C43126263 @default.
- W3105649115 hasConcept C55493867 @default.
- W3105649115 hasConcept C59404180 @default.
- W3105649115 hasConcept C59822182 @default.
- W3105649115 hasConcept C63479239 @default.
- W3105649115 hasConcept C86803240 @default.
- W3105649115 hasConcept C97931131 @default.
- W3105649115 hasConceptScore W3105649115C104317684 @default.
- W3105649115 hasConceptScore W3105649115C111919701 @default.
- W3105649115 hasConceptScore W3105649115C116834253 @default.
- W3105649115 hasConceptScore W3105649115C119857082 @default.
- W3105649115 hasConceptScore W3105649115C13280743 @default.
- W3105649115 hasConceptScore W3105649115C134306372 @default.
- W3105649115 hasConceptScore W3105649115C138885662 @default.
- W3105649115 hasConceptScore W3105649115C150899416 @default.
- W3105649115 hasConceptScore W3105649115C154945302 @default.
- W3105649115 hasConceptScore W3105649115C167927819 @default.
- W3105649115 hasConceptScore W3105649115C171041071 @default.
- W3105649115 hasConceptScore W3105649115C177264268 @default.
- W3105649115 hasConceptScore W3105649115C185592680 @default.
- W3105649115 hasConceptScore W3105649115C185798385 @default.
- W3105649115 hasConceptScore W3105649115C199360897 @default.
- W3105649115 hasConceptScore W3105649115C205649164 @default.