Matches in SemOpenAlex for { <https://semopenalex.org/work/W2608045553> ?p ?o ?g. }
- W2608045553 endingPage "23" @default.
- W2608045553 startingPage "1" @default.
- W2608045553 abstract "Despite the promising progress made in recent years, person re-identification (re-ID) remains a challenging task due to the complex variations in human appearances from different camera views. For this challenging problem, a large variety of algorithms have been developed in the fully supervised setting, requiring access to a large amount of labeled training data. However, the main bottleneck for fully supervised re-ID is the limited availability of labeled training samples. To address this problem, we propose a self-trained subspace learning paradigm for person re-ID that effectively utilizes both labeled and unlabeled data to learn a discriminative subspace where person images across disjoint camera views can be easily matched. The proposed approach first constructs pseudo-pairwise relationships among unlabeled persons using the k-nearest neighbors algorithm. Then, with the pseudo-pairwise relationships, the unlabeled samples can be easily combined with the labeled samples to learn a discriminative projection by solving an eigenvalue problem. In addition, we refine the pseudo-pairwise relationships iteratively, which further improves learning performance. A multi-kernel embedding strategy is also incorporated into the proposed approach to cope with the non-linearity in a person’s appearance and explore the complementation of multiple kernels. In this way, the performance of person re-ID can be greatly enhanced when training data are insufficient. Experimental results on six widely used datasets demonstrate the effectiveness of our approach, and its performance can be comparable to the reported results of most state-of-the-art fully supervised methods while using much fewer labeled data." @default.
- W2608045553 created "2017-05-05" @default.
- W2608045553 creator A5034737032 @default.
- W2608045553 creator A5036726873 @default.
- W2608045553 creator A5047455588 @default.
- W2608045553 creator A5051332325 @default.
- W2608045553 creator A5063235838 @default.
- W2608045553 date "2017-06-28" @default.
- W2608045553 modified "2023-10-09" @default.
- W2608045553 title "Enhancing Person Re-identification in a Self-Trained Subspace" @default.
- W2608045553 cites W119849253 @default.
- W2608045553 cites W1518138188 @default.
- W2608045553 cites W1532801683 @default.
- W2608045553 cites W1602182271 @default.
- W2608045553 cites W166429404 @default.
- W2608045553 cites W1709635438 @default.
- W2608045553 cites W1902024696 @default.
- W2608045553 cites W1935207225 @default.
- W2608045553 cites W1962025484 @default.
- W2608045553 cites W1967456674 @default.
- W2608045553 cites W1969204685 @default.
- W2608045553 cites W1975165783 @default.
- W2608045553 cites W1979838576 @default.
- W2608045553 cites W1983320747 @default.
- W2608045553 cites W1984608801 @default.
- W2608045553 cites W1991209141 @default.
- W2608045553 cites W1991359796 @default.
- W2608045553 cites W1999478721 @default.
- W2608045553 cites W2009907187 @default.
- W2608045553 cites W2014764728 @default.
- W2608045553 cites W2014850105 @default.
- W2608045553 cites W2022469758 @default.
- W2608045553 cites W2026569857 @default.
- W2608045553 cites W2043409787 @default.
- W2608045553 cites W2046835352 @default.
- W2608045553 cites W2070784585 @default.
- W2608045553 cites W2079057609 @default.
- W2608045553 cites W2079972027 @default.
- W2608045553 cites W2089074647 @default.
- W2608045553 cites W2101210369 @default.
- W2608045553 cites W2108588392 @default.
- W2608045553 cites W2113609219 @default.
- W2608045553 cites W2114217318 @default.
- W2608045553 cites W2115669554 @default.
- W2608045553 cites W2131154631 @default.
- W2608045553 cites W2151873133 @default.
- W2608045553 cites W2152756885 @default.
- W2608045553 cites W2154330368 @default.
- W2608045553 cites W2163584563 @default.
- W2608045553 cites W2203864774 @default.
- W2608045553 cites W2220271458 @default.
- W2608045553 cites W2300840837 @default.
- W2608045553 cites W2327827989 @default.
- W2608045553 cites W2433217581 @default.
- W2608045553 cites W2467139031 @default.
- W2608045553 cites W2472876510 @default.
- W2608045553 cites W2474013209 @default.
- W2608045553 cites W2475284720 @default.
- W2608045553 cites W2520433280 @default.
- W2608045553 cites W2963901085 @default.
- W2608045553 cites W3099224353 @default.
- W2608045553 doi "https://doi.org/10.1145/3089249" @default.
- W2608045553 hasPublicationYear "2017" @default.
- W2608045553 type Work @default.
- W2608045553 sameAs 2608045553 @default.
- W2608045553 citedByCount "76" @default.
- W2608045553 countsByYear W26080455532017 @default.
- W2608045553 countsByYear W26080455532018 @default.
- W2608045553 countsByYear W26080455532019 @default.
- W2608045553 countsByYear W26080455532020 @default.
- W2608045553 countsByYear W26080455532021 @default.
- W2608045553 countsByYear W26080455532022 @default.
- W2608045553 countsByYear W26080455532023 @default.
- W2608045553 crossrefType "journal-article" @default.
- W2608045553 hasAuthorship W2608045553A5034737032 @default.
- W2608045553 hasAuthorship W2608045553A5036726873 @default.
- W2608045553 hasAuthorship W2608045553A5047455588 @default.
- W2608045553 hasAuthorship W2608045553A5051332325 @default.
- W2608045553 hasAuthorship W2608045553A5063235838 @default.
- W2608045553 hasBestOaLocation W26080455532 @default.
- W2608045553 hasConcept C114614502 @default.
- W2608045553 hasConcept C116834253 @default.
- W2608045553 hasConcept C119857082 @default.
- W2608045553 hasConcept C153180895 @default.
- W2608045553 hasConcept C154945302 @default.
- W2608045553 hasConcept C184898388 @default.
- W2608045553 hasConcept C2776145971 @default.
- W2608045553 hasConcept C32834561 @default.
- W2608045553 hasConcept C33923547 @default.
- W2608045553 hasConcept C41008148 @default.
- W2608045553 hasConcept C41608201 @default.
- W2608045553 hasConcept C45340560 @default.
- W2608045553 hasConcept C59822182 @default.
- W2608045553 hasConcept C74193536 @default.
- W2608045553 hasConcept C86803240 @default.
- W2608045553 hasConcept C97931131 @default.
- W2608045553 hasConceptScore W2608045553C114614502 @default.
- W2608045553 hasConceptScore W2608045553C116834253 @default.