Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950281010> ?p ?o ?g. }
- W2950281010 abstract "In this paper we propose a novel metric learning framework called Nullspace Kernel Maximum Margin Metric Learning (NK3ML) which efficiently addresses the small sample size (SSS) problem inherent in person re-identification and offers a significant performance gain over existing state-of-the-art methods. Taking advantage of the very high dimensionality of the feature space, the metric is learned using a maximum margin criterion (MMC) over a discriminative nullspace where all training sample points of a given class map onto a single point, minimizing the within class scatter. A kernel version of MMC is used to obtain a better between class separation. Extensive experiments on four challenging benchmark datasets for person re-identification demonstrate that the proposed algorithm outperforms all existing methods. We obtain 99.8% rank-1 accuracy on the most widely accepted and challenging dataset VIPeR, compared to the previous state of the art being only 63.92%." @default.
- W2950281010 created "2019-06-27" @default.
- W2950281010 creator A5016405213 @default.
- W2950281010 creator A5032100914 @default.
- W2950281010 date "2018-07-28" @default.
- W2950281010 modified "2023-09-27" @default.
- W2950281010 title "Maximum Margin Metric Learning Over Discriminative Nullspace for Person Re-identification" @default.
- W2950281010 cites W1518138188 @default.
- W2950281010 cites W1709635438 @default.
- W2950281010 cites W1927348918 @default.
- W2950281010 cites W1949591461 @default.
- W2950281010 cites W1979260620 @default.
- W2950281010 cites W1991452654 @default.
- W2950281010 cites W2014764728 @default.
- W2950281010 cites W2048110836 @default.
- W2950281010 cites W2059998433 @default.
- W2950281010 cites W2068042582 @default.
- W2950281010 cites W2073127487 @default.
- W2950281010 cites W2105055468 @default.
- W2950281010 cites W2106053110 @default.
- W2950281010 cites W2114217318 @default.
- W2950281010 cites W2127691749 @default.
- W2950281010 cites W2151065677 @default.
- W2950281010 cites W2153635508 @default.
- W2950281010 cites W2169495281 @default.
- W2950281010 cites W2289130514 @default.
- W2950281010 cites W2342611082 @default.
- W2950281010 cites W2475284720 @default.
- W2950281010 cites W2765309247 @default.
- W2950281010 cites W2963721283 @default.
- W2950281010 cites W2964304299 @default.
- W2950281010 cites W42769906 @default.
- W2950281010 hasPublicationYear "2018" @default.
- W2950281010 type Work @default.
- W2950281010 sameAs 2950281010 @default.
- W2950281010 citedByCount "0" @default.
- W2950281010 crossrefType "posted-content" @default.
- W2950281010 hasAuthorship W2950281010A5016405213 @default.
- W2950281010 hasAuthorship W2950281010A5032100914 @default.
- W2950281010 hasConcept C111030470 @default.
- W2950281010 hasConcept C114614502 @default.
- W2950281010 hasConcept C116834253 @default.
- W2950281010 hasConcept C119857082 @default.
- W2950281010 hasConcept C127413603 @default.
- W2950281010 hasConcept C13280743 @default.
- W2950281010 hasConcept C138885662 @default.
- W2950281010 hasConcept C153180895 @default.
- W2950281010 hasConcept C154945302 @default.
- W2950281010 hasConcept C176217482 @default.
- W2950281010 hasConcept C185798385 @default.
- W2950281010 hasConcept C205649164 @default.
- W2950281010 hasConcept C21547014 @default.
- W2950281010 hasConcept C2776401178 @default.
- W2950281010 hasConcept C33923547 @default.
- W2950281010 hasConcept C41008148 @default.
- W2950281010 hasConcept C41895202 @default.
- W2950281010 hasConcept C59822182 @default.
- W2950281010 hasConcept C74193536 @default.
- W2950281010 hasConcept C774472 @default.
- W2950281010 hasConcept C83665646 @default.
- W2950281010 hasConcept C86803240 @default.
- W2950281010 hasConcept C97931131 @default.
- W2950281010 hasConceptScore W2950281010C111030470 @default.
- W2950281010 hasConceptScore W2950281010C114614502 @default.
- W2950281010 hasConceptScore W2950281010C116834253 @default.
- W2950281010 hasConceptScore W2950281010C119857082 @default.
- W2950281010 hasConceptScore W2950281010C127413603 @default.
- W2950281010 hasConceptScore W2950281010C13280743 @default.
- W2950281010 hasConceptScore W2950281010C138885662 @default.
- W2950281010 hasConceptScore W2950281010C153180895 @default.
- W2950281010 hasConceptScore W2950281010C154945302 @default.
- W2950281010 hasConceptScore W2950281010C176217482 @default.
- W2950281010 hasConceptScore W2950281010C185798385 @default.
- W2950281010 hasConceptScore W2950281010C205649164 @default.
- W2950281010 hasConceptScore W2950281010C21547014 @default.
- W2950281010 hasConceptScore W2950281010C2776401178 @default.
- W2950281010 hasConceptScore W2950281010C33923547 @default.
- W2950281010 hasConceptScore W2950281010C41008148 @default.
- W2950281010 hasConceptScore W2950281010C41895202 @default.
- W2950281010 hasConceptScore W2950281010C59822182 @default.
- W2950281010 hasConceptScore W2950281010C74193536 @default.
- W2950281010 hasConceptScore W2950281010C774472 @default.
- W2950281010 hasConceptScore W2950281010C83665646 @default.
- W2950281010 hasConceptScore W2950281010C86803240 @default.
- W2950281010 hasConceptScore W2950281010C97931131 @default.
- W2950281010 hasLocation W29502810101 @default.
- W2950281010 hasOpenAccess W2950281010 @default.
- W2950281010 hasPrimaryLocation W29502810101 @default.
- W2950281010 hasRelatedWork W1532564325 @default.
- W2950281010 hasRelatedWork W1905908634 @default.
- W2950281010 hasRelatedWork W2090781449 @default.
- W2950281010 hasRelatedWork W2124325819 @default.
- W2950281010 hasRelatedWork W2174144271 @default.
- W2950281010 hasRelatedWork W2338824513 @default.
- W2950281010 hasRelatedWork W2492486054 @default.
- W2950281010 hasRelatedWork W2511386574 @default.
- W2950281010 hasRelatedWork W2552765257 @default.
- W2950281010 hasRelatedWork W2555454054 @default.
- W2950281010 hasRelatedWork W2607841987 @default.
- W2950281010 hasRelatedWork W2753354908 @default.