FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308469673> ?p ?o ?g. }

• W4308469673 endingPage "164" @default.
• W4308469673 startingPage "155" @default.
• W4308469673 abstract "Person re-identification (ReID) aims to associate the same person across non-overlapping cameras. However, most of existing works neglect the issue of camera-imbalanced data distribution. Consequently, pedestrian representation learning gives preference to the head cameras, which have comparatively more training data, and disregards the tail cameras, which have relatively less training data. In this paper, we propose a novel framework for camera-aware representation learning to overcome this issue, named CARL. On the proxy level representation learning, CARL presents a multiple-center softmax loss to correct the head camera bias and presents a hard sub-center mining strategy to improve the discrimination of tail camera samples. On the pair-wise level representation learning, CARL builds a camera-balanced memory bank (CBM) to re-balance the sample pair distribution and proposes a camera-paired loss for pair-wise metric learning. Extensive experiments and ablation studies on MSMT17, the current largest ReID dataset with massive camera-imbalanced data distribution, demonstrate that our CARL is superior to previous metric learning based ReID methods and achieves state-of-the-art performance." @default.
• W4308469673 created "2022-11-12" @default.
• W4308469673 creator A5033870633 @default.
• W4308469673 creator A5041686328 @default.
• W4308469673 creator A5049692788 @default.
• W4308469673 creator A5053703740 @default.
• W4308469673 creator A5064721095 @default.
• W4308469673 creator A5082786719 @default.
• W4308469673 date "2023-01-01" @default.
• W4308469673 modified "2023-10-15" @default.
• W4308469673 title "Camera-aware representation learning for person re-identification" @default.
• W4308469673 cites W157648163 @default.
• W4308469673 cites W2135442311 @default.
• W4308469673 cites W2204750386 @default.
• W4308469673 cites W2511791013 @default.
• W4308469673 cites W2519373641 @default.
• W4308469673 cites W2520774990 @default.
• W4308469673 cites W2585635281 @default.
• W4308469673 cites W2810967842 @default.
• W4308469673 cites W2884366600 @default.
• W4308469673 cites W2912406707 @default.
• W4308469673 cites W2957279468 @default.
• W4308469673 cites W2962691289 @default.
• W4308469673 cites W2962898354 @default.
• W4308469673 cites W2963026686 @default.
• W4308469673 cites W2963047834 @default.
• W4308469673 cites W2963049565 @default.
• W4308469673 cites W2963078173 @default.
• W4308469673 cites W2963466847 @default.
• W4308469673 cites W2963805953 @default.
• W4308469673 cites W2963842104 @default.
• W4308469673 cites W2964130064 @default.
• W4308469673 cites W2964271799 @default.
• W4308469673 cites W2964304299 @default.
• W4308469673 cites W2967515867 @default.
• W4308469673 cites W2969985801 @default.
• W4308469673 cites W2979931389 @default.
• W4308469673 cites W2984040540 @default.
• W4308469673 cites W2990827756 @default.
• W4308469673 cites W2991234496 @default.
• W4308469673 cites W2998522188 @default.
• W4308469673 cites W3034303554 @default.
• W4308469673 cites W3034580371 @default.
• W4308469673 cites W3035014997 @default.
• W4308469673 cites W3035724178 @default.
• W4308469673 cites W3096285474 @default.
• W4308469673 cites W3098711604 @default.
• W4308469673 cites W3099206234 @default.
• W4308469673 cites W3101227480 @default.
• W4308469673 cites W3106778652 @default.
• W4308469673 cites W3109582659 @default.
• W4308469673 cites W3112777276 @default.
• W4308469673 cites W3115484111 @default.
• W4308469673 cites W3134760092 @default.
• W4308469673 cites W3150864706 @default.
• W4308469673 cites W3150889503 @default.
• W4308469673 cites W3156246736 @default.
• W4308469673 cites W3159427232 @default.
• W4308469673 cites W3210807744 @default.
• W4308469673 doi "https://doi.org/10.1016/j.neucom.2022.11.009" @default.
• W4308469673 hasPublicationYear "2023" @default.
• W4308469673 type Work @default.
• W4308469673 citedByCount "4" @default.
• W4308469673 countsByYear W43084696732022 @default.
• W4308469673 countsByYear W43084696732023 @default.
• W4308469673 crossrefType "journal-article" @default.
• W4308469673 hasAuthorship W4308469673A5033870633 @default.
• W4308469673 hasAuthorship W4308469673A5041686328 @default.
• W4308469673 hasAuthorship W4308469673A5049692788 @default.
• W4308469673 hasAuthorship W4308469673A5053703740 @default.
• W4308469673 hasAuthorship W4308469673A5064721095 @default.
• W4308469673 hasAuthorship W4308469673A5082786719 @default.
• W4308469673 hasConcept C108583219 @default.
• W4308469673 hasConcept C116834253 @default.
• W4308469673 hasConcept C119857082 @default.
• W4308469673 hasConcept C154945302 @default.
• W4308469673 hasConcept C162324750 @default.
• W4308469673 hasConcept C176217482 @default.
• W4308469673 hasConcept C17744445 @default.
• W4308469673 hasConcept C188441871 @default.
• W4308469673 hasConcept C199539241 @default.
• W4308469673 hasConcept C21547014 @default.
• W4308469673 hasConcept C2776359362 @default.
• W4308469673 hasConcept C31972630 @default.
• W4308469673 hasConcept C41008148 @default.
• W4308469673 hasConcept C59404180 @default.
• W4308469673 hasConcept C59822182 @default.
• W4308469673 hasConcept C86803240 @default.
• W4308469673 hasConcept C94625758 @default.
• W4308469673 hasConceptScore W4308469673C108583219 @default.
• W4308469673 hasConceptScore W4308469673C116834253 @default.
• W4308469673 hasConceptScore W4308469673C119857082 @default.
• W4308469673 hasConceptScore W4308469673C154945302 @default.
• W4308469673 hasConceptScore W4308469673C162324750 @default.
• W4308469673 hasConceptScore W4308469673C176217482 @default.
• W4308469673 hasConceptScore W4308469673C17744445 @default.
• W4308469673 hasConceptScore W4308469673C188441871 @default.
• W4308469673 hasConceptScore W4308469673C199539241 @default.

• next