FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313188908> ?p ?o ?g. }

• W4313188908 endingPage "1362" @default.
• W4313188908 startingPage "1349" @default.
• W4313188908 abstract "Person re-identification (RelD) is an important problem in intelligent surveillance and public security. Among all the solutions to this problem, existing mask-based methods first use a well-pretrained segmentation model to generate a foreground mask, in order to exclude the background from ReID. Then they perform the RelD task directly on the segmented pedestrian image. However, such a process requires extra datasets with pixel-level semantic labels. In this paper, we propose a Weakly Supervised Pedestrian Segmentation (WSPS) framework to produce the foreground mask directly from the RelD datasets. In contrast, our WSPS only requires image-level subject ID labels. To better utilize the pedestrian mask, we also propose the Image Synthesis Augmentation (ISA) technique to further augment the dataset. Experiments show that the features learned from our proposed framework are robust and discriminative. Compared with the baseline, the mAP of our framework is about 4.4%, 11.7%, and 4.0% higher on three widely used datasets including Market-1501, CUHK03, and MSMT17. The code will be available soon." @default.
• W4313188908 created "2023-01-06" @default.
• W4313188908 creator A5008067346 @default.
• W4313188908 creator A5019313200 @default.
• W4313188908 creator A5044361651 @default.
• W4313188908 creator A5089730660 @default.
• W4313188908 date "2023-03-01" @default.
• W4313188908 modified "2023-10-12" @default.
• W4313188908 title "Weakly Supervised Pedestrian Segmentation for Person Re-Identification" @default.
• W4313188908 cites W1982925187 @default.
• W4313188908 cites W2124351162 @default.
• W4313188908 cites W2168356304 @default.
• W4313188908 cites W2194775991 @default.
• W4313188908 cites W2204750386 @default.
• W4313188908 cites W2295107390 @default.
• W4313188908 cites W2560023338 @default.
• W4313188908 cites W2584009249 @default.
• W4313188908 cites W2584637367 @default.
• W4313188908 cites W2585635281 @default.
• W4313188908 cites W2593768305 @default.
• W4313188908 cites W2600144439 @default.
• W4313188908 cites W2768610172 @default.
• W4313188908 cites W2798550112 @default.
• W4313188908 cites W2798748179 @default.
• W4313188908 cites W2798775284 @default.
• W4313188908 cites W2798794112 @default.
• W4313188908 cites W2884366600 @default.
• W4313188908 cites W2886209409 @default.
• W4313188908 cites W2931208564 @default.
• W4313188908 cites W2962691289 @default.
• W4313188908 cites W2962793481 @default.
• W4313188908 cites W2962867364 @default.
• W4313188908 cites W2963047834 @default.
• W4313188908 cites W2963150697 @default.
• W4313188908 cites W2963322158 @default.
• W4313188908 cites W2963383990 @default.
• W4313188908 cites W2963709863 @default.
• W4313188908 cites W2963805953 @default.
• W4313188908 cites W2963978393 @default.
• W4313188908 cites W2964130064 @default.
• W4313188908 cites W2964707258 @default.
• W4313188908 cites W2965099462 @default.
• W4313188908 cites W2967515867 @default.
• W4313188908 cites W2970909715 @default.
• W4313188908 cites W2980073905 @default.
• W4313188908 cites W2981393440 @default.
• W4313188908 cites W2981689412 @default.
• W4313188908 cites W2982026851 @default.
• W4313188908 cites W2984145721 @default.
• W4313188908 cites W2997169099 @default.
• W4313188908 cites W2997851315 @default.
• W4313188908 cites W2998508940 @default.
• W4313188908 cites W3002544507 @default.
• W4313188908 cites W3034227982 @default.
• W4313188908 cites W3034930876 @default.
• W4313188908 cites W3047312295 @default.
• W4313188908 cites W3096285474 @default.
• W4313188908 cites W3097870364 @default.
• W4313188908 cites W3103352455 @default.
• W4313188908 cites W3105159632 @default.
• W4313188908 cites W3106568457 @default.
• W4313188908 cites W3107169861 @default.
• W4313188908 cites W3115695930 @default.
• W4313188908 cites W3115879670 @default.
• W4313188908 cites W3135741259 @default.
• W4313188908 cites W3138516171 @default.
• W4313188908 cites W3160639636 @default.
• W4313188908 cites W3163538250 @default.
• W4313188908 cites W3166274350 @default.
• W4313188908 cites W3185727700 @default.
• W4313188908 cites W3186064588 @default.
• W4313188908 cites W3190500189 @default.
• W4313188908 cites W3193305989 @default.
• W4313188908 cites W3194178355 @default.
• W4313188908 cites W3208037308 @default.
• W4313188908 cites W3210967702 @default.
• W4313188908 cites W4212883693 @default.
• W4313188908 doi "https://doi.org/10.1109/tcsvt.2022.3210476" @default.
• W4313188908 hasPublicationYear "2023" @default.
• W4313188908 type Work @default.
• W4313188908 citedByCount "0" @default.
• W4313188908 crossrefType "journal-article" @default.
• W4313188908 hasAuthorship W4313188908A5008067346 @default.
• W4313188908 hasAuthorship W4313188908A5019313200 @default.
• W4313188908 hasAuthorship W4313188908A5044361651 @default.
• W4313188908 hasAuthorship W4313188908A5089730660 @default.
• W4313188908 hasConcept C111919701 @default.
• W4313188908 hasConcept C115961682 @default.
• W4313188908 hasConcept C116834253 @default.
• W4313188908 hasConcept C124504099 @default.
• W4313188908 hasConcept C127413603 @default.
• W4313188908 hasConcept C153180895 @default.
• W4313188908 hasConcept C154945302 @default.
• W4313188908 hasConcept C160633673 @default.
• W4313188908 hasConcept C22212356 @default.
• W4313188908 hasConcept C2777113093 @default.
• W4313188908 hasConcept C2780156472 @default.
• W4313188908 hasConcept C31972630 @default.

• next