Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912152775> ?p ?o ?g. }
- W2912152775 endingPage "19" @default.
- W2912152775 startingPage "1" @default.
- W2912152775 abstract "Person re-identification aims at identifying a certain pedestrian across non-overlapping multi-camera networks in different time and places. Existing person re-identification approaches mainly focus on matching pedestrians on images; however, little attention has been paid to re-identify pedestrians in videos. Compared to images, video clips contain motion patterns of pedestrians, which is crucial to person re-identification. Moreover, consecutive video frames present pedestrian appearance with different body poses and from different viewpoints, providing valuable information toward addressing the challenge of pose variation, occlusion, and viewpoint change, and so on. In this article, we propose a Dense 3D-Convolutional Network (D3DNet) to jointly learn spatio-temporal and appearance representation for person re-identification in videos. The D3DNet consists of multiple three-dimensional (3D) dense blocks and transition layers. The 3D dense blocks enlarge the receptive fields of visual neurons in both spatial and temporal dimensions, leading to discriminative appearance representation as well as short-term and long-term motion patterns of pedestrians without the requirement of an additional motion estimation module. Moreover, we formulate a loss function consisting of an identification loss and a center loss to minimize intra-class variance and maximize inter-class variance simultaneously, toward addressing the challenge of large intra-class variance and small inter-class variance. Extensive experiments on two real-world video datasets of person identification, i.e., MARS and iLIDS-VID, have shown the effectiveness of the proposed approach." @default.
- W2912152775 created "2019-02-21" @default.
- W2912152775 creator A5003217535 @default.
- W2912152775 creator A5036125002 @default.
- W2912152775 creator A5046305086 @default.
- W2912152775 creator A5062778155 @default.
- W2912152775 creator A5088031350 @default.
- W2912152775 date "2019-01-24" @default.
- W2912152775 modified "2023-09-23" @default.
- W2912152775 title "Dense 3D-Convolutional Neural Network for Person Re-Identification in Videos" @default.
- W2912152775 cites W119849253 @default.
- W2912152775 cites W1522734439 @default.
- W2912152775 cites W166429404 @default.
- W2912152775 cites W1927348918 @default.
- W2912152775 cites W1941498359 @default.
- W2912152775 cites W1949591461 @default.
- W2912152775 cites W1962025484 @default.
- W2912152775 cites W1979260620 @default.
- W2912152775 cites W1983364832 @default.
- W2912152775 cites W1991452654 @default.
- W2912152775 cites W2024868105 @default.
- W2912152775 cites W2047632871 @default.
- W2912152775 cites W2106053110 @default.
- W2912152775 cites W2126680226 @default.
- W2912152775 cites W2151103935 @default.
- W2912152775 cites W2169495281 @default.
- W2912152775 cites W2183341477 @default.
- W2912152775 cites W2219504084 @default.
- W2912152775 cites W2228002889 @default.
- W2912152775 cites W2256680489 @default.
- W2912152775 cites W2258844511 @default.
- W2912152775 cites W2300840837 @default.
- W2912152775 cites W2336162022 @default.
- W2912152775 cites W2342611082 @default.
- W2912152775 cites W2346369283 @default.
- W2912152775 cites W2433217581 @default.
- W2912152775 cites W2463071499 @default.
- W2912152775 cites W2471048925 @default.
- W2912152775 cites W2472876510 @default.
- W2912152775 cites W2475284720 @default.
- W2912152775 cites W2519803806 @default.
- W2912152775 cites W2520433280 @default.
- W2912152775 cites W2520774990 @default.
- W2912152775 cites W2526833393 @default.
- W2912152775 cites W2550580161 @default.
- W2912152775 cites W2584637367 @default.
- W2912152775 cites W2585006962 @default.
- W2912152775 cites W2592051407 @default.
- W2912152775 cites W2606377603 @default.
- W2912152775 cites W2608045553 @default.
- W2912152775 cites W2622829582 @default.
- W2912152775 cites W2791295466 @default.
- W2912152775 cites W2798385569 @default.
- W2912152775 cites W2798874329 @default.
- W2912152775 cites W2803629456 @default.
- W2912152775 cites W2963047834 @default.
- W2912152775 cites W2963216120 @default.
- W2912152775 cites W2963960612 @default.
- W2912152775 cites W2964163358 @default.
- W2912152775 cites W2964304299 @default.
- W2912152775 cites W3098711604 @default.
- W2912152775 cites W46454230 @default.
- W2912152775 doi "https://doi.org/10.1145/3231741" @default.
- W2912152775 hasPublicationYear "2019" @default.
- W2912152775 type Work @default.
- W2912152775 sameAs 2912152775 @default.
- W2912152775 citedByCount "45" @default.
- W2912152775 countsByYear W29121527752018 @default.
- W2912152775 countsByYear W29121527752019 @default.
- W2912152775 countsByYear W29121527752020 @default.
- W2912152775 countsByYear W29121527752021 @default.
- W2912152775 countsByYear W29121527752022 @default.
- W2912152775 countsByYear W29121527752023 @default.
- W2912152775 crossrefType "journal-article" @default.
- W2912152775 hasAuthorship W2912152775A5003217535 @default.
- W2912152775 hasAuthorship W2912152775A5036125002 @default.
- W2912152775 hasAuthorship W2912152775A5046305086 @default.
- W2912152775 hasAuthorship W2912152775A5062778155 @default.
- W2912152775 hasAuthorship W2912152775A5088031350 @default.
- W2912152775 hasConcept C104114177 @default.
- W2912152775 hasConcept C105795698 @default.
- W2912152775 hasConcept C116834253 @default.
- W2912152775 hasConcept C121955636 @default.
- W2912152775 hasConcept C142362112 @default.
- W2912152775 hasConcept C144133560 @default.
- W2912152775 hasConcept C153180895 @default.
- W2912152775 hasConcept C153349607 @default.
- W2912152775 hasConcept C154945302 @default.
- W2912152775 hasConcept C165064840 @default.
- W2912152775 hasConcept C166957645 @default.
- W2912152775 hasConcept C17744445 @default.
- W2912152775 hasConcept C196083921 @default.
- W2912152775 hasConcept C199539241 @default.
- W2912152775 hasConcept C205649164 @default.
- W2912152775 hasConcept C2776035091 @default.
- W2912152775 hasConcept C2776359362 @default.
- W2912152775 hasConcept C2777113093 @default.
- W2912152775 hasConcept C2777212361 @default.