FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313449748> ?p ?o ?g. }

• W4313449748 endingPage "470" @default.
• W4313449748 startingPage "458" @default.
• W4313449748 abstract "Occluded person re-identification (ReID) is a challenging task due to more background noises and incomplete foreground information. Although existing human parsing-based ReID methods can tackle this problem with semantic alignment at the finest pixel level, their performance is heavily affected by the human parsing model. Most supervised methods propose to train an extra human parsing model aside from the ReID model with cross-domain human parts annotation, suffering from expensive annotation cost and domain gap; Unsupervised methods integrate a feature clustering-based human parsing process into the ReID model, but lacking supervision signals brings less satisfactory segmentation results. In this paper, we argue that the pre-existing information in the ReID training dataset can be directly used as supervision signals to train the human parsing model without any extra annotation. By integrating a weakly supervised human co-parsing network into the ReID network, we propose a novel framework that exploits shared information across different images of the same pedestrian, called the Human Co-parsing Guided Alignment (HCGA) framework. Specifically, the human co-parsing network is weakly supervised by three consistency criteria, namely global semantics, local space, and background. By feeding the semantic information and deep features from the person ReID network into the guided alignment module, features of the foreground and human parts can then be obtained for effective occluded person ReID. Experiment results on two occluded and two holistic datasets demonstrate the superiority of our method. Especially on Occluded-DukeMTMC, it achieves 70.2% Rank-1 accuracy and 57.5% mAP." @default.
• W4313449748 created "2023-01-06" @default.
• W4313449748 creator A5011424573 @default.
• W4313449748 creator A5018318136 @default.
• W4313449748 creator A5031897915 @default.
• W4313449748 creator A5039546706 @default.
• W4313449748 creator A5064237960 @default.
• W4313449748 creator A5082605318 @default.
• W4313449748 date "2023-01-01" @default.
• W4313449748 modified "2023-10-14" @default.
• W4313449748 title "Human Co-Parsing Guided Alignment for Occluded Person Re-Identification" @default.
• W4313449748 cites W1677182931 @default.
• W4313449748 cites W1982925187 @default.
• W4313449748 cites W2163352848 @default.
• W4313449748 cites W2183341477 @default.
• W4313449748 cites W2194775991 @default.
• W4313449748 cites W2204750386 @default.
• W4313449748 cites W2584637367 @default.
• W4313449748 cites W2798775284 @default.
• W4313449748 cites W2916798096 @default.
• W4313449748 cites W2954275231 @default.
• W4313449748 cites W2955147859 @default.
• W4313449748 cites W2962691289 @default.
• W4313449748 cites W2962706983 @default.
• W4313449748 cites W2962784289 @default.
• W4313449748 cites W2962926870 @default.
• W4313449748 cites W2963078173 @default.
• W4313449748 cites W2963330186 @default.
• W4313449748 cites W2963521811 @default.
• W4313449748 cites W2963805953 @default.
• W4313449748 cites W2963876278 @default.
• W4313449748 cites W2964044605 @default.
• W4313449748 cites W2964130064 @default.
• W4313449748 cites W2964140013 @default.
• W4313449748 cites W2964163358 @default.
• W4313449748 cites W2964201641 @default.
• W4313449748 cites W2964304299 @default.
• W4313449748 cites W2979931389 @default.
• W4313449748 cites W2981393440 @default.
• W4313449748 cites W2981420411 @default.
• W4313449748 cites W2984040540 @default.
• W4313449748 cites W2986093954 @default.
• W4313449748 cites W2988964414 @default.
• W4313449748 cites W2990317318 @default.
• W4313449748 cites W2990500698 @default.
• W4313449748 cites W2998493658 @default.
• W4313449748 cites W2998792609 @default.
• W4313449748 cites W3034580371 @default.
• W4313449748 cites W3034611771 @default.
• W4313449748 cites W3035186652 @default.
• W4313449748 cites W3035385098 @default.
• W4313449748 cites W3087124270 @default.
• W4313449748 cites W3087658752 @default.
• W4313449748 cites W3093104573 @default.
• W4313449748 cites W3098379913 @default.
• W4313449748 cites W3099193570 @default.
• W4313449748 cites W3100506510 @default.
• W4313449748 cites W3115879670 @default.
• W4313449748 cites W3162863184 @default.
• W4313449748 cites W3174656328 @default.
• W4313449748 cites W3175823695 @default.
• W4313449748 cites W3184567417 @default.
• W4313449748 cites W3189500528 @default.
• W4313449748 cites W3194557739 @default.
• W4313449748 cites W4200316912 @default.
• W4313449748 cites W4200343840 @default.
• W4313449748 cites W4205914576 @default.
• W4313449748 cites W4214736485 @default.
• W4313449748 doi "https://doi.org/10.1109/tip.2022.3229639" @default.
• W4313449748 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37015433" @default.
• W4313449748 hasPublicationYear "2023" @default.
• W4313449748 type Work @default.
• W4313449748 citedByCount "1" @default.
• W4313449748 countsByYear W43134497482023 @default.
• W4313449748 crossrefType "journal-article" @default.
• W4313449748 hasAuthorship W4313449748A5011424573 @default.
• W4313449748 hasAuthorship W4313449748A5018318136 @default.
• W4313449748 hasAuthorship W4313449748A5031897915 @default.
• W4313449748 hasAuthorship W4313449748A5039546706 @default.
• W4313449748 hasAuthorship W4313449748A5064237960 @default.
• W4313449748 hasAuthorship W4313449748A5082605318 @default.
• W4313449748 hasConcept C116834253 @default.
• W4313449748 hasConcept C119857082 @default.
• W4313449748 hasConcept C138885662 @default.
• W4313449748 hasConcept C153180895 @default.
• W4313449748 hasConcept C154945302 @default.
• W4313449748 hasConcept C162324750 @default.
• W4313449748 hasConcept C184337299 @default.
• W4313449748 hasConcept C186644900 @default.
• W4313449748 hasConcept C187736073 @default.
• W4313449748 hasConcept C199360897 @default.
• W4313449748 hasConcept C204321447 @default.
• W4313449748 hasConcept C2776321320 @default.
• W4313449748 hasConcept C2776401178 @default.
• W4313449748 hasConcept C2780451532 @default.
• W4313449748 hasConcept C41008148 @default.
• W4313449748 hasConcept C41895202 @default.
• W4313449748 hasConcept C59822182 @default.

• next