Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206866525> ?p ?o ?g. }
- W3206866525 endingPage "4492" @default.
- W3206866525 startingPage "4482" @default.
- W3206866525 abstract "With the rise of deep learning methods, person Re-Identification (ReID) performance has been improved tremendously in many public datasets. However, most public ReID datasets are collected in a short time window in which persons’ appearance rarely changes. In real-world applications such as in a shopping mall, the same person may change their wearings, and different persons may wear similar apparel. It reveals a critical problem that current ReID models heavily rely on a person’s apparel, resulting in an inconsistent ReID performance. Therefore, it is crucial to learn an apparel-invariant person representation under clothes changing or several persons wearing similar clothes cases. In this work, we tackle this problem from the viewpoint of invariant feature representation learning. The main contributions of this work are as follows. (1) We propose the semi-supervised Apparel-invariant Feature Learning (AIFL) framework to learn an apparel-invariant pedestrian representation using images of the same person wearing different clothes. (2) To obtain images of the same person wearing different clothes, we propose an unsupervised apparel-simulation GAN (AS-GAN) to synthesize cloth-changing images according to the target cloth embedding. It is worth noting that the images used in ReID tasks were cropped from real-world low-quality CCTV videos, making it more challenging to synthesize cloth-changing images. Extensive experiments demonstrate that our proposal can improve the ReID performance of the baseline models." @default.
- W3206866525 created "2021-10-25" @default.
- W3206866525 creator A5024965898 @default.
- W3206866525 creator A5037942269 @default.
- W3206866525 creator A5039418272 @default.
- W3206866525 creator A5047416722 @default.
- W3206866525 creator A5053762066 @default.
- W3206866525 creator A5078722945 @default.
- W3206866525 creator A5079865276 @default.
- W3206866525 date "2022-01-01" @default.
- W3206866525 modified "2023-10-17" @default.
- W3206866525 title "Apparel-Invariant Feature Learning for Person Re-Identification" @default.
- W3206866525 cites W1518138188 @default.
- W3206866525 cites W1594368566 @default.
- W3206866525 cites W1941498359 @default.
- W3206866525 cites W1949591461 @default.
- W3206866525 cites W1973255633 @default.
- W3206866525 cites W1994623790 @default.
- W3206866525 cites W2017257315 @default.
- W3206866525 cites W2097117768 @default.
- W3206866525 cites W2108598243 @default.
- W3206866525 cites W2125889200 @default.
- W3206866525 cites W2194775991 @default.
- W3206866525 cites W2256680489 @default.
- W3206866525 cites W2293561010 @default.
- W3206866525 cites W2433217581 @default.
- W3206866525 cites W2441160157 @default.
- W3206866525 cites W2475284720 @default.
- W3206866525 cites W2559085405 @default.
- W3206866525 cites W2590973145 @default.
- W3206866525 cites W2736410039 @default.
- W3206866525 cites W2755066373 @default.
- W3206866525 cites W2771558241 @default.
- W3206866525 cites W2777534232 @default.
- W3206866525 cites W2912149104 @default.
- W3206866525 cites W2963000559 @default.
- W3206866525 cites W2963047834 @default.
- W3206866525 cites W2963073614 @default.
- W3206866525 cites W2963420272 @default.
- W3206866525 cites W2963438548 @default.
- W3206866525 cites W2963446712 @default.
- W3206866525 cites W2963574614 @default.
- W3206866525 cites W2963721283 @default.
- W3206866525 cites W2963852441 @default.
- W3206866525 cites W2963968597 @default.
- W3206866525 cites W2963989829 @default.
- W3206866525 cites W2964186374 @default.
- W3206866525 cites W2964304299 @default.
- W3206866525 cites W2964304707 @default.
- W3206866525 cites W2964318046 @default.
- W3206866525 cites W2994675267 @default.
- W3206866525 cites W3005339439 @default.
- W3206866525 cites W3015309773 @default.
- W3206866525 cites W3035275216 @default.
- W3206866525 cites W3042524218 @default.
- W3206866525 cites W3100507239 @default.
- W3206866525 cites W3105077954 @default.
- W3206866525 cites W3119699484 @default.
- W3206866525 cites W4231109964 @default.
- W3206866525 doi "https://doi.org/10.1109/tmm.2021.3119133" @default.
- W3206866525 hasPublicationYear "2022" @default.
- W3206866525 type Work @default.
- W3206866525 sameAs 3206866525 @default.
- W3206866525 citedByCount "10" @default.
- W3206866525 countsByYear W32068665252021 @default.
- W3206866525 countsByYear W32068665252022 @default.
- W3206866525 countsByYear W32068665252023 @default.
- W3206866525 crossrefType "journal-article" @default.
- W3206866525 hasAuthorship W3206866525A5024965898 @default.
- W3206866525 hasAuthorship W3206866525A5037942269 @default.
- W3206866525 hasAuthorship W3206866525A5039418272 @default.
- W3206866525 hasAuthorship W3206866525A5047416722 @default.
- W3206866525 hasAuthorship W3206866525A5053762066 @default.
- W3206866525 hasAuthorship W3206866525A5078722945 @default.
- W3206866525 hasAuthorship W3206866525A5079865276 @default.
- W3206866525 hasConcept C108583219 @default.
- W3206866525 hasConcept C116834253 @default.
- W3206866525 hasConcept C119857082 @default.
- W3206866525 hasConcept C153180895 @default.
- W3206866525 hasConcept C154945302 @default.
- W3206866525 hasConcept C166957645 @default.
- W3206866525 hasConcept C17744445 @default.
- W3206866525 hasConcept C190470478 @default.
- W3206866525 hasConcept C199539241 @default.
- W3206866525 hasConcept C2776359362 @default.
- W3206866525 hasConcept C31972630 @default.
- W3206866525 hasConcept C33923547 @default.
- W3206866525 hasConcept C37914503 @default.
- W3206866525 hasConcept C41008148 @default.
- W3206866525 hasConcept C41608201 @default.
- W3206866525 hasConcept C530175646 @default.
- W3206866525 hasConcept C59404180 @default.
- W3206866525 hasConcept C59822182 @default.
- W3206866525 hasConcept C86803240 @default.
- W3206866525 hasConcept C94625758 @default.
- W3206866525 hasConcept C95457728 @default.
- W3206866525 hasConceptScore W3206866525C108583219 @default.
- W3206866525 hasConceptScore W3206866525C116834253 @default.