FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3113448926> ?p ?o ?g. }

• W3113448926 endingPage "1607" @default.
• W3113448926 startingPage "1596" @default.
• W3113448926 abstract "With the assistance of sophisticated training methods applied to single labeled datasets, the performance of fully-supervised person re-identification (Person Re-ID) has been improved significantly in recent years. However, these models trained on a single dataset usually suffer from considerable performance degradation when applied to videos of a different camera network. To make Person Re-ID systems more practical and scalable, several cross-dataset domain adaptation methods have been proposed, which achieve high performance without the labeled data from the target domain. However, these approaches still require the unlabeled data of the target domain during the training process, making them impractical. A practical Person Re-ID system pre-trained on other datasets should start running immediately after deployment on a new site without having to wait until sufficient images or videos are collected and the pre-trained model is tuned. To serve this purpose, in this paper, we reformulate person re-identification as a multi-dataset domain generalization problem. We propose a multi-dataset feature generalization network (MMFA-AAE), which is capable of learning a universal domain-invariant feature representation from multiple labeled datasets and generalizing it to `unseen' camera systems. The network is based on an adversarial auto-encoder to learn a generalized domain-invariant latent feature representation with the Maximum Mean Discrepancy (MMD) measure to align the distributions across multiple domains. Extensive experiments demonstrate the effectiveness of the proposed method. Our MMFA-AAE approach not only outperforms most of the domain generalization Person Re-ID methods, but also surpasses many state-of-the-art supervised methods and unsupervised domain adaptation methods by a large margin." @default.
• W3113448926 created "2021-01-05" @default.
• W3113448926 creator A5016271966 @default.
• W3113448926 creator A5067029753 @default.
• W3113448926 creator A5075200053 @default.
• W3113448926 date "2021-01-01" @default.
• W3113448926 modified "2023-10-16" @default.
• W3113448926 title "Multi-Domain Adversarial Feature Generalization for Person Re-Identification" @default.
• W3113448926 cites W1596233070 @default.
• W3113448926 cites W1920259731 @default.
• W3113448926 cites W1920962657 @default.
• W3113448926 cites W1997206883 @default.
• W3113448926 cites W2030558520 @default.
• W3113448926 cites W2047632871 @default.
• W3113448926 cites W2108598243 @default.
• W3113448926 cites W2139763424 @default.
• W3113448926 cites W2151065677 @default.
• W3113448926 cites W2194775991 @default.
• W3113448926 cites W2204750386 @default.
• W3113448926 cites W2300840837 @default.
• W3113448926 cites W2342611082 @default.
• W3113448926 cites W2433217581 @default.
• W3113448926 cites W2441160157 @default.
• W3113448926 cites W2467139031 @default.
• W3113448926 cites W2471048925 @default.
• W3113448926 cites W2521429215 @default.
• W3113448926 cites W2585635281 @default.
• W3113448926 cites W2604211872 @default.
• W3113448926 cites W2625674597 @default.
• W3113448926 cites W2736410039 @default.
• W3113448926 cites W2738486593 @default.
• W3113448926 cites W2775106887 @default.
• W3113448926 cites W2898491875 @default.
• W3113448926 cites W2904427185 @default.
• W3113448926 cites W2947319827 @default.
• W3113448926 cites W2963000559 @default.
• W3113448926 cites W2963047834 @default.
• W3113448926 cites W2963163009 @default.
• W3113448926 cites W2963557071 @default.
• W3113448926 cites W2964044605 @default.
• W3113448926 cites W2964289004 @default.
• W3113448926 cites W2967515867 @default.
• W3113448926 cites W3003755145 @default.
• W3113448926 cites W3100506510 @default.
• W3113448926 cites W3103352455 @default.
• W3113448926 doi "https://doi.org/10.1109/tip.2020.3046864" @default.
• W3113448926 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33382653" @default.
• W3113448926 hasPublicationYear "2021" @default.
• W3113448926 type Work @default.
• W3113448926 sameAs 3113448926 @default.
• W3113448926 citedByCount "28" @default.
• W3113448926 countsByYear W31134489262021 @default.
• W3113448926 countsByYear W31134489262022 @default.
• W3113448926 countsByYear W31134489262023 @default.
• W3113448926 crossrefType "journal-article" @default.
• W3113448926 hasAuthorship W3113448926A5016271966 @default.
• W3113448926 hasAuthorship W3113448926A5067029753 @default.
• W3113448926 hasAuthorship W3113448926A5075200053 @default.
• W3113448926 hasBestOaLocation W31134489261 @default.
• W3113448926 hasConcept C116834253 @default.
• W3113448926 hasConcept C119857082 @default.
• W3113448926 hasConcept C134306372 @default.
• W3113448926 hasConcept C138885662 @default.
• W3113448926 hasConcept C153180895 @default.
• W3113448926 hasConcept C154945302 @default.
• W3113448926 hasConcept C177148314 @default.
• W3113448926 hasConcept C17744445 @default.
• W3113448926 hasConcept C199539241 @default.
• W3113448926 hasConcept C2776359362 @default.
• W3113448926 hasConcept C2776401178 @default.
• W3113448926 hasConcept C33923547 @default.
• W3113448926 hasConcept C36503486 @default.
• W3113448926 hasConcept C37736160 @default.
• W3113448926 hasConcept C41008148 @default.
• W3113448926 hasConcept C41895202 @default.
• W3113448926 hasConcept C48044578 @default.
• W3113448926 hasConcept C59404180 @default.
• W3113448926 hasConcept C59822182 @default.
• W3113448926 hasConcept C77088390 @default.
• W3113448926 hasConcept C86803240 @default.
• W3113448926 hasConcept C94625758 @default.
• W3113448926 hasConceptScore W3113448926C116834253 @default.
• W3113448926 hasConceptScore W3113448926C119857082 @default.
• W3113448926 hasConceptScore W3113448926C134306372 @default.
• W3113448926 hasConceptScore W3113448926C138885662 @default.
• W3113448926 hasConceptScore W3113448926C153180895 @default.
• W3113448926 hasConceptScore W3113448926C154945302 @default.
• W3113448926 hasConceptScore W3113448926C177148314 @default.
• W3113448926 hasConceptScore W3113448926C17744445 @default.
• W3113448926 hasConceptScore W3113448926C199539241 @default.
• W3113448926 hasConceptScore W3113448926C2776359362 @default.
• W3113448926 hasConceptScore W3113448926C2776401178 @default.
• W3113448926 hasConceptScore W3113448926C33923547 @default.
• W3113448926 hasConceptScore W3113448926C36503486 @default.
• W3113448926 hasConceptScore W3113448926C37736160 @default.
• W3113448926 hasConceptScore W3113448926C41008148 @default.
• W3113448926 hasConceptScore W3113448926C41895202 @default.
• W3113448926 hasConceptScore W3113448926C48044578 @default.

• next