FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312505280> ?p ?o ?g. }

• W4312505280 endingPage "1122" @default.
• W4312505280 startingPage "1109" @default.
• W4312505280 abstract "Visual place recognition is a challenging problem in robotics and autonomous systems because the scene undergoes appearance and viewpoint changes in a changing world. Existing state-of-the-art methods heavily rely on CNN-based architectures. However, CNN cannot effectively model image spatial structure information due to the inherent locality. To address this issue, this paper proposes a novel Transformer-based place recognition method to combine local details, spatial context, and semantic information for image feature embedding. Firstly, to overcome the inherent locality of the convolutional neural network (CNN), a hybrid CNN-Transformer feature extraction network is introduced. The network utilizes the feature pyramid based on CNN to obtain the detailed visual understanding, while using the vision Transformer to model image contextual information and aggregate task-related features dynamically. Specifically, the multi-level output tokens from the Transformer are fed into a single Transformer encoder block to fuse multi-scale spatial information. Secondly, to acquire the multi-scale semantic information, a global semantic NetVLAD aggregation strategy is constructed. This strategy employs semantic enhanced NetVLAD, imposing prior knowledge on the terms of the Vector of Locally Aggregated Descriptors (VLAD), to aggregate multi-level token maps, and further concatenates the multi-level semantic features globally. Finally, to alleviate the disadvantage that the fixed margin of triplet loss leads to the suboptimal convergence, an adaptive triplet loss with dynamic margin is proposed. Extensive experiments on public datasets show that the learned features are robust to appearance and viewpoint changes and achieve promising performance compared to state-of-the-arts." @default.
• W4312505280 created "2023-01-05" @default.
• W4312505280 creator A5012281552 @default.
• W4312505280 creator A5019177930 @default.
• W4312505280 creator A5057728337 @default.
• W4312505280 creator A5073029812 @default.
• W4312505280 date "2023-03-01" @default.
• W4312505280 modified "2023-10-09" @default.
• W4312505280 title "Hybrid CNN-Transformer Features for Visual Place Recognition" @default.
• W4312505280 cites W1162411702 @default.
• W4312505280 cites W1524680991 @default.
• W4312505280 cites W1703761565 @default.
• W4312505280 cites W1950136256 @default.
• W4312505280 cites W2019085623 @default.
• W4312505280 cites W2034082222 @default.
• W4312505280 cites W2054957336 @default.
• W4312505280 cites W2062118960 @default.
• W4312505280 cites W2071027807 @default.
• W4312505280 cites W2073761981 @default.
• W4312505280 cites W2108598243 @default.
• W4312505280 cites W2110405746 @default.
• W4312505280 cites W2117228865 @default.
• W4312505280 cites W2119605622 @default.
• W4312505280 cites W2144824356 @default.
• W4312505280 cites W2146881125 @default.
• W4312505280 cites W2150066425 @default.
• W4312505280 cites W2151103935 @default.
• W4312505280 cites W2155893237 @default.
• W4312505280 cites W2291826042 @default.
• W4312505280 cites W2340897893 @default.
• W4312505280 cites W2550553598 @default.
• W4312505280 cites W2580440899 @default.
• W4312505280 cites W2737075200 @default.
• W4312505280 cites W2810077221 @default.
• W4312505280 cites W2885052112 @default.
• W4312505280 cites W2939122829 @default.
• W4312505280 cites W2940791172 @default.
• W4312505280 cites W2955147859 @default.
• W4312505280 cites W2963521811 @default.
• W4312505280 cites W2964157791 @default.
• W4312505280 cites W2990519439 @default.
• W4312505280 cites W2997164612 @default.
• W4312505280 cites W301022506 @default.
• W4312505280 cites W3034213661 @default.
• W4312505280 cites W3034275286 @default.
• W4312505280 cites W3035022492 @default.
• W4312505280 cites W3095367607 @default.
• W4312505280 cites W3096609285 @default.
• W4312505280 cites W3099206234 @default.
• W4312505280 cites W3107331169 @default.
• W4312505280 cites W3107919704 @default.
• W4312505280 cites W3110076758 @default.
• W4312505280 cites W3110536152 @default.
• W4312505280 cites W3120620666 @default.
• W4312505280 cites W3128990302 @default.
• W4312505280 cites W3134941379 @default.
• W4312505280 cites W3138516171 @default.
• W4312505280 cites W3165924482 @default.
• W4312505280 cites W3168649818 @default.
• W4312505280 cites W3171125843 @default.
• W4312505280 cites W3171516518 @default.
• W4312505280 cites W3173736705 @default.
• W4312505280 cites W3192804777 @default.
• W4312505280 cites W3206622090 @default.
• W4312505280 cites W3216991452 @default.
• W4312505280 cites W4205474609 @default.
• W4312505280 cites W4206760693 @default.
• W4312505280 cites W4214493665 @default.
• W4312505280 cites W4296122752 @default.
• W4312505280 cites W4312336574 @default.
• W4312505280 cites W4312710812 @default.
• W4312505280 cites W56385144 @default.
• W4312505280 doi "https://doi.org/10.1109/tcsvt.2022.3212434" @default.
• W4312505280 hasPublicationYear "2023" @default.
• W4312505280 type Work @default.
• W4312505280 citedByCount "5" @default.
• W4312505280 countsByYear W43125052802023 @default.
• W4312505280 crossrefType "journal-article" @default.
• W4312505280 hasAuthorship W4312505280A5012281552 @default.
• W4312505280 hasAuthorship W4312505280A5019177930 @default.
• W4312505280 hasAuthorship W4312505280A5057728337 @default.
• W4312505280 hasAuthorship W4312505280A5073029812 @default.
• W4312505280 hasConcept C111919701 @default.
• W4312505280 hasConcept C118505674 @default.
• W4312505280 hasConcept C121332964 @default.
• W4312505280 hasConcept C138885662 @default.
• W4312505280 hasConcept C153180895 @default.
• W4312505280 hasConcept C154945302 @default.
• W4312505280 hasConcept C165801399 @default.
• W4312505280 hasConcept C190502265 @default.
• W4312505280 hasConcept C2779808786 @default.
• W4312505280 hasConcept C31972630 @default.
• W4312505280 hasConcept C41008148 @default.
• W4312505280 hasConcept C41895202 @default.
• W4312505280 hasConcept C50644808 @default.
• W4312505280 hasConcept C59404180 @default.
• W4312505280 hasConcept C62520636 @default.
• W4312505280 hasConcept C66322947 @default.

• next