Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382118226> ?p ?o ?g. }
- W4382118226 endingPage "309" @default.
- W4382118226 startingPage "290" @default.
- W4382118226 abstract "Human action recognition based on WiFi Channel State Information (CSI) has attracted enormous attention in recent years. Although performing well under supervised learning, the recognition model suffers from significant performance degradation when applied in a new domain (e.g. a new environment, a different location, or a new user). To enable the recognition model robust to domains, researchers have proposed various methods, including semi-supervised domain adaptation, unsupervised domain adaptation, and domain generalization. Semi-supervised and unsupervised solutions still require a large number of partially-labeled or unlabeled samples in the new domain, while domain generalization solutions have difficulties in achieving acceptable accuracy. To mitigate these problems, we propose a one-shot bimodal domain adaptation method to achieve cross domain action recognition with much reduced effort. The method contains two key points. One is that it synthesizes virtual samples to augment the training datatset of the target domain, requiring only one sample per action in the target domain. The other is that it regards the amplitude and the phase as two consistent modals and fuses them to enhance the recognition accuracy. Virtual data synthesis is achieved by linear transformation with dynamic domain weights and the synthesis autoencoder. Bimodal fusion is achieved by the fusion autoencoder and feature concatenation under the criterion of consistency. Evaluations on daily activities achieved the average accuracy of 85.03% and 90.53% at target locations, 87.90% and 82.40% in target rooms. Evaluations on hand gestures achieved the average accuracy of 91.67% and 85.53% on target users, 83.04% and 88.01% in target rooms." @default.
- W4382118226 created "2023-06-27" @default.
- W4382118226 creator A5021353633 @default.
- W4382118226 creator A5035478126 @default.
- W4382118226 creator A5037528282 @default.
- W4382118226 creator A5071191374 @default.
- W4382118226 date "2023-01-01" @default.
- W4382118226 modified "2023-09-26" @default.
- W4382118226 title "Towards Cross Domain CSI Action Recognition Through One-Shot Bimodal Domain Adaptation" @default.
- W4382118226 cites W2054642006 @default.
- W4382118226 cites W2064081294 @default.
- W4382118226 cites W2089695767 @default.
- W4382118226 cites W2626807326 @default.
- W4382118226 cites W2808442904 @default.
- W4382118226 cites W2896542121 @default.
- W4382118226 cites W2897132279 @default.
- W4382118226 cites W2897189857 @default.
- W4382118226 cites W2904994966 @default.
- W4382118226 cites W2909052447 @default.
- W4382118226 cites W2931750383 @default.
- W4382118226 cites W2938652275 @default.
- W4382118226 cites W2950821050 @default.
- W4382118226 cites W2966927162 @default.
- W4382118226 cites W2967202213 @default.
- W4382118226 cites W2969645632 @default.
- W4382118226 cites W2974216175 @default.
- W4382118226 cites W2980714463 @default.
- W4382118226 cites W2982661692 @default.
- W4382118226 cites W3006408325 @default.
- W4382118226 cites W3011762860 @default.
- W4382118226 cites W3012910746 @default.
- W4382118226 cites W3018493579 @default.
- W4382118226 cites W3018805456 @default.
- W4382118226 cites W3035892629 @default.
- W4382118226 cites W3040956619 @default.
- W4382118226 cites W3044315440 @default.
- W4382118226 cites W3045907623 @default.
- W4382118226 cites W3088369757 @default.
- W4382118226 cites W3121283712 @default.
- W4382118226 cites W3126121953 @default.
- W4382118226 cites W3132590175 @default.
- W4382118226 cites W3133129984 @default.
- W4382118226 cites W3133546873 @default.
- W4382118226 cites W3137577088 @default.
- W4382118226 doi "https://doi.org/10.1007/978-3-031-34776-4_16" @default.
- W4382118226 hasPublicationYear "2023" @default.
- W4382118226 type Work @default.
- W4382118226 citedByCount "0" @default.
- W4382118226 crossrefType "book-chapter" @default.
- W4382118226 hasAuthorship W4382118226A5021353633 @default.
- W4382118226 hasAuthorship W4382118226A5035478126 @default.
- W4382118226 hasAuthorship W4382118226A5037528282 @default.
- W4382118226 hasAuthorship W4382118226A5071191374 @default.
- W4382118226 hasConcept C101738243 @default.
- W4382118226 hasConcept C119857082 @default.
- W4382118226 hasConcept C134306372 @default.
- W4382118226 hasConcept C138885662 @default.
- W4382118226 hasConcept C153180895 @default.
- W4382118226 hasConcept C154945302 @default.
- W4382118226 hasConcept C177148314 @default.
- W4382118226 hasConcept C26517878 @default.
- W4382118226 hasConcept C2776401178 @default.
- W4382118226 hasConcept C33923547 @default.
- W4382118226 hasConcept C36503486 @default.
- W4382118226 hasConcept C38652104 @default.
- W4382118226 hasConcept C41008148 @default.
- W4382118226 hasConcept C41895202 @default.
- W4382118226 hasConcept C50644808 @default.
- W4382118226 hasConceptScore W4382118226C101738243 @default.
- W4382118226 hasConceptScore W4382118226C119857082 @default.
- W4382118226 hasConceptScore W4382118226C134306372 @default.
- W4382118226 hasConceptScore W4382118226C138885662 @default.
- W4382118226 hasConceptScore W4382118226C153180895 @default.
- W4382118226 hasConceptScore W4382118226C154945302 @default.
- W4382118226 hasConceptScore W4382118226C177148314 @default.
- W4382118226 hasConceptScore W4382118226C26517878 @default.
- W4382118226 hasConceptScore W4382118226C2776401178 @default.
- W4382118226 hasConceptScore W4382118226C33923547 @default.
- W4382118226 hasConceptScore W4382118226C36503486 @default.
- W4382118226 hasConceptScore W4382118226C38652104 @default.
- W4382118226 hasConceptScore W4382118226C41008148 @default.
- W4382118226 hasConceptScore W4382118226C41895202 @default.
- W4382118226 hasConceptScore W4382118226C50644808 @default.
- W4382118226 hasLocation W43821182261 @default.
- W4382118226 hasOpenAccess W4382118226 @default.
- W4382118226 hasPrimaryLocation W43821182261 @default.
- W4382118226 hasRelatedWork W2292254049 @default.
- W4382118226 hasRelatedWork W2572600474 @default.
- W4382118226 hasRelatedWork W2592385986 @default.
- W4382118226 hasRelatedWork W2776466379 @default.
- W4382118226 hasRelatedWork W2785535669 @default.
- W4382118226 hasRelatedWork W2897995864 @default.
- W4382118226 hasRelatedWork W2998168123 @default.
- W4382118226 hasRelatedWork W3090006671 @default.
- W4382118226 hasRelatedWork W4220775285 @default.
- W4382118226 hasRelatedWork W4287995534 @default.
- W4382118226 isParatext "false" @default.
- W4382118226 isRetracted "false" @default.