Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386453655> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W4386453655 endingPage "1" @default.
- W4386453655 startingPage "1" @default.
- W4386453655 abstract "Hand pose estimation (HPE), which aims to identify and recover the keypoints of a hand, is essential to many potential applications. Conventional computer vision (CV) methods extract visible features from images or videos captured by cameras. However, they are heavily affected by low image contrast, fail to work under occluded scenarios, and inevitably incur privacy concerns. Fortunately, CV leveraging widely available radio frequency (RF) signals (also known as RF vision) can fully address the problem with much lower computational complexity. In this paper, we propose Ske-Fi as an avatar of HPE enabled by RF vision, which uses the emerging Impulse Radio Ultra-Wide Band (IR-UWB) available on smart devices (e.g., Apple air tag) to sense the reflected RF signals of a hand to extract the hand skeleton features for pose estimation. Whereas Ske-Fi is apparently immune to low contrast and occlusion, its substantially reduced resolution provided by IR-UWB signal makes the resulting RF image incomprehensible by human eyes and thus negating offline labeling. To address the challenge, Ske-Fi involves a deep complex-valued neural network Ske-Net trained via a cross-modal supervision framework; it uses a synchronized camera assisted by a state-of-the-art vision network as a teacher to teach Ske-Net as a student in independently performing HPE afterward. Furthermore, for occlusion cases, Ske-Fi adopts an adversarial learning scheme to distill HPE features regardless of diversified occlusions. Our extensive evaluations evidently demonstrate that Ske-Fi outperforms conventional CV solutions which achieves a comparable HPE accuracy under normal circumstances and maintains this accuracy under adverse scenarios." @default.
- W4386453655 created "2023-09-06" @default.
- W4386453655 creator A5041894655 @default.
- W4386453655 creator A5042055991 @default.
- W4386453655 creator A5042967628 @default.
- W4386453655 creator A5079870134 @default.
- W4386453655 creator A5081222445 @default.
- W4386453655 creator A5086887250 @default.
- W4386453655 date "2023-01-01" @default.
- W4386453655 modified "2023-10-15" @default.
- W4386453655 title "Ske-Fi: Estimating Hand Poses via RF Vision Under Low Contrast and Occlusion" @default.
- W4386453655 doi "https://doi.org/10.1109/jiot.2023.3312316" @default.
- W4386453655 hasPublicationYear "2023" @default.
- W4386453655 type Work @default.
- W4386453655 citedByCount "0" @default.
- W4386453655 crossrefType "journal-article" @default.
- W4386453655 hasAuthorship W4386453655A5041894655 @default.
- W4386453655 hasAuthorship W4386453655A5042055991 @default.
- W4386453655 hasAuthorship W4386453655A5042967628 @default.
- W4386453655 hasAuthorship W4386453655A5079870134 @default.
- W4386453655 hasAuthorship W4386453655A5081222445 @default.
- W4386453655 hasAuthorship W4386453655A5086887250 @default.
- W4386453655 hasConcept C107457646 @default.
- W4386453655 hasConcept C108583219 @default.
- W4386453655 hasConcept C154945302 @default.
- W4386453655 hasConcept C21916231 @default.
- W4386453655 hasConcept C2776502983 @default.
- W4386453655 hasConcept C2777365542 @default.
- W4386453655 hasConcept C2988552953 @default.
- W4386453655 hasConcept C31972630 @default.
- W4386453655 hasConcept C41008148 @default.
- W4386453655 hasConcept C74064498 @default.
- W4386453655 hasConcept C76155785 @default.
- W4386453655 hasConceptScore W4386453655C107457646 @default.
- W4386453655 hasConceptScore W4386453655C108583219 @default.
- W4386453655 hasConceptScore W4386453655C154945302 @default.
- W4386453655 hasConceptScore W4386453655C21916231 @default.
- W4386453655 hasConceptScore W4386453655C2776502983 @default.
- W4386453655 hasConceptScore W4386453655C2777365542 @default.
- W4386453655 hasConceptScore W4386453655C2988552953 @default.
- W4386453655 hasConceptScore W4386453655C31972630 @default.
- W4386453655 hasConceptScore W4386453655C41008148 @default.
- W4386453655 hasConceptScore W4386453655C74064498 @default.
- W4386453655 hasConceptScore W4386453655C76155785 @default.
- W4386453655 hasFunder F4320321001 @default.
- W4386453655 hasFunder F4320322768 @default.
- W4386453655 hasLocation W43864536551 @default.
- W4386453655 hasOpenAccess W4386453655 @default.
- W4386453655 hasPrimaryLocation W43864536551 @default.
- W4386453655 hasRelatedWork W1588781970 @default.
- W4386453655 hasRelatedWork W1891287906 @default.
- W4386453655 hasRelatedWork W1969923398 @default.
- W4386453655 hasRelatedWork W1987421842 @default.
- W4386453655 hasRelatedWork W2036807459 @default.
- W4386453655 hasRelatedWork W2166024367 @default.
- W4386453655 hasRelatedWork W2731899572 @default.
- W4386453655 hasRelatedWork W2772917594 @default.
- W4386453655 hasRelatedWork W2775347418 @default.
- W4386453655 hasRelatedWork W3215138031 @default.
- W4386453655 isParatext "false" @default.
- W4386453655 isRetracted "false" @default.
- W4386453655 workType "article" @default.