File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1145/3458750
- Scopus: eid_2-s2.0-85114460624
- WOS: WOS:000693585500001
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: XGest: Enabling Cross-Label Gesture Recognition with RF Signals
Title | XGest: Enabling Cross-Label Gesture Recognition with RF Signals |
---|---|
Authors | |
Keywords | machine learning gesture recognition RF sensing |
Issue Date | 2021 |
Citation | ACM Transactions on Sensor Networks, 2021, v. 17, n. 4, article no. 37 How to Cite? |
Abstract | Extensive efforts have been devoted to human gesture recognition with radio frequency (RF) signals. However, their performance degrades when applied to novel gesture classes that have never been seen in the training set. To handle unseen gestures, extra efforts are inevitable in terms of data collection and model retraining. In this article, we present XGest, a cross-label gesture recognition system that can accurately recognize gestures outside of the predefined gesture set with zero extra training effort. The key insight of XGest is to build a knowledge transfer framework between different gesture datasets. Specifically, we design a novel deep neural network to embed gestures into a high-dimensional Euclidean space. Several techniques are designed to tackle the spatial resolution limits imposed by RF hardware and the specular reflection effect of RF signals in this model. We implement XGest on a commodity mmWave device, and extensive experiments have demonstrated the significant recognition performance. |
Persistent Identifier | http://hdl.handle.net/10722/303822 |
ISSN | 2021 Impact Factor: 2.560 2020 SCImago Journal Rankings: 0.598 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhang, Yi | - |
dc.contributor.author | Yang, Zheng | - |
dc.contributor.author | Zhang, Guidong | - |
dc.contributor.author | Wu, Chenshu | - |
dc.contributor.author | Zhang, Li | - |
dc.date.accessioned | 2021-09-15T08:26:05Z | - |
dc.date.available | 2021-09-15T08:26:05Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | ACM Transactions on Sensor Networks, 2021, v. 17, n. 4, article no. 37 | - |
dc.identifier.issn | 1550-4859 | - |
dc.identifier.uri | http://hdl.handle.net/10722/303822 | - |
dc.description.abstract | Extensive efforts have been devoted to human gesture recognition with radio frequency (RF) signals. However, their performance degrades when applied to novel gesture classes that have never been seen in the training set. To handle unseen gestures, extra efforts are inevitable in terms of data collection and model retraining. In this article, we present XGest, a cross-label gesture recognition system that can accurately recognize gestures outside of the predefined gesture set with zero extra training effort. The key insight of XGest is to build a knowledge transfer framework between different gesture datasets. Specifically, we design a novel deep neural network to embed gestures into a high-dimensional Euclidean space. Several techniques are designed to tackle the spatial resolution limits imposed by RF hardware and the specular reflection effect of RF signals in this model. We implement XGest on a commodity mmWave device, and extensive experiments have demonstrated the significant recognition performance. | - |
dc.language | eng | - |
dc.relation.ispartof | ACM Transactions on Sensor Networks | - |
dc.subject | machine learning | - |
dc.subject | gesture recognition | - |
dc.subject | RF sensing | - |
dc.title | XGest: Enabling Cross-Label Gesture Recognition with RF Signals | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1145/3458750 | - |
dc.identifier.scopus | eid_2-s2.0-85114460624 | - |
dc.identifier.volume | 17 | - |
dc.identifier.issue | 4 | - |
dc.identifier.spage | article no. 37 | - |
dc.identifier.epage | article no. 37 | - |
dc.identifier.eissn | 1550-4867 | - |
dc.identifier.isi | WOS:000693585500001 | - |