FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381193485> ?p ?o ?g. }

• W4381193485 endingPage "25" @default.
• W4381193485 startingPage "1" @default.
• W4381193485 abstract "Radar sensing technologies offer several advantages over other gesture input modalities, such as the ability to reliably sense human movements, a reasonable deployment cost, insensitivity to ambient conditions such as light, temperature, and the ability to preserve anonymity. These advantages come at the price of high processing complexity mainly due to the spatio-temporal variations of gesture articulation performed by different people. Deep learning methods, such as CNN-LSTM and 3D CNN-LSTM, have a high potential to recognize radar-based gestures but usually require hundreds or thousands of labeled training samples and high processing power. Asking a lot of people to acquire a lot of gestures is particularly tedious and tiring to the point of being unrealistic. To overcome these challenges, we propose FORTE, a hand gesture recognition with few samples based on an optimized CNN architecture working on pre-processed raw data. Using a k=5-fold cross-validation, we define and compare three alternative CNNs for recognizing hand gestures acquired in a semi-mobile context of use with a portable radar attached to a smartphone. The best CNN reaches an accuracy of 94.96% with a precision of 95.92% and a recall of 96.03% for a dataset composed of solely 5 participants producing 2 samples for 20 classes covering 1 pointing, 2 pantomimic, 3 iconic, and 14 semaphoric gestures. We suggest some implications for designing radar-based gestures and we discuss the limitations of this approach." @default.
• W4381193485 created "2023-06-20" @default.
• W4381193485 creator A5002970970 @default.
• W4381193485 creator A5015455700 @default.
• W4381193485 creator A5027874987 @default.
• W4381193485 creator A5043868402 @default.
• W4381193485 creator A5092203331 @default.
• W4381193485 date "2023-06-14" @default.
• W4381193485 modified "2023-09-25" @default.
• W4381193485 title "FORTE: Few Samples for Recognizing Hand Gestures with a Smartphone-attached Radar" @default.
• W4381193485 cites W1947634087 @default.
• W4381193485 cites W1973331351 @default.
• W4381193485 cites W2011191879 @default.
• W4381193485 cites W2070584460 @default.
• W4381193485 cites W2093639577 @default.
• W4381193485 cites W2511561981 @default.
• W4381193485 cites W2754889825 @default.
• W4381193485 cites W2789382606 @default.
• W4381193485 cites W2794189208 @default.
• W4381193485 cites W2808135883 @default.
• W4381193485 cites W2886305296 @default.
• W4381193485 cites W2891778553 @default.
• W4381193485 cites W2896451019 @default.
• W4381193485 cites W2899287308 @default.
• W4381193485 cites W2908889571 @default.
• W4381193485 cites W2908899527 @default.
• W4381193485 cites W2922148914 @default.
• W4381193485 cites W2923491365 @default.
• W4381193485 cites W2941266383 @default.
• W4381193485 cites W2950678157 @default.
• W4381193485 cites W2966778699 @default.
• W4381193485 cites W2971144987 @default.
• W4381193485 cites W2974420364 @default.
• W4381193485 cites W2974623198 @default.
• W4381193485 cites W3043120882 @default.
• W4381193485 cites W3113022896 @default.
• W4381193485 cites W3115265657 @default.
• W4381193485 cites W3146968685 @default.
• W4381193485 cites W3162968607 @default.
• W4381193485 cites W3170753664 @default.
• W4381193485 cites W3195349361 @default.
• W4381193485 cites W3198738227 @default.
• W4381193485 cites W4206600472 @default.
• W4381193485 cites W4220782259 @default.
• W4381193485 cites W4220794923 @default.
• W4381193485 cites W4283317971 @default.
• W4381193485 cites W2783421817 @default.
• W4381193485 cites W2938431921 @default.
• W4381193485 doi "https://doi.org/10.1145/3593231" @default.
• W4381193485 hasPublicationYear "2023" @default.
• W4381193485 type Work @default.
• W4381193485 citedByCount "0" @default.
• W4381193485 crossrefType "journal-article" @default.
• W4381193485 hasAuthorship W4381193485A5002970970 @default.
• W4381193485 hasAuthorship W4381193485A5015455700 @default.
• W4381193485 hasAuthorship W4381193485A5027874987 @default.
• W4381193485 hasAuthorship W4381193485A5043868402 @default.
• W4381193485 hasAuthorship W4381193485A5092203331 @default.
• W4381193485 hasBestOaLocation W43811934851 @default.
• W4381193485 hasConcept C107457646 @default.
• W4381193485 hasConcept C108583219 @default.
• W4381193485 hasConcept C151730666 @default.
• W4381193485 hasConcept C154945302 @default.
• W4381193485 hasConcept C159437735 @default.
• W4381193485 hasConcept C207347870 @default.
• W4381193485 hasConcept C2779343474 @default.
• W4381193485 hasConcept C28490314 @default.
• W4381193485 hasConcept C31972630 @default.
• W4381193485 hasConcept C41008148 @default.
• W4381193485 hasConcept C554190296 @default.
• W4381193485 hasConcept C76155785 @default.
• W4381193485 hasConcept C86803240 @default.
• W4381193485 hasConceptScore W4381193485C107457646 @default.
• W4381193485 hasConceptScore W4381193485C108583219 @default.
• W4381193485 hasConceptScore W4381193485C151730666 @default.
• W4381193485 hasConceptScore W4381193485C154945302 @default.
• W4381193485 hasConceptScore W4381193485C159437735 @default.
• W4381193485 hasConceptScore W4381193485C207347870 @default.
• W4381193485 hasConceptScore W4381193485C2779343474 @default.
• W4381193485 hasConceptScore W4381193485C28490314 @default.
• W4381193485 hasConceptScore W4381193485C31972630 @default.
• W4381193485 hasConceptScore W4381193485C41008148 @default.
• W4381193485 hasConceptScore W4381193485C554190296 @default.
• W4381193485 hasConceptScore W4381193485C76155785 @default.
• W4381193485 hasConceptScore W4381193485C86803240 @default.
• W4381193485 hasFunder F4320321390 @default.
• W4381193485 hasFunder F4320323983 @default.
• W4381193485 hasFunder F4320326734 @default.
• W4381193485 hasIssue "EICS" @default.
• W4381193485 hasLocation W43811934851 @default.
• W4381193485 hasOpenAccess W4381193485 @default.
• W4381193485 hasPrimaryLocation W43811934851 @default.
• W4381193485 hasRelatedWork W1977995219 @default.
• W4381193485 hasRelatedWork W2057046019 @default.
• W4381193485 hasRelatedWork W2507962226 @default.
• W4381193485 hasRelatedWork W2543128534 @default.
• W4381193485 hasRelatedWork W2739074143 @default.
• W4381193485 hasRelatedWork W3096217294 @default.

• next