Samsung electronics co., ltd. (20250087025). ATTENTIVE SENSING FOR EFFICIENT MULTIMODAL GESTURE RECOGNITION: Difference between revisions
Creating a new page |
Creating a new page |
||
| Line 8: | Line 8: | ||
[[Category:samsung electronics co., ltd.]] | [[Category:samsung electronics co., ltd.]] | ||
==Inventor(s)== | |||
[[:Category:Mostafa El-khamy of San Diego CA (US)|Mostafa El-khamy of San Diego CA (US)]][[Category:Mostafa El-khamy of San Diego CA (US)]] | |||
[[:Category:Soheil Hor of Sunnyvale CA (US)|Soheil Hor of Sunnyvale CA (US)]][[Category:Soheil Hor of Sunnyvale CA (US)]] | |||
[[:Category:Yanlin Zhou of San Diego CA (US)|Yanlin Zhou of San Diego CA (US)]][[Category:Yanlin Zhou of San Diego CA (US)]] | |||
==ATTENTIVE SENSING FOR EFFICIENT MULTIMODAL GESTURE RECOGNITION== | |||
This abstract first appeared for US patent application 20250087025 titled 'ATTENTIVE SENSING FOR EFFICIENT MULTIMODAL GESTURE RECOGNITION | |||
==Original Abstract Submitted== | |||
a system and a method for performing gesture recognition are disclosed, the method comprising detecting a gesture using a primary modality; evaluating an expected accuracy gain (eag) to identify a modality that yields a maximum relative eag among the primary modality and one or more secondary modalities; and activating the one or more secondary modalities for detecting the gesture if the one or more secondary modalities correspond to the modality that yields the maximum relative eag. | |||
[[Category:G06V40/20]] | |||
[[Category:CPC_G06V40/20]] | |||
Latest revision as of 02:09, 15 March 2025
ATTENTIVE SENSING FOR EFFICIENT MULTIMODAL GESTURE RECOGNITION
Organization Name
Inventor(s)
Mostafa El-khamy of San Diego CA (US)
Soheil Hor of Sunnyvale CA (US)
Yanlin Zhou of San Diego CA (US)
ATTENTIVE SENSING FOR EFFICIENT MULTIMODAL GESTURE RECOGNITION
This abstract first appeared for US patent application 20250087025 titled 'ATTENTIVE SENSING FOR EFFICIENT MULTIMODAL GESTURE RECOGNITION
Original Abstract Submitted
a system and a method for performing gesture recognition are disclosed, the method comprising detecting a gesture using a primary modality; evaluating an expected accuracy gain (eag) to identify a modality that yields a maximum relative eag among the primary modality and one or more secondary modalities; and activating the one or more secondary modalities for detecting the gesture if the one or more secondary modalities correspond to the modality that yields the maximum relative eag.