DeepMon: Mobile GPU-based deep learning framework for continuous vision applications

• المؤلفون الرئيسيون: HUYNH, Nguyen Loc, LEE, Youngki, BALAN, Rajesh Krishna
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2017
• الموضوعات: Continuous vision; Deep learning; Mobile GPU; Mobile sensing; Computer and Systems Architecture; Software Engineering
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/3671; https://ink.library.smu.edu.sg/context/sis_research/article/4673/viewcontent/mobisys17_paper07.pdf
• المؤسسة: Singapore Management University

The rapid emergence of head-mounted devices such as the Microsoft Holo-lens enables a wide variety of continuous vision applications. Such applications often adopt deep-learning algorithms such as CNN and RNN to extract rich contextual information from the first-person-view video streams. Despite th...