Zobrazeno 1 - 10
of 480
pro vyhledávání: '"ZHANG, Deyu"'
This paper addresses the challenges of Online Action Recognition (OAR), a framework that involves instantaneous analysis and classification of behaviors in video streams. OAR must operate under stringent latency constraints, making it an indispensabl
Externí odkaz:
http://arxiv.org/abs/2412.01267
Running LLMs on end devices has garnered significant attention recently due to their advantages in privacy preservation. With the advent of lightweight LLM models and specially designed GPUs, on-device LLM inference has achieved the necessary accurac
Externí odkaz:
http://arxiv.org/abs/2409.04040
Multi-instance Repetitive Action Counting (MRAC) aims to estimate the number of repetitive actions performed by multiple instances in untrimmed videos, commonly found in human-centric domains like sports and exercise. In this paper, we propose MultiC
Externí odkaz:
http://arxiv.org/abs/2409.04035
Empowering In-Browser Deep Learning Inference on Edge Devices with Just-in-Time Kernel Optimizations
Autor:
Jia, Fucheng, Jiang, Shiqi, Cao, Ting, Cui, Wei, Xia, Tianrui, Cao, Xu, Li, Yuanchun, Zhang, Deyu, Ren, Ju, Liu, Yunxin, Qiu, Lili, Yang, Mao
Web is increasingly becoming the primary platform to deliver AI services onto edge devices, making in-browser deep learning (DL) inference more prominent. Nevertheless, the heterogeneity of edge devices, combined with the underdeveloped state of Web
Externí odkaz:
http://arxiv.org/abs/2309.08978
Autor:
Luo, Li, Guo, Mingda, Zhang, Deyu, Hu, Yang, Cui, Tianyou, Zhao, Mengqian, Yin, Jian, Long, Xuwei
Publikováno v:
In Food and Bioproducts Processing December 2024 148:52-61
Publikováno v:
In Engineering Applications of Artificial Intelligence July 2024 133 Part A
Federated meta-learning (FML) has emerged as a promising paradigm to cope with the data limitation and heterogeneity challenges in today's edge learning arena. However, its performance is often limited by slow convergence and corresponding low commun
Externí odkaz:
http://arxiv.org/abs/2108.06453
Autor:
Zhang, Deyu, Wu, Chang, Liu, Yue, Li, Wanshun, Li, Shiyu, Peng, Lisi, Kang, Le, Ullah, Saif, Gong, Zijun, Li, Zhaoshen, Ding, Dan, Jin, Zhendong, Huang, Haojie
Publikováno v:
In Journal of Hazardous Materials 5 April 2024 467
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.