Search

Your search keyword '"Li, Guangya"' showing total 22 results
Start Over Author "Li, Guangya" Search Limiters Academic (Peer-Reviewed) Journals
22 results on '"Li, Guangya"'

3. DEEPEYE: A Compact and Accurate Video Comprehension at Terminal Devices Compressed with Quantization and Tensorization

Author

Cheng, Yuan, Li, Guangya, Chen, Hai-Bao, Tan, Sheldon X. -D., and Yu, Hao

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

As it requires a huge number of parameters when exposed to high dimensional inputs in video detection and classification, there is a grand challenge to develop a compact yet accurate video comprehension at terminal devices. Current works focus on optimizations of video detection and classification in a separated fashion. In this paper, we introduce a video comprehension (object detection and action recognition) system for terminal devices, namely DEEPEYE. Based on You Only Look Once (YOLO), we have developed an 8-bit quantization method when training YOLO; and also developed a tensorized-compression method of Recurrent Neural Network (RNN) composed of features extracted from YOLO. The developed quantization and tensorization can significantly compress the original network model yet with maintained accuracy. Using the challenging video datasets: MOMENTS and UCF11 as benchmarks, the results show that the proposed DEEPEYE achieves 3.994x model compression rate with only 0.47% mAP decreased; and 15,047x parameter reduction and 2.87x speed-up with 16.58% accuracy improvement., Comment: 10 pages, 9 figures and 2 tables

Published
2018

8. A two-step lineage reprogramming strategy to generate functionally competent human hepatocytes from fibroblasts

Author

Xie, Bingqing, Sun, Da, Du, Yuanyuan, Jia, Jun, Sun, Shicheng, Xu, Jun, Liu, Yifang, Xiang, Chengang, Chen, Sitong, Xie, Huangfan, Wang, Qiming, Li, Guangya, LYU, Xuehui, Shen, Hui, Li, Shiyu, Wu, Min, Zhang, Xiaonan, Pu, Yue, Xiang, Kuanhui, Lai, Weifeng, Du, Peng, Yuan, Zhenghong, Li, Cheng, Shi, Yan, Lu, Shichun, and Deng, Hongkui

Published
2019
Full Text
View/download PDF

9. The efficient generation of functional human hepatocytes from chemically induced pluripotent stem cells.

Author

Lv, Yun, Rao, Ziyan, Liu, Lulu, Jia, Jun, Wu, Chenyang, Xu, Jun, Du, Yuanyuan, Liu, Yinan, Liu, Bei, Shi, Jihang, Li, Guangya, Zhao, Dongyu, and Deng, Hongkui

Subjects
PLURIPOTENT stem cells, LIVER cells, DRUG discovery, PROGENITOR cells, RNA sequencing
Abstract

Derivation of human hepatocytes from pluripotent stem cells in vitro has important applications including cell therapy and drug discovery. However, the differentiation of pluripotent stem cells into hepatocytes in vitro was not well recapitulated the development of liver. Here, we developed a differentiation protocol by mimicking the two‐stage development of hepatoblasts, which permits the efficient generation of hepatic progenitor cells from chemically induced pluripotent stem cells (hCiPSCs). Single‐cell RNA sequencing (scRNA‐seq) indicates the similarity between hepatoblasts differentiated in vitro and in vivo. Moreover, hCiPSC‐derived hepatic progenitor cells can further differentiate into hepatocytes that are similar to primary human hepatocytes with respect to gene expression and key hepatic functions. Our results demonstrate the feasibility of generating hepatic progenitor cells and hepatocytes from hCiPSCs with high efficiency and set the foundation for broad translational applications of hCiPSC‐derived hepatocytes. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

14. RATP Fall 2020 Demo Project

Author

Li, Guangya

Subjects
ComputingMilieux_COMPUTERSANDEDUCATION, Social and Behavioral Sciences
Abstract

A project to test the relationship between the format of the online courses and the importance of interactivity.

Published
2022
Full Text
View/download PDF

15. DEEPEYE

Author

Cheng, Yuan, primary, Li, Guangya, additional, Wong, Ngai, additional, Chen, Hai-Bao, additional, and Yu, Hao, additional

Published
2020
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results