Taipei Tech AIoT Lab

Artificial Intelligence of Things


  • 2021/4/21 - The paper co-work with NetDB, "Efficient Two-stream Action Recognition on FPGA", was accepted by CVPR 2021 ECV Workshop!
  • 2019/10/10 - Our paper "AnyCharge: An IoT Wireless Charging Service for the Public" has been accepted by IEEE IOT Journal!
  • 2018/10/24 - Our paper "VIVID: Virtual Environment for Visual Deep Learning" won the ACM MM 2018 Best Open Source Software Award!


AED Drone

Heart attack is one of the leading causes of death in humans. The portable Automatic External Defibrillator (AED) can automatically detect the patient's heart rhythm pulse and apply an electric shock to restore the heart to work. If patients can be treated with electric shock within one minute, the success rate of first aid can be as high as 90%. In order to save more lives, we cooperate with the Taiwan Public Defibrillation Development Association to develop 4G drone AED emergency services.

Drone Action Recognition

In this project, we develop a large-scale action detector of drone that can recognize numerous complex human actions such as running, eating, smoking, photo shooting, and create a large-scale dataset to evaluate our algorithm.

VIVID - Virtual Environment for Visual Deep Learning

VIVID is a photo-realistic simulator that aims to facilitate deep learning for computer vision, which supports different characters: robot, drone, and automobile. The platform can be used for many research fields including deep reinforcement learning, semantic segmentation object recognition and human action recognition. For more details please visit the project's github page.

Pothole Detection

We work together with Feng Chia University to develop a real-time pothole detector on Xilinx FPGA. Additionally, we propose to train detectors in VIVID, and increase the accuracy with less real training photos. Furthermore, our system can connect to CarSim and simulate the response of real cars' suspension systems.

AnyCharge - An IoT-based Public Charging Service

AnyCharge is a public wireless charging service based on IoT technology. All the chargers are controllable by our cloud. We have deployed around 70 charging spots in Taiwan, Thailand, and Singapore (website, paper).

Mining Telecom Fraud using Social Network Analysis

Telecom fraud is one of the most prevalent crimes today and causes most property loss. To identify the roles of the fraudsters, we cooperate with Criminal Investigation Bureau of Taiwan and propose a Telecom Fraud Analysis Model (TFAM).

Photo Courtesy: KKNews



Prof. Kuan-Ting (K. T.) Lai 賴冠廷

Dr. Kuan-Ting Lai received bachelor's degree in Electric Engineering and master's degree in Computer Science from National Taiwan University in 2003 and 2005. After graduation, he joined Quanta Computer as a video ASIC engineer for 4 years, and started to pursue Ph.D. in 2009, under supervision of Prof. Ming-Syan Chen. During 2012-2013, Dr. Lai visited Prof. Shih-Fu Chang’s DVMM lab at Columbia University, and co-developed a large-scale video event detection system with IBM T. J. Watson Research Center. He received his Ph.D. degree in Feb. 2015 and became the VP of technology at Arkados Group. He also co-founded AnyCharge, a wireless charging service provider in Asia. In 2018, Dr. Lai joined the Department of Electronic Engineering at National Taipei University of Technology (臺北科技大學電子工程系) as an Assistant Professor. His research interests include computer vision, deep learning, virtual-to-real learning and Internet of Things. His habit is traveling around the world by joining conferences and making new friends.


Year 2020

Nehal Ahmad


Chang-Yu Tsou

  • R&D,PtE engineer in Tong Hsing Electronic Ind., Ltd

Yueh-Tsung Chung

  • Tong Hsing Electronic Ind., Lt

Ting-Chun Wang

  • Google Taiwan Engineering Limited Intern
  • HTC Corporation Intern



Drisya Babu Asari Leju

  • Associative Software Engineer (IVR/ASR Engineer) at Pivot Systems Pvt.Ltd, Technopark, Trivandrum

Year 2019

Chi-Hung Tian

  • Exchange student at Osaka Prefecture University for studying Computer Science

Chao-Yu Siao

  • Coding 365 Teaching Assistant

Jun-Jia Su

  • Arima Communications Corp Intern
  • AU Optronics Corp Intern

Yung-Chin Hsu

  • Google Taiwan Engineering Limited Intern
  • HTC Corporation Intern

Wei-Chuan Chiang

  • Institute for Information Industry Intern

Chun-Hsien Yu

  • PROV Technology Corporation, software engineer
  • shuttle computer, Android BSP engineer



The table is created by Google Scholar on August 20, 2020. For latest information, please visit My Google Scholar Profile.

Title Cited by Year
AnyCharge: An IoT-Based Wireless Charging Service for the Public
KT Lai, FC Cheng, SCT Chou, YC Chang, GW Wu, JC Tsai
IEEE Internet of Things Journal 6 (6), 10888-10901, 2019
An Efficient and Resource-Aware Hashtag Recommendation Using Deep Neural Networks
D Kao, KT Lai, MS Chen
Pacific-Asia Conference on Knowledge Discovery and Data Mining, 150-162, 2019
VIVID: Virtual Environment for Visual Deep Learning
KT Lai, CC Lin, CY Kang, ME Liao, MS Chen
2018 ACM Multimedia Conference on Multimedia Conference, 1356-1359, 2018
1 2018
The privileged sensing framework: A principled approach to improved human-autonomy integration
AR Marathe, JS Metcalfe, BJ Lance, JR Lukos, D Jangraw, KT Lai, ...
Theoretical Issues in Ergonomics Science 19 (3), 283-320, 2018
12 2018
Mining the Networks of Telecommunication Fraud Groups using Social Network Analysis
YC Chang, KT Lai, SCT Chou, MS Chen
Advances in Social Networks Analysis and Mining (ASONAM), 2017
3 2017
Learning sample specific weights for late fusion
KT Lai, D Liu, SF Chang, MS Chen
IEEE Transactions on Image Processing 24 (9), 2772-2783, 2015
17 2015
Recognizing complex events in videos by learning key static-dynamic evidences
KT Lai, D Liu, MS Chen, SF Chang
European Conference on Computer Vision, 675-688, 2014
43 2014
Video Event Detection by Inferring Temporal Instance Labels
KT Lai, XY Felix, MS Chen, SF Chang
Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, 2014
117 2014
Sample-specific late fusion for visual category recognition
D Liu, KT Lai, G Ye, MS Chen, SF Chang
Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, 803-810, 2013
59 2013
Human action recognition using histogram of oriented gradient of motion history image
CP Huang, CH Hsieh, KT Lai, WY Huang
Instrumentation, Measurement, Computer, Communication and Control, 2011 …, 2011
45 2011
Orientation histogram of SIFT displacement for recognizing actions in broadcast videos
KT Lai, MS Chen, CH Hsieh, MF Lai
Visual Information Processing (EUVIP), 2011 3rd European Workshop on, 286-291, 2011
3 2011
Human action recognition using key points displacement
KT Lai, CH Hsieh, MF Lai, MS Chen
International Conference on Image and Signal Processing, 439-447, 2010
9 2010
Player detection and tracking in broadcast tennis video
YC Jiang, KT Lai, CH Hsieh, MF Lai
Pacific-Rim Symposium on Image and Video Technology, 759-770, 2009
15 2009

Contact Us

Office Address

Complex Building (綜科館), Room 406-1. No. 1, Sec. 3, Zhongxiao E. Rd., Taipei City, 10643, Taiwan (臺北科技大學)

Phone Number

(+886-2) 2771-2171 Ext. 2275