中央研究院 資訊科學研究所

活動訊息

友善列印

列印可使用瀏覽器提供的(Ctrl+P)功能

[新聘演講]Real-Time Object Detection Methods

:::

[新聘演講]Real-Time Object Detection Methods

  • 講者王建堯 博士 (中央研究院資訊科學研究所)
    邀請人:陳孟彰
  • 時間2022-03-28 (Mon.) 10:00 – 12:00
  • 地點實體: 資訊所新館106演講廳;視訊連結將於演講前提供
線上串流
會議鏈結:
https://asmeet.webex.com/asmeet/j.php?MTID=m9c96591d3191906063cc57ec61b9ae47
 
會議號:
25105922120
 
會議密碼:
fpDK3xxKR23
 
摘要

Object detection is one of the most important issues in computer vision, and it is a core technology in various computer vision-based systems. For example, face verification, autonomous driving, vehicle tracking, traffic analysis, and medical image analysis. Object detection systems can be more valuable when it applies to real-time application domain. This talk gives a brief introduction on real-time object detection methods for various devices. These methods include YOLOv4, Scaled-YOLOv4, and YOLOR.

BIO

Chien-Yao Wang received the Ph.D. degree in Computer Science and Information Engineering from National Central University, Zhongli, Taiwan, in 2017. He is currently a postdoctoral research fellow with the Institute of Information Science, Academia Sinica, Taiwan. His research interests include signal processing, deep learning, and machine learning. Currently, his research focuses on multi-task representation learning for multimodal signal. From 2020 to 2022, he releases several works on object detection and many computer vision tasks, including YOLOv4, Scaled-YOLOv4, and YOLOR. These works are the best real-time object detection methods in the world from 2020 until now.