LPCVC  2021

2021 LPCVC Overview

Since 2015, the IEEE Low Power Computer Vision Challenges have attracted top researchers worldwide showing their solutions that can achieve high accuracy with low energy consumption.

The 2021 Low-Power Computer Vision Challenge (2021 LPCVC) will be hosted online and features 2 tracks sponsored by Facebook and Xilinx. The challenge will be open for submission from 2021/08/01-2021/08/31. Winners will present their solutions during the ICCV workshop in October 2021. More details are posted below. Please join the online discussion forum lpcvc.slack.com.

*The participant agreement for the LPCVC 2021 contest can be found here.


2021 LPCVC Winners Announcement

The 2021 IEEE Low-Power Computer Vision Challenge (LPCVC) concluded successfully on 2021/08/31, after a month of competition; 53 teams submitted 366 solutions to the two tracks: (1) tracking moving objects in video and (2) FPGA object detection. This challenge is sponsored by Facebook-PyTorch, Xilinx, and the National Science Foundation (CNS-1925713).

The winners of the video track are:

  1. First Award: The VITA team from University of Texas at Austin, Texas A&M University, and Wormpex AI Research. The team members are Zhenyu Wu, Hao-Yu Miao, Xin Hu, Pengcheng Pi, Siqi Fan, Taiyu Long, Zhenyu Hu, Yi Wu, Zhou Ren, Zhangyang Wang, and Gang Hua. The first four members have equal contributions.
  2. Second Award: The baseSlim team from Meituan. The team members are Yang Yong, Junjie Liu, Ranran Huang, Jiancheng Cai, Jinjin Zhang, Shenqi Lai, Xin Ma, Xiaobin Wei, Huanyu Wang, Zhenhua Chai, Xinmin Liu, Xiaolin Wei.
  3. Third Award: The team withdrew.
  4. Honorable Mentions: The spring team from Zhejiang University, University of Sydney, Beihang University. The team members are Yucheng Wang, Weitao Feng, Jiahao Hu, Yongqiang Yao, Ruihao Gong, Shuo Wu, Qi Zhang, Yusong Wang, Yan Ren, Liang Liu, Yanfei Wang, Fengwei Yu.

The winners of the FPGA object detection track are:

  1. The SPRING team from SenseTime, Beihang University, Peking University. The members are Jiahao Hu, Pu Li, Yongqiang Yao, Ruihao Gong, Shuo Wu, Yucheng Wang, Liang Liu, Yusong Wang, Fengwei Yu. The first four members have equal contributions.
  2. The MIT HANLAB team from Massachusetts Institute of Technology. The members are Zhekai Zhang, Han Cai, and Song Han.
  3. The NYCU ADAR LAB team from National Yang Ming Chiao Tung University and Academia Sinica. The members are Chien-Yao Wang, Yu-Hsiang Huang, Jyun-Hua Chen, Ching-Yun Kao, and Juinn-Dar Huang.

ICCV workshop (Low-Power Computer Vision) on October 11:

Track Winners Presentation:


Tracks

How to participate: Login on this website to participate in the following trakcs. A registered account is free to participate any tracks. Detailed instruction can be found on the corresponding information page.

Online Track - UAV Video

Track multiple moving objects in video captured by an unmanned aerial vehicle (UAV).

More Info

Online Track - Xilinx Sponsored Track

More Information soon to come.

More Info

Sponsors


Organizers

NameRole and OrganizationEmail
Mohamed M. Sabry AlyIEEE Council on Design Automation, Nanyang Technolgical Universitymsabry@ntu.edu.sg
Alexander C BergUniversity of North Carolinaaberg@cs.unc.edu
Ming-Ching ChangUniversity at Albany - SUNYmchang2@albany.edu
Shu-Ching ChenFlorida International Universitychens@cs.fiu.edu
Yen-Kuang ChenIEEE Circuits and Systems Society, Alibabay.k.chen@ieee.org
Yiran ChenACM Speical Interest Group on Design Automation, Duke Universityyiran.chen@duke.edu
Chia-Ming ChengMediatekcm.cheng@mediatek.com
Bohyung HanSeoul National Universitybhhan@snu.ac.kr
Xiao Hulpcv.ai submission manager, Purdue studenthu440@purdue.edu
Anirudh Vegesanalpcv.ai submission manager, Purdue studentavegesan@purdue.edu
Christian KellerFacebookchk@fb.com
Mark LiaoAcademia Sinica, Taiwanliao@iis.sinica.edu.tw
Tsung-Han LinMediatekTsung-Han.Lin@mediatek.com
(contact) Yung-Hsiang LuChair, Purdue University Professoryunglu@purdue.edu
An LuoAmazonanluo@amazon.com
Terence MartinezIEEE Future Directions t.c.martinez@ieee.org
Ryan McBeeSouthwest Research Instituteryan.mcbee@swri.org
Andreas MoshovosUniversity of Toronto/Vector Institutemoshovos@ece.utoronto.ca
Naveen PurushothamXilinx Inc.npurusho@xilinx.com
Tim RogersPurduetimrogers@purdue.edu
Mei-Ling ShyuIEEE Multimedia Technical Committee, Miami Universityshyu@miami.edu
Ashish SirasaoXilinx Inc.asirasa@xilinx.com
Joseph SpisakFacebookjspisak@fb.com
George K. ThiruvathukalLoyola University Chiicagogkt@cs.luc.edu
Yueh-Hua WuAcademia Sinica, Taiwankriswu@iis.sinica.edu.tw
Junsong YuanUniversity at Buffalojsyuan@buffalo.edu
Carole-Jean WuFacebookcarolejeanwu@fb.com