Few-Shot Learning for vehicle footprint recognition - ICME 2021

Few-Shot Learning for Vehicle Footprint Recognition


An SEG DEEE team won 3rd Prize at the Grand Challenge "Few-Shot Learning for Vehicle Footprint Recognition" of IEEE (Institute of Electrical and Electronics Engineers) -  International Conference on Multimedia and Expo (ICME) 2021. 

ICME has been the flagship multimedia conference sponsored by four IEEE societies since 2000.This award is to recognize participants who can be either university students, graduated researchers, or from industries with great research ideas on the topic of “few-shot learning” (A branch from AI) to aid with the specific problem of tire pattern image classification and retrieval for the use of traffic accident management. Due to covid19, the grand challenge of ICME 2021 was held online.

The team, from SEG-DEEE and Electronics IG, developed an AI model and published it under the name “Pix2Pt Map for Transfer-Based Few-Shot Learning” which acts as a convenient tire classification model to aid in the identification of tire patterns for traffic accident management. With the successful application and proof of applicability, the team won third prize in the International Grand Challenge of ICME 2021.

EIG would like to congratulate the members who participated in this competition;
  • Sui JinZhou
  • Gabrielle Ee Song Xin
  • Lek Chen Ping
We would also like to like thank the following for their constant support in our participation for the competition;
  • Soh Lai Seng (Director - SEG)
  • Ramanathan Mohandas (AD - CI)
  • Eric Teo (PC - DEEE)
  • Kadir Yusop (CSM)
  • Banna Rao (CSM)
  • Caleb Tan (Electronics IG Advisor)
  • Hamid Saeedipour (PL)
  • Hong Ling Tim (PL)
  • Jeffery Koh
  • All other RP staff who rendered their support
Thank You!

 





Comments

Popular posts from this blog

Contactless Doorbell Workshop

Arduino Bluetooth Car Workshop

LTA SG Mobility Gallery Visit