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" o f 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