Search Results for author: Jaesik Min

Found 4 papers, 3 papers with code

Sequential Deformation for Accurate Scene Text Detection

no code implementations ECCV 2020 Shanyu Xiao, Liangrui Peng, Ruijie Yan, Keyu An, Gang Yao, Jaesik Min

Scene text detection has been significantly advanced over recent years, especially after the emergence of deep neural network.

Scene Text Detection Text Detection

Character decomposition to resolve class imbalance problem in Hangul OCR

1 code implementation12 Aug 2022 Geonuk Kim, Jaemin Son, Kanghyu Lee, Jaesik Min

As the total number of the characters could overwhelm the capacity of a neural network, the existing OCR encoding methods pre-define a smaller set of characters that are frequently used.

Optical Character Recognition Optical Character Recognition (OCR)

Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning

1 code implementation ICCV 2021 Sungyong Baik, Janghoon Choi, Heewon Kim, Dohee Cho, Jaesik Min, Kyoung Mu Lee

The problem lies in that each application and task may require different auxiliary loss function, especially when tasks are diverse and distinct.

Few-Shot Learning

End-to-end Learning of Image based Lane-Change Decision

1 code implementation26 Jun 2017 Seong-Gyun Jeong, Jiwon Kim, Sujung Kim, Jaesik Min

We propose an image based end-to-end learning framework that helps lane-change decisions for human drivers and autonomous vehicles.

Autonomous Vehicles object-detection +1

Cannot find the paper you are looking for? You can Submit a new open access paper.