CVPR-20 5편 논문 채택

KAIST AI대학원 소속 연구자들의 논문 5편이 CVPR-20 (the IEEE Conference on Computer Vision and Pattern Recognition) 학회에 채택되었습니다.
CVPR는 세계 최고의 컴퓨터 비전 학회 중의 하나로, 2020년 6월 16일부터 20일까지 미국 시애틀의 Washington State Convention Center에서 개최될 예정입니다.

채택된 논문 목록:

“Regularizing Class-wise Predictions via Self-knowledge Distillation”
by Sukmin Yun*, Jongjin Park* (KAIST AI), Kimin Lee, and Jinwoo Shin (KAIST AI)

“M2m: Imbalanced Classification via Major-to-minor Translation”
by Jaehyung Kim*, Jongheon Jeong*, and Jinwoo Shin (KAIST AI)

“Cars Can’t Fly Up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks”
by Sungha Choi, Joanne Kim, and Jaegul Choo (KAIST AI, as of 3/1/2020)

“Reference-based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence”
by Junsoo Lee, Eungyeup Kim, Yunsung Lee, Dongjun Kim, Jaehyuk Chang, and Jaegul Choo (KAIST AI, as of 3/1/2020)

“Exploring Unlabeled Faces for Novel Attribute Discovery”
by Hyojin Bahng, Sunghyo Chung, Seungjoo Yoo, and Jaegul Choo (KAIST AI, as of 3/1/2020)