We have one paper accepted to the 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022). The paper is “Multi-Source Domain Alignment for Robust Segmentation in Unknown Targets” by Pranjay Shyam, Kuk-Jin Yoon, and Kyung-Soo Kim. [Publication Link]
We have one paper accepted to IEEE Intelligent Vehicles Symposium 2022. The paper is “Infra Sim-to-Real : An efficient baseline and dataset for Infrastructure based Online Object Detection and Tracking using Domain Adaptation” by Pranjay Shyam, Sumit Mishra, Kuk-Jin Yoon, and Kyung-Soo Kim.
We won the 2nd place in PBVS Semi-Supervised Hyperspectral Object Detection Challenge(SSHODC) 2022. “Semi-Supervised Hyperspectral Object Detection Challenge Results – PBVS 2022” by Aneesh Rangnekar, Zack Mulhollan, Anthony Vodacek, Matthew Hoff man, Angel Sappa, Jun Yu, Liwen Zhang, Shenshen Du, Hao Chang, Keda Lu, Zhong Zhang, Fang Gao, Ye Yu, Feng Shuang, Lei Wang, Qiang Ling,…
We have five papers accepted to IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR) 2022. The papers are “SphereSR: 360° Image Super-Resolution with Arbitrary Projection via Continuous Spherical Image Representation” by Youngho Yoon, Inchul Chung, Lin Wang, and Kuk-Jin Yoon, “UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation” by Taeyeop Lee, Byeong-Uk Lee, Inkyu Shin, Jaesung…
The paper “BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-aided Adversarial Learning” by 오창균, 조원준, 박대희, 채유정, 윤국진 won the first best paper award at Domestic Workshop on 34th Image Processing and Image Understanding (IPIU 2022). The paper “Exploring Pixel-level Self-supervision for Weakly Supervised Semantic Segmentation” by 윤성훈, 권혁준, 정재석, 김현성, 김신정, 윤국진 won the…
We cover a variety of issues in the field of computer vision and machine learning. Our research can be applied to various systems and machines such as autonomous cars, drones, medical diagnoses systems, and any other AI systems. If you are interested in computer vision and machine learning, please feel free to contact us.
