Guoyuan Presents Poster at ICCV 2023

At the ICCV2023 conference, Guoyuan An presented his paper, “Towards Content-based Pixel Retrieval in Revisited Oxford and Paris.” This research introduced the innovative concept of pixel retrieval, along with associated benchmark datasets.

Towards Content-based Pixel Retrieval in Revisited Oxford and Paris
Guoyuan An, Woo Jae Kim, Saelyne Yang, Rong Li, Yuchi Huo, and SungEui Yoon
TopInternational Conference on Computer Vision (ICCV), 2023

Xu Presents Workshop Poster at ICCV 2023

Xu Yin gave a presentation about his work at the ICCV2023 workshop (VIPriors). The paper is related to his journal paper titled “Contour-Aware Equipotential Learning for Semantic Segmentation“, published in TMM2022.

Contour-Aware Equipotential Learning for Semantic Segmentation
Xu Yin, Dongbo Min, Yuchi Huo, and Sung-Eui Yoon
IEEE Transactions on Multimedia (TMM), 2022

ICCV 2023 Conference

Prof. Yoon and his Ph.D. students — Jaeyoon Kim, Guoyuan An, and Xu Yin — attended the ICCV2023 conference, held in Paris, France from Oct. 2nd to 6th. At the conference, we had the pleasure of reconnecting with Yuchi Huo, an assistant professor at Zhejiang University and a former post-doctoral researcher at our lab.

Pictured, from left to right: Prof. Yoon, Prof. Huo, Xu Yin, Guoyuan An, Jaeyoon Kim

Prof. Yoon’s Oral Presentation at KCCV2023

Our professor, Sung-Eui Yoon, gave an oral presentation at the KCCV2023 conference held between Aug 7 and 9 in Seoul, Korea. In this talk, he introduced “Feature Separation and Recalibration for Adversarial Robustness” which was chosen as a highlight paper (acceptance ratio: 2.6%) at CVPR2023.

Feature Separation and Recalibration for Adversarial Robustness
Woo Jae Kim, Yoonki Cho, Junsik Jung, and Sung-Eui Yoon
TopIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Highlights paper
arXiv GitHub Slides Poster

2023 KAIST Annual R&D Report

Our paper titled “Confidence-Based Robot Navigation Under Sensor Occlusion with Deep Reinforcement Learning” was selected as one of the KAIST’s Research Highlights on the 2023 KAIST Annual R&D Report. This paper proposed a novel RL-based navigation method under sensor occlusion.

Confidence-Based Robot Navigation Under Sensor Occlusion with Deep Reinforcement Learning
Hyeongyeol Ryu, Minsung Yoon, Daehyung Park, and Sung-Eui Yoon
TopIEEE International Conference on Robotics and Automation (ICRA), 2022
Outstanding navigation paper finalist
Code (zip)

KCGS 2023 석사논문 최우수상

우리연구실 석사과정 한규범 군이 한국컴퓨터그래픽스학회 2023 (KCGS 2023)에서 석사논문 최우수상을 수상하였습니다. 본 논문은 국제학회 I3DG 2023에 accept된 논문으로 다시 한 번 우수성을 입증 받았습니다. 축하합니다!

Pixel-wise Guidance for Utilizing Auxiliary Features in Monte Carlo Denoising
Kyu Beom Han, Olivia G. Odenthal, Woo Jae Kim, and Sung-Eui Yoon
ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (I3DG) / Proceedings of the ACM on Computer Graphics and Interactive Techniques, 2023

Woo Jae Presents a Highlights Paper at CVPR 2023

Woo Jae Kim introduced his paper titled “Feature Separation and Recalibration for Adversarial Robustness” at CVPR 2023. Woo Jae’s work was chosen as one of the 235 Highlights papers with an acceptance ratio of 2.6%.

Keep up the good work Woo Jae!

Feature Separation and Recalibration for Adversarial Robustness
Woo Jae Kim, Yoonki Cho, Junsik Jung, and Sung-Eui Yoon
TopIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Highlights paper
arXiv GitHub Slides Poster

Outstanding Planning Paper Award at ICRA 2023

We are delighted to announce that our paper, entitled “Learning-based Initialization of Trajectory Optimization for Path-following Problems of Redundant Manipulators,” has been honored with the prestigious “Outstanding Planning Paper Award” at the IEEE International Conference on Robotics and Automation (ICRA 2023).
These awards recognize the exemplary contributions within each robotics field, as only 15 papers were selected among a competitive pool of 1341 accepted submissions.

We want to express our gratitude to the conference organizers and the entire research community for their support and recognition of our work.

KAIST Research News: https://researchnews.kaist.ac.kr/researchnews/html/news/?mode=V&mng_no=29730&skey=&sval=&list_s_date=&list_e_date=&GotoPage=1

Learning-based Initialization of Trajectory Optimization for Path-following Problems of Redundant Manipulators
Minsung Yoon, Mincheul Kang, Daehyung Park, and Sung-Eui Yoon
TopIEEE International Conference on Robotics and Automation (ICRA), 2023
Outstanding planning paper award

Minsung Yoon Presents Posters at ICRA 2023

On June 1st, Minsung Yoon presented posters for two robotics papers at ICRA 2023 on behalf of the co-authors. The first paper is titled “Learning-based Initialization of Trajectory Optimization for Path-following Problems of Redundant Manipulators“, and the second paper is titled “Towards Safe Remote Manipulation: User Command Adjustment based on Risk Prediction for Dynamic Obstacles“. Notably, the first paper received the Outstanding Planning Paper Award at ICRA 2023.

Learning-based Initialization of Trajectory Optimization for Path-following Problems of Redundant Manipulators
Minsung Yoon, Mincheul Kang, Daehyung Park, and Sung-Eui Yoon
TopIEEE International Conference on Robotics and Automation (ICRA), 2023
Outstanding planning paper award
Towards Safe Remote Manipulation: User Command Adjustment based on Risk Prediction for Dynamic Obstacles
Mincheul Kang, Minsung Yoon, and Sung-Eui Yoon
TopIEEE International Conference on Robotics and Automation (ICRA), 2023