no code implementations • 29 Nov 2023 • Seongho Keum, Sanghyun Kim, Soojeong Lee, Juho Lee
Due to the lack of patch-level labels, multiple instance learning (MIL) is a common practice for training a WSI classifier.
1 code implementation • 12 Jul 2023 • Sanghyun Kim, Seohyeon Jung, Balhae Kim, Moonseok Choi, Jinwoo Shin, Juho Lee
Large-scale image generation models, with impressive quality made possible by the vast amount of data available on the Internet, raise social concerns that these models may generate harmful or copyrighted content.
no code implementations • 6 May 2023 • Sanghyun Kim, Jiwon Seo
Consequently, when the testing dataset was collected at different locations from the training dataset, a classification accuracy of 64. 47% was obtained, which was slightly higher than the accuracy of the existing method using dual single-polarized antennas.
1 code implementation • CVPR 2023 • Sanghyun Kim, Deunsol Jung, Minsu Cho
Recent state-of-the-art methods for HOI detection typically build on transformer architectures with two decoder branches, one for human-object pair detection and the other for interaction classification.
Ranked #2 on Human-Object Interaction Detection on V-COCO
no code implementations • CVPR 2023 • Deunsol Jung, Sanghyun Kim, Won Hwa Kim, Minsu Cho
The edge selection module selects relevant object pairs, i. e., edges in the scene graph, which helps contextual reasoning, and the quad attention module then updates the edge features using both edge-to-node and edge-to-edge cross-attentions to capture contextual information between objects and object pairs.
no code implementations • 6 Apr 2022 • Sanghyun Kim, Jungyun Byun, Kwansik Park
In this study, we proposed a machine learning approach for global positioning system (GPS) multipath detection that uses dual antennas.
no code implementations • 21 Aug 2021 • Sanghyun Kim, Halim Lee, Kwansik Park
In this study, the global positioning system (GPS) multipath detection was performed based on the carrier-to-noise-density ratio, C/N0, measured through a dual-polarized antenna.
no code implementations • 13 Aug 2021 • Joon Hyo Rhee, Sanghyun Kim, Pyo-Woong Son, Jiwon Seo
Once its operational performance is determined to be satisfactory, South Korea plans to move to the second phase of the program, which is a nationwide eLoran system.
no code implementations • 24 Sep 2020 • Sanghyun Kim, Jongmin Park, Jae-Kwan Yun, Jiwon Seo
In this study, we applied reinforcement learning based on the proximal policy optimization algorithm to perform motion planning for an unmanned aerial vehicle (UAV) in an open space with static obstacles.