no code implementations • 20 Jun 2023 • Daniel Rho, Taesoo Kim, Sooill Park, JaeHyun Park, JaeHan Park
In this work, we propose a new perspective to understand the role of margins based on gradient analysis.
no code implementations • 14 Jun 2023 • JaeHyun Park, Jaegyun Im, Sanha Hwang, Mintaek Lim, Sabina Ualibekova, Sejin Kim, Sundong Kim
In the pursuit of artificial general intelligence (AGI), we tackle Abstraction and Reasoning Corpus (ARC) tasks using a novel two-pronged approach.
no code implementations • 29 Nov 2022 • Sung Joon Maeng, JaeHyun Park, Ismail Guvenc
Unmanned aerial vehicles (UAVs) are expected to be used extensively in the future for various applications, either as user equipment (UEs) connected to a cellular wireless network, or as an infrastructure extension of an existing wireless network to serve other UEs.
no code implementations • 4 Oct 2022 • JaeHyun Park, Subin Lee, Eon Kim, Byeongjun Moon, Dabeen Yu, Yeonseung Yu, Junghwan Kim
Feature fusion modules from encoder and self-attention module have been adopted in semantic segmentation.
no code implementations • 21 Feb 2022 • JaeHyun Park, Chansoo Kim, Kichun Jo
As the Light Detection And Range (LiDAR) sensor is widely used in the autonomous car, fast semantic segmentation of LiDAR point cloud, which is the point-wise classification of the point cloud within the sensor framerate, has attracted attention in recognition of the driving environment.
no code implementations • 26 Feb 2021 • Yigit Tuncel, Ganapati Bhat, JaeHyun Park, Umit Ogras
The proposed framework uses an efficient iterative algorithm to compute initial energy allocations at the beginning of a day.