Výsledky vyhledávání - "Park, SeongHyun"

Report

Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers

Autor: Seong, Kiyoung, Park, Seonghyun, Kim, Seonghwan, Kim, Woo Youn, Ahn, Sungsoo

Understanding transition pathways between meta-stable states in molecular systems is crucial to advance material design and drug discovery. However, unbiased molecular dynamics simulations are computationally infeasible due to the high energy barrier

Externí odkaz: http://arxiv.org/abs/2405.19961

Zobrazit plný text záznamu

Report

Non-backtracking Graph Neural Networks

Autor: Park, Seonghyun, Ryu, Narae, Kim, Gahee, Woo, Dongyeop, Yun, Se-Young, Ahn, Sungsoo

The celebrated message-passing updates for graph neural networks allow representing large-scale graphs with local and computationally tractable updates. However, the updates suffer from backtracking, i.e., a message flowing through the same edge twic

Externí odkaz: http://arxiv.org/abs/2310.07430

Zobrazit plný text záznamu

Report

Diffusion Probabilistic Models for Structured Node Classification

Autor: Jang, Hyosoon, Park, Seonghyun, Mo, Sangwoo, Ahn, Sungsoo

This paper studies structured node classification on graphs, where the predictions should consider dependencies between the node labels. In particular, we focus on solving the problem for partially labeled graphs where it is essential to incorporate

Externí odkaz: http://arxiv.org/abs/2302.10506

Zobrazit plný text záznamu

Report

NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results

Autor: Pérez-Pellitero, Eduardo, Catley-Chandar, Sibi, Shaw, Richard, Leonardis, Aleš, Timofte, Radu, Zhang, Zexin, Liu, Cen, Peng, Yunbo, Lin, Yue, Yu, Gaocheng, Zhang, Jin, Ma, Zhe, Wang, Hongbin, Chen, Xiangyu, Wang, Xintao, Wu, Haiwei, Liu, Lin, Dong, Chao, Zhou, Jiantao, Yan, Qingsen, Zhang, Song, Chen, Weiye, Liu, Yuhang, Zhang, Zhen, Zhang, Yanning, Shi, Javen Qinfeng, Gong, Dong, Zhu, Dan, Sun, Mengdi, Chen, Guannan, Hu, Yang, Li, Haowei, Zou, Baozhu, Liu, Zhen, Lin, Wenjie, Jiang, Ting, Jiang, Chengzhi, Li, Xinpeng, Han, Mingyan, Fan, Haoqiang, Sun, Jian, Liu, Shuaicheng, Marín-Vega, Juan, Sloth, Michael, Schneider-Kamp, Peter, Röttger, Richard, Li, Chunyang, Bao, Long, He, Gang, Xu, Ziyao, Xu, Li, Zhan, Gen, Sun, Ming, Wen, Xing, Li, Junlin, Li, Jinjing, Li, Chenghua, Gang, Ruipeng, Li, Fangya, Liu, Chenming, Feng, Shuang, Lei, Fei, Liu, Rui, Ruan, Junxiang, Dai, Tianhong, Li, Wei, Lu, Zhan, Liu, Hengyan, Huang, Peian, Ren, Guangyu, Luo, Yonglin, Liu, Chang, Tu, Qiang, Ma, Sai, Cao, Yizhen, Tel, Steven, Heyrman, Barthelemy, Ginhac, Dominique, Lee, Chul, Kim, Gahyeon, Park, Seonghyun, Vien, An Gia, Mai, Truong Thanh Nhat, Yoon, Howoon, Vo, Tu, Holston, Alexander, Zaheer, Sheir, Park, Chan Y.

Publikováno v: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022

This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022. This manuscript focuses on the competition set

Externí odkaz: http://arxiv.org/abs/2205.12633

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání