J
Junhyun Lee
Researcher at Korea University
Publications - 16
Citations - 1219
Junhyun Lee is an academic researcher from Korea University. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 7, co-authored 13 publications receiving 495 citations.
Papers
More filters
Proceedings Article
Self-attention graph pooling
TL;DR: Li et al. as discussed by the authors proposed a graph pooling method based on self-attention to consider both node features and graph topology, which achieved superior graph classification performance on the benchmark datasets using a reasonable number of parameters.
Proceedings ArticleDOI
HOTR: End-to-End Human-Object Interaction Detection with Transformers
TL;DR: Zhang et al. as mentioned in this paper presented a novel framework, referred by HOTR, which directly predicts a set of human, object, interaction triplets from an image based on a transformer encoder-decoder architecture.
Book ChapterDOI
The Eighth Visual Object Tracking VOT2020 Challenge Results
Matej Kristan,Ales Leonardis,Jiří Matas,Michael Felsberg,Roman Pflugfelder,Roman Pflugfelder,Joni-Kristian Kamarainen,Martin Danelljan,Luka Čehovin Zajc,Alan Lukežič,Ondrej Drbohlav,Linbo He,Yushan Zhang,Yushan Zhang,Song Yan,Jinyu Yang,Gustavo Fernandez,Alexander G. Hauptmann,Alireza Memarmoghadam,Alvaro Garcia-Martin,Andreas Robinson,Anton Varfolomieiev,Awet Haileslassie Gebrehiwot,Bedirhan Uzun,Bin Yan,Bing Li,Chen Qian,Chi-Yi Tsai,Christian Micheloni,Dong Wang,Fei Wang,Fei Xie,Felix Järemo Lawin,Fredrik K. Gustafsson,Gian Luca Foresti,Goutam Bhat,Guangqi Chen,Haibin Ling,Haitao Zhang,Hakan Cevikalp,Haojie Zhao,Haoran Bai,Hari Chandana Kuchibhotla,Hasan Saribas,Heng Fan,Hossein Ghanei-Yakhdan,Houqiang Li,Houwen Peng,Huchuan Lu,Hui Li,Javad Khaghani,Jesús Bescós,Jianhua Li,Jianlong Fu,Jiaqian Yu,Jingtao Xu,Josef Kittler,Jun Yin,Junhyun Lee,Kaicheng Yu,Kaiwen Liu,Kang Yang,Kenan Dai,Li Cheng,Li Zhang,Lijun Wang,Linyuan Wang,Luc Van Gool,Luca Bertinetto,Matteo Dunnhofer,Miao Cheng,Mohana Murali Dasari,Ning Wang,Pengyu Zhang,Philip H. S. Torr,Qiang Wang,Radu Timofte,Rama Krishna Sai Subrahmanyam Gorthi,Seokeon Choi,Seyed Mojtaba Marvasti-Zadeh,Shaochuan Zhao,Shohreh Kasaei,Shoumeng Qiu,Shuhao Chen,Thomas B. Schön,Tianyang Xu,Wei Lu,Weiming Hu,Wengang Zhou,Xi Qiu,Xiao Ke,Xiaojun Wu,Xiaolin Zhang,Xiaoyun Yang,Xue-Feng Zhu,Yingjie Jiang,Yingming Wang,Yiwei Chen,Yu Ye,Yuezhou Li,Yuncon Yao,Yunsung Lee,Yuzhang Gu,Zezhou Wang,Zhangyong Tang,Zhen-Hua Feng,Zhijun Mai,Zhipeng Zhang,Zhirong Wu,Ziang Ma +109 more
TL;DR: A significant novelty is introduction of a new VOT short-term tracking evaluation methodology, and introduction of segmentation ground truth in the VOT-ST2020 challenge – bounding boxes will no longer be used in theVDT challenges.
Journal ArticleDOI
Detection of masses in mammograms using a one-stage object detector based on a deep convolutional neural network.
Hwejin Jung,Bumsoo Kim,Inyeop Lee,Minhwan Yoo,Junhyun Lee,Soo Youn Ham,Okhee Woo,Jaewoo Kang +7 more
TL;DR: This work proposes a mass detection model based on RetinaNet that achieves comparable or better performance than more complex state-of-the-art models including the two-stage object detector and makes the model’s weights pre-trained on both GURO and INbreast publicly available.
Posted Content
Self-Attention Graph Pooling
TL;DR: This paper proposes a graph pooling method based on self-attention using graph convolution, which achieves superior graph classification performance on the benchmark datasets using a reasonable number of parameters.