no code implementations • 15 Jun 2023 • Federica Spinola, Philipp Benz, Minhyeong Yu, Tae-hoon Kim
In real-world scenarios we often need to perform multiple tasks simultaneously.
no code implementations • 19 Aug 2022 • Jinwoo Hwang, Philipp Benz, Tae-hoon Kim
Improving multi-view aggregation is integral for multi-view pedestrian detection, which aims to obtain a bird's-eye-view pedestrian occupancy map from images captured through a set of calibrated cameras.
no code implementations • 4 Aug 2022 • Jonghu Jeong, Minyong Cho, Philipp Benz, Jinwoo Hwang, Jeewook Kim, Seungkwan Lee, Tae-hoon Kim
We further conduct a user study to qualitatively assess our defense of the reconstruction attack.
no code implementations • 14 Dec 2021 • Tobiloba Adejumo, Tae-hoon Kim, David Le, Taeyoon Son, Guangying Ma, Xincheng Yao
Uniform lumen intensity was observed in both small and large arteries.
1 code implementation • 5 Mar 2020 • Hyeon Cho, Tae-hoon Kim, Hyung Jin Chang, Wonjun Hwang
We propose a self-supervised visual learning method by predicting the variable playback speeds of a video.
no code implementations • 1 Jan 2019 • Tae-hoon Kim, Dongmin Kang, Kari Pulli, Jonghyun Choi
High-performance visual recognition systems generally require a large collection of labeled images to train.
1 code implementation • 6 Dec 2018 • Karl Cobbe, Oleg Klimov, Chris Hesse, Tae-hoon Kim, John Schulman
In this paper, we investigate the problem of overfitting in deep reinforcement learning.
1 code implementation • CVPR 2019 • Hyeonwoo Noh, Tae-hoon Kim, Jonghwan Mun, Bohyung Han
Specifically, we employ linguistic knowledge sources such as structured lexical database (e. g. WordNet) and visual descriptions for unsupervised task discovery, and transfer a learned task conditional visual classifier as an answering unit in a visual question answering model.
4 code implementations • 22 May 2018 • Sungheon Park, Tae-hoon Kim, Kyogu Lee, Nojun Kwak
In this paper, we propose a simple yet effective method for multiple music source separation using convolutional neural networks.
Sound Audio and Speech Processing
no code implementations • 3 Jan 2018 • Tae-hoon Kim, Jonghyun Choi
We propose to learn a curriculum or a syllabus for supervised learning and deep reinforcement learning with deep neural networks by an attachable deep neural network, called ScreenerNet.