no code implementations • NAACL (ACL) 2022 • Hwa-Yeon Kim, Jong-Hwan Kim, Jae-Min Kim
Autoregressive transformer (ART)-based grapheme-to-phoneme (G2P) models have been proposed for bi/multilingual text-to-speech systems.
no code implementations • 6 Sep 2023 • In-Ug Yoon, Tae-Min Choi, Sun-Kyung Lee, Young-Min Kim, Jong-Hwan Kim
To create these IOS classifiers, we encode a bias prompt into the classifiers using our specially designed module, which harnesses key-prompt pairs to pinpoint the IOS features of classes in each session.
1 code implementation • 4 Aug 2023 • Hwan-Soo Choi, Jongoh Jeong, Young Hoo Cho, Kuk-Jin Yoon, Jong-Hwan Kim
Sensor fusion approaches for intelligent self-driving agents remain key to driving scene understanding given visual global contexts acquired from input sensors.
no code implementations • 5 Jun 2023 • Hoyeon Lee, Hyun-Wook Yoon, Jong-Hwan Kim, Jae-Min Kim
We investigate the effectiveness of zero-shot and few-shot cross-lingual transfer for phrase break prediction using a pre-trained multilingual language model.
no code implementations • 26 May 2023 • In-Ug Yoon, Tae-Min Choi, Young-Min Kim, Jong-Hwan Kim
Few-shot class-incremental learning (FSCIL) presents the primary challenge of balancing underfitting to a new session's task and forgetting the tasks from previous sessions.
1 code implementation • 20 Feb 2023 • Tae-Min Choi, Jong-Hwan Kim
In this paper, we explore incremental few-shot object detection (iFSD), which incrementally learns novel classes using only a few examples without revisiting base classes.
1 code implementation • 21 Nov 2022 • Jongoh Jeong, Jong-Hwan Kim
Road scene understanding tasks have recently become crucial for self-driving vehicles.
no code implementations • 20 Sep 2022 • Curie Kim, Ue-Hwan Kim, Jong-Hwan Kim
There have been attempts to detect 3D objects by fusion of stereo camera images and LiDAR sensor data or using LiDAR for pre-training and only monocular images for testing, but there have been less attempts to use only monocular image sequences due to low accuracy.
no code implementations • 20 Sep 2022 • Curie Kim, Yewon Hwang, Jong-Hwan Kim
Reinforcement learning has shown an outstanding performance in the applications of games, particularly in Atari games as well as Go.
1 code implementation • CVPR 2022 • Jin-Man Park, Ue-Hwan Kim, Seon-Hoon Lee, Jong-Hwan Kim
Moreover, we design an evaluation protocol which reflects performance in real-world settings.
1 code implementation • 19 Apr 2021 • Ue-Hwan Kim, Yewon Hwang, Sun-Kyung Lee, Jong-Hwan Kim
Our dataset consists of five sub-datasets in two languages (Korean and English) and amounts to 209, 926 video instances from 122 participants.
no code implementations • 5 Apr 2021 • Dong He, Jie Cheng, Jong-Hwan Kim
This paper proposes the GSECnet - Ground Segmentation network for Edge Computing, an efficient ground segmentation framework of point clouds specifically designed to be deployable on a low-power edge computing unit.
1 code implementation • 23 Mar 2021 • Ue-Hwan Kim, Jong-Hwan Kim
Self-supervised learning of depth map prediction and motion estimation from monocular video sequences is of vital importance -- since it realizes a broad range of tasks in robotics and autonomous vehicles.
1 code implementation • 9 Mar 2021 • Jin-Man Park, Jae-Hyuk Jang, Sahng-Min Yoo, Sun-Kyung Lee, Ue-Hwan Kim, Jong-Hwan Kim
We present a challenging dataset, ChangeSim, aimed at online scene change detection (SCD) and more.
Ranked #2 on Scene Change Detection on ChangeSim
no code implementations • 20 Oct 2020 • Tae-Min Choi, Ji-Su Kang, Jong-Hwan Kim
In RDIS, we generate extra missing values by applying a random drop on the observed values in incomplete data.
1 code implementation • 19 Oct 2020 • Joonhyuk Kim, Sahng-Min Yoo, Gyeong-Moon Park, Jong-Hwan Kim
Our novel ETM framework contains Target-specific Memory (TM) for each target domain to alleviate catastrophic forgetting.
1 code implementation • 23 Sep 2020 • Ue-Hwan Kim, Dongho Ka, Hwasoo Yeo, Jong-Hwan Kim
To achieve the goal, pedestrian orientation recognition and prediction of pedestrian's crossing or not-crossing intention play a central role.
1 code implementation • 14 Nov 2019 • Ue-Hwan Kim, Se-Ho Kim, Jong-Hwan Kim
Intelligent agents need to understand the surrounding environment to provide meaningful services to or interact intelligently with humans.
no code implementations • 22 Aug 2019 • Yong-Ho Yoo, Ue-Hwan Kim, Jong-Hwan Kim
In this paper, we propose a convolutional recurrent reconstructive network (CRRN), which decomposes the anomaly patterns generated by the printer defects, from SPI data.
1 code implementation • 14 Aug 2019 • Ue-Hwan Kim, Jin-Man Park, Taek-Jin Song, Jong-Hwan Kim
We claim the following characteristics for a versatile environment model: accuracy, applicability, usability, and scalability.
1 code implementation • 31 Jul 2019 • Ue-Hwan Kim, Jong-Hwan Kim
The service provision with these two main components in a Smart Home environment requires: 1) learning and reasoning algorithms and 2) the integration of robot and IoT systems.
1 code implementation • 31 Jul 2019 • Ue-Hwan Kim, Sahng-Min Yoo, Jong-Hwan Kim
Current soft keyboards, however, increase the typo rate due to lack of tactile feedback and degrade the usability of mobile devices due to their large portion on screens.
no code implementations • ICLR 2018 • Yong-Ho Yoo, Kook Han, Sanghyun Cho, Kyoung-Chul Koh, Jong-Hwan Kim
We propose the dense RNN, which has the fully connections from each hidden state to multiple preceding hidden states of all layers directly.