1 code implementation • CVPR 2023 • Sungwoong Kim, DaeJin Jo, Donghoon Lee, Jongmin Kim
Particularly, MAGVLT achieves competitive results on both zero-shot image-to-text and text-to-image generation tasks from MS-COCO by one moderate-sized model (fewer than 500M parameters) even without the use of monomodal data and networks.
2 code implementations • 26 Jan 2023 • Donghoon Lee, Ellen Yorke, Masoud Zarepisheh, Saad Nadeem, Yu-Chi Hu
The predicted respiratory patterns, represented by time-varying displacement vector fields (DVFs) at different breathing phases, are modulated through auxiliary inputs of 1D breathing traces so that a larger amplitude in the trace results in more significant predicted deformation.
1 code implementation • 11 Oct 2022 • DaeJin Jo, Sungwoong Kim, Daniel Wontae Nam, Taehwan Kwon, Seungeun Rho, Jongmin Kim, Donghoon Lee
In order to resolve these issues, in this paper, we propose a learnable hash-based episodic count, which we name LECO, that efficiently performs as a task-specific intrinsic reward in hard exploration problems.
no code implementations • 16 Aug 2022 • Gabriele Pozzato, Aki Takahashi, Xueyan Li, Donghoon Lee, Johan Ko, Simona Onori
In this paper, a core-shell enhanced single particle model for iron-phosphate battery cells is formulated, implemented, and verified.
no code implementations • 20 May 2022 • Aki Takahashi, Gabriele Pozzato, Anirudh Allam, Vahid Azimi, Xueyan Li, Donghoon Lee, Johan Ko, Simona Onori
In this paper, a novel electrochemical model for LiFePO$_4$ battery cells that accounts for the positive particle lithium intercalation and deintercalation dynamics is proposed.
1 code implementation • 22 Mar 2022 • Eric Hambro, Sharada Mohanty, Dmitrii Babaev, Minwoo Byeon, Dipam Chakraborty, Edward Grefenstette, Minqi Jiang, DaeJin Jo, Anssi Kanervisto, Jongmin Kim, Sungwoong Kim, Robert Kirk, Vitaly Kurin, Heinrich Küttler, Taehwon Kwon, Donghoon Lee, Vegard Mella, Nantas Nardelli, Ivan Nazarov, Nikita Ovsov, Jack Parker-Holder, Roberta Raileanu, Karolis Ramanauskas, Tim Rocktäschel, Danielle Rothermel, Mikayel Samvelyan, Dmitry Sorokin, Maciej Sypetkowski, Michał Sypetkowski
In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge.
1 code implementation • ICML Workshop AutoML 2021 • Chiheon Kim, Saehoon Kim, Jongmin Kim, Donghoon Lee, Sungwoong Kim
Large-batch training has been essential in leveraging large-scale datasets and models in deep learning.
no code implementations • 16 Jun 2021 • Donghoon Lee, Sadegh R Alam, Jue Jiang, Pengpeng Zhang, Saad Nadeem, Yu-Chi Hu
Purpose: Radiotherapy presents unique challenges and clinical requirements for longitudinal tumor and organ-at-risk (OAR) prediction during treatment.
no code implementations • ICCV 2021 • Donghoon Lee, Onur C. Hamsici, Steven Feng, Prachee Sharma, Thorsten Gernoth
The point cloud is partial as it is obtained by a depth sensor capturing only the visible part of the object from a certain viewpoint.
no code implementations • CVPR 2020 • Donghoon Lee, Hyunsin Park, Trung Pham, Chang D. Yoo
This paper considers an influence function that predicts how generalization performance, in terms of validation loss, is affected by a particular augmented training sample.
no code implementations • 18 May 2020 • Donghoon Lee
Entropy augmented to reward is known to soften the greedy argmax policy to softmax policy.
no code implementations • 5 Sep 2019 • Donghoon Lee, Georgios B. Giannakis
Radio tomographic imaging (RTI) is an emerging technology for localization of physical objects in a geographical area covered by wireless networks.
no code implementations • ICLR 2019 • Donghoon Lee, Chang D. Yoo
The differentiable augmentation model and reformulation of the influence function allow the parameters of the augmented model to be directly updated by backpropagation to minimize the validation loss.
no code implementations • CVPR 2019 • Donghoon Lee, Tomas Pfister, Ming-Hsuan Yang
To synthesize a realistic video, the network renders each frame based on the current input and previous frames.
2 code implementations • NeurIPS 2018 • Donghoon Lee, Sifei Liu, Jinwei Gu, Ming-Yu Liu, Ming-Hsuan Yang, Jan Kautz
Learning to insert an object instance into an image in a semantically coherent manner is a challenging and interesting problem.
1 code implementation • 28 May 2018 • Nuri Kim, Donghoon Lee, Songhwai Oh
Recent object detectors find instances while categorizing candidate regions.
no code implementations • 6 Apr 2018 • Donghoon Lee, Dimitris Berberidis, Georgios B. Giannakis
Key to success of RTI is to model accurately the shadowing effects as the bi-dimensional integral of the SLF scaled by a weight function, which is estimated using regularized regression.
Signal Processing Applications
no code implementations • 12 Jan 2018 • Donghoon Lee, Ming-Hsuan Yang, Songhwai Oh
Single image reflection separation is an ill-posed problem since two scenes, a transmitted scene and a reflected scene, need to be inferred from a single observation.
1 code implementation • ECCV 2018 • Donghoon Lee, Sangdoo Yun, Sungjoon Choi, Hwiyeon Yoo, Ming-Hsuan Yang, Songhwai Oh
We introduce a new problem of generating an image based on a small number of key local patches without any geometric prior.
no code implementations • ICCV 2015 • Donghoon Lee, Ming-Hsuan Yang, Songhwai Oh
In this paper, we consider the problem of estimating the gaze direction of a person from a low-resolution image.
no code implementations • CVPR 2015 • Donghoon Lee, Hyunsin Park, Chang D. Yoo
Without increasing prediction time, the prediction of cGPRT can be performed in the same framework as the cascade regression trees (CRT) but with better generalization.