Zobrazeno 1 - 10
of 1 688
pro vyhledávání: '"Kim, SooHyun"'
Autor:
Kim, Soohyun
This dissertation examines the challenges and opportunities of analyzing distinct sources of mental health data in the age of precision medicine and big data. The focus lies on two areas: leveraging real-time Ecological Momentary Assessment (EMA) dat
Autor:
Villa-Renteria, Ivan, Wang, Mason L., Shah, Zachary, Li, Zhe, Kim, Soohyun, Ramachandran, Neelesh, Pilanci, Mert
We present Subtractive Training, a simple and novel method for synthesizing individual musical instrument stems given other instruments as context. This method pairs a dataset of complete music mixes with 1) a variant of the dataset lacking a specifi
Externí odkaz:
http://arxiv.org/abs/2406.19328
We present a new multi-modal face image generation method that converts a text prompt and a visual input, such as a semantic mask or scribble map, into a photo-realistic face image. To do this, we combine the strengths of Generative Adversarial netwo
Externí odkaz:
http://arxiv.org/abs/2405.04356
Autor:
Kim, Soohyun, Kim, Junho, Kim, Taekyung, Heo, Hwan, Kim, Seungryong, Lee, Jiyoung, Kim, Jin-Hwa
In this paper, we tackle the challenging task of Panoramic Image-to-Image translation (Pano-I2I) for the first time. This task is difficult due to the geometric distortion of panoramic images and the lack of a panoramic image dataset with diverse con
Externí odkaz:
http://arxiv.org/abs/2304.04960
Autor:
Heo, Hwan, Kim, Taekyung, Lee, Jiyoung, Lee, Jaewon, Kim, Soohyun, Kim, Hyunwoo J., Kim, Jin-Hwa
Multi-resolution hash encoding has recently been proposed to reduce the computational cost of neural renderings, such as NeRF. This method requires accurate camera poses for the neural renderings of given scenes. However, contrary to previous methods
Externí odkaz:
http://arxiv.org/abs/2302.01571
Existing work in data fusion has covered identification of causal estimands when integrating data from heterogeneous sources. These results typically require additional assumptions to make valid estimation and inference. However, there is little lite
Externí odkaz:
http://arxiv.org/abs/2301.02904
Autor:
Park, Jihye, Kim, Sunwoo, Kim, Soohyun, Cho, Seokju, Yoo, Jaejun, Uh, Youngjung, Kim, Seungryong
Existing techniques for image-to-image translation commonly have suffered from two critical problems: heavy reliance on per-sample domain annotation and/or inability of handling multiple attributes per image. Recent truly-unsupervised methods adopt c
Externí odkaz:
http://arxiv.org/abs/2208.14889
Publikováno v:
In Journal of Hydrology: Regional Studies October 2024 55
We present a novel Transformer-based network architecture for instance-aware image-to-image translation, dubbed InstaFormer, to effectively integrate global- and instance-level information. By considering extracted content features from an image as t
Externí odkaz:
http://arxiv.org/abs/2203.16248
Autor:
Kim, Soohyun
This dissertation consists of three papers studying the relationship between paid leave policies and work and informal care outcomes among older workers. Paper one investigates whether different types of paid leave provided by employers are associate