Jinwoo Kim

Hi, I'm a Ph.D. student at Yonsei University advised by Prof. Seon Joo Kim. 

My research centers around compositional understanding of multi-modal world, focusing on visual inputs; towards interpretable, controllabel, and usable neural networks. Related keywords may contain object-centric learning, representation learning, tokenization, etc.

And also, I have studied diverse areas of computer vision, including computational color constancy, super resolution, video instance segmentation, and video event detection. 

Education


2021 - Present

2018 - 2021

2016 - 2018

Work Experience

Dec. 2021 - Jun. 2022

Mar. 2019 - Jul. 2019

 Publications

Accelerating Large Image Super-Resolution Networks with Pixel-Level Classification

Jinho Jeong, Jinwoo Kim, Younghyun Jo, Seon Joo Kim

Under Review


Towards Interpretable Controllability in Object-Centric Learning

Jinwoo Kim*, Jangyuk Choi*, Jeahyun Kang, Changyeon Lee, Ho-Jin Choi, Seon Joo Kim

(* equal contribution)

Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing

Dongyoung Kim, Jinwoo Kim, Junsang Yu, Seon Joo Kim

CVPR 2024

[paper]

Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning

Jinwoo Kim*, Janghyuk Choi*, Ho-Jin Choi, Seon Joo Kim

(* equal contribution)

CVPR 2023

[paper] [code] 

UBoCo: Unsupervised Boundary Contrastive Learning for Generic Event Boundary Detection

Hyolim Kang*, Jinwoo Kim*, Taehyun Kim, Seon Joo Kim 

(*equal contribution)

CVPR 2022

[paper]  [code]

Winning the CVPR’2021 Kinetics-GEBD Challenge: Contrastive Learning Approach

Hyolim Kang, Jinwoo Kim, Kyungmin Kim, Taehyun Kim, Seon Joo Kim

Large Scale Multi-Illuminant (LSMI) Dataset for Developing White Balance Algorithm under Mixed Illumination

Dongyoung Kim, Jinwoo Kim, Seonghyeon Nam, Dongwoo Lee, Yeonkyung Lee, Nahyup Kang, Hyong-Euk Lee, ByungIn Yoo, Jae-Joon Han, Seon Joo Kim

ICCV 2021

[paper]  [code]

Awards