Taeoh Kim

Bio

I am a Researcher & Engineer in NAVER Cloud Corporation.

Before joining NAVER, I obtained my Ph.D. in Electronic Engineering at Yonsei University under the supervision of Prof. Sangyoun Lee.

I conduct research and development on technologies for Video AI (Video Understanding and Generation), and provide technical support for related services.

Also, we are always looking for an Intern interested in Video-related research. Please feel free to contact me.

For more information on our research, please refer to Team Publications.

News

2025-06

Three papers are accepted to ICCV 2025.

2025-02

One paper is accepted to CVPR 2025.

2024-11

I gave a presentation in DAN 24, NAVER Conference. [Session] [Press]

2024-09

One paper is accepted to NeurIPS 2024.

2024-07

One paper is accepted to ECCV 2024 as an Oral Presentation.

2024-01

I won the N Innovation Award 2023. [About]

Publications

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs

Jeongseok Hyun, Minho Shim, Sukjun Hwang, Su Ho Han, Taeoh Kim, Inwoong Lee, Dongyoon Wee, Joon-Young Lee, Seon Joo Kim

ICCV 2025

Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval

Wonjun Moon, Cheol-Ho Cho, Woojin Jun, Minho Shim, Taeoh Kim, Inwoong Lee, Dongyoon Wee, Jae-Pil Heo

ICCV 2025

Paper

CoMoGaussian: Continuous Motion-Aware Gaussian Splatting from Motion-Blurred Images

Jungho Lee, DongHyeong Kim, Dogyoon Lee, Suhwan Cho, Minhyeok Lee, Wonjoon Lee, Taeoh Kim, Dongyoon Wee, Sangyoun Lee

ICCV 2025

Paper Project Code

CoCoGaussian: Leveraging Circle of Confusion for Gaussian Splatting from Defocused Images

Jungho Lee, Suhwan Cho, Taeoh Kim, Ho-Deok Jang, Minhyeok Lee, Geonho Cha, Dongyoon Wee, Dogyoon Lee, Sangyoun Lee

CVPR 2025

Paper Project Code

Towards Multi-Domain Learning for Generalizable Video Anomaly Detection

MyeongAh Cho, Taeoh Kim, Minho Shim, Dongyoon Wee, Sangyoun Lee

NeurIPS 2024

Paper

Classification Matters: Improving Video Action Detection with Class-Specific Attention

Jinsung Lee, Taeoh Kim, Inwoong Lee, Minho Shim, Dongyoon Wee, Minsu Cho, Suha Kwak

ECCV 2024 (Oral)

Paper Project Code

A Nonlinear, Regularized, and Data-independent Modulation for Continuously Interactive Image Processing Network

Hyeongmin Lee, Taeoh Kim, Hanbin Son, Sangwook Baek, Minsu Cheon, Sangyoun Lee

Internation Journal of Computer Vision 2023 (IJCV, IF 11.6)

Paper

Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection

Pilhyeon Lee, Taeoh Kim, Minho Shim, Dongyoon Wee, Hyeran Byun

CVPR 2023

Paper

Exploring Temporally Dynamic Data Augmentation for Video Recognition

Taeoh Kim, Jinhyung Kim, Minho Shim, Sangdoo Yun, Myunggu Kang, Dongyoon Wee, Sangyoun Lee

ICLR 2023 (Spotlight)

Paper

Frequency Selective Augmentation for Video Representation Learning

Jinhyung Kim, Taeoh Kim, Minho Shim, Dongyoon Han, Dongyoon Wee, Junmo Kim

AAAI 2023 (Oral)

Paper

Unsupervised Video Anomaly Detection via Normalizing Flows with Implicit Latent Features

MyeongAh Cho, Taeoh Kim, Woo Jin Kim, Suhwan Cho, Sangyoun Lee

Pattern Recognition 2022 (PR, IF 7.5)

Paper

Geometry-Aware Deep Video Deblurring via Recurrent Feature Refinement

Taeoh Kim, Sangyoun Lee

IEEE Transactions on Image Processing 2022 (IEEE TIP, IF 10.8)

Paper

Enhanced Standard Compatible Image Compression Framework based on Auxiliary Codec Networks

Hanbin Son, Taeoh Kim, Hyeongmin Lee, Sangyoun Lee

IEEE Transactions on Image Processing 2021 (IEEE TIP, IF 10.8)

Paper

Block-Attentive Subpixel Prediction Networks for Computationally Efficient Image Restoration

Taeoh Kim, Chajin Shin, Sangjin Lee, Sangyoun Lee

IEEE Access 2021 (IF 3.4)

Paper

Test-Time Adaptation for Out-of-distributed Image Inpainting

Chajin Shin, Taeoh Kim, Sangjin Lee, Sangyoun Lee

ICIP 2021

Paper Code

Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition

Taeoh Kim*, Hyeongmin Lee*, MyeongAh Cho*, Ho Seong Lee, Dong Heon Cho, Sangyoun Lee

ECCV Workshop 2020

Paper

Relational Deep Feature Learning for Heterogeneous Face Recognition

MyeongAh Cho, Taeoh Kim, Ig-Jae Kim, Kyungjae Lee, Sangyoun Lee

IEEE Transactions on Information Forensics and Security 2020 (IEEE TIFS, IF 6.3)

Paper

Extrapolative-Interpolative Cycle-Consistency Learning For Video Frame Extrapolation

Sangjin Lee, Hyeongmin Lee, Taeoh Kim, Sangyoun Lee

ICIP 2020

Paper

AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation

Hyeongmin Lee, Taeoh Kim, Tae-Young Chung, Daehyun Pak, Yuseok Ban, Sangyoun Lee

CVPR 2020

Paper Code

Sampling Operator to Learn the Scalable Correlation Filter for Visual Tracking

Minkyu Lee, Taeoh Kim, Yuseok Ban, Eungyeol Song, Sangyoun Lee

IEEE Access 2019 (IF 3.4)

Paper

SF-CNN: A Fast Compression Artifacts Removal via Spatial-To-Frequency Convolutional Neural Networks

Taeoh Kim, Hyeongmin Lee, Hanbin Son, Sangyoun Lee

ICIP 2019

Paper

NIR-to-VIS Face Recognition via Embedding Relations and Coordinates of the Pairwise Features

MyeongAh Cho, Tae-Young Chung, Taeoh Kim, Sangyoun Lee

ICB 2019

Paper

Collabonet: Collaboration of Generative Models by Unsupervised Classification

Hyeongmin Lee, Taeoh Kim, Eungyeol Song, Sangyoun Lee

ICIP 2018

Paper

Contacts

E-mail LinkedIn Google Scholar