Taeoh Kim

Research Engineer / Technical Lead. at, NAVER Cloud Corp.

As an engineer, I conduct research and development on technologies for video understanding and generation, and provide technical support for related services.

E-mail: taeoh.kim [at] navercorp.com

Google Scholar  /  Linkedin

profile photo

News!

[Nov 2024] (New!) I gave a presentation in DAN 24, NAVER Conference [Session] [Press]
[Sep 2024] One Paper is accepted to NeurIPS 2024 (Video Anomaly Detection).
[Jul 2024] One Paper is accepted to ECCV 2024 (Oral) (Video Action Detection).
[Jan 2024] I won the N Innovation Award 2023, R&D Track [About] [Post].
[Aug 2023] One Paper is accepted to International Journal of Computer Vision (Image Processing).
[Feb 2023] One Paper is accepted to CVPR 2023 (Video Action Localization).
[Jan 2023] One Paper is accepted to ICLR 2023 (Spotlight) (Video Understanding).
[Nov 2022] One Paper is accepted to AAAI 2023 (Oral) (Video Representation Learning).
[Apr 2022] One Paper is accepted to Pattern Recognition (Video Anomaly Detection).
[Dec 2021] One Paper is accepted to IEEE Transactions on Image Processing (Video Deblurring).
[Nov 2021] One Paper is accepted to IEEE Transactions on Image Processing (Image Compression).


Publications

mdvad Towards Multi-Domain Learning for Generalizable Video Anomaly Detection

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

NeurIPS, 2024
Paper / Project Page (Coming Soon)

cmatter 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 Presentation, 2.3% Acceptance Rate)
Paper / Project Page / Code

ijcv 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 (IJCV, IF 19.5), 2023
Paper

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

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

CVPR, 2023
Paper

dynaaug 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 Presentation, Notable Top 25%)
Paper / OpenReview

freqaug Frequency Selective Augmentation for Video Representation Learning

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

AAAI, 2023 (Oral Presentation)
Paper

flowano Unsupervised Video Anomaly Detection via Normalizing Flows with Implicit Latent Features

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

Pattern Recognition (PR, IF 8.0), 2022
Paper

geovd Geometry-Aware Deep Video Deblurring via Recurrent Feature Refinement

Taeoh Kim, Sangyoun Lee

IEEE Transactions on Image Processing (TIP, IF 10.6), 2022
Paper

acn Enhanced Standard Compatible Image Compression Framework based on Auxiliary Codec Networks

Hanbin Son, Taeoh Kim, Hyeongmin Lee, Sangyoun Lee

IEEE Transactions on Image Processing (TIP, IF 10.6), 2021
Paper

spn Block-Attentive Subpixel Prediction Networks for Computationally Efficient Image Restoration

Taeoh Kim, Chajin Shin, Sangjin Lee, Sangyoun Lee

IEEE Access (IF 3.367), 2021
Paper

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

Chajin Shin, Taeoh Kim, Sangjin Lee, Sangyoun Lee

ICIP, 2021
Paper / Code

aim AIM 2020 Challenge on Image Extreme Inpainting
2nd Place in the Image Inpainting Challenge Track 1: Classic Inpainting

Evangelos Ntavelis, AndrĀ“es Romero, Siavash Bigdeli, Radu Timofte, Zheng Hui, Xiumei Wang, Xinbo Gao, Chajin Shin, Taeoh Kim, Hanbin Son, Sangyoun Lee et al.

ECCV Workshops (Advances in Image Manipulation (AIM)), 2020
Paper

viprior Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition
4th Place in the VIPriors Action Recognition Challenge

Taeoh Kim*, Hyeongmin Lee*, MyeongAh Cho*, Ho Seong Lee, Dong Heon Cho, Sangyoun Lee (*Equal Contribution)

ECCV Workshops (1st Visual Inductive Priors (VIPriors) for Data-Efficient Deep Learning Workshop), 2020
Paper

spn 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 (IF 7.718), 2020
Paper

spn Extrapolative-Interpolative Cycle- Consistency Learning For Video Frame Extrapolation

Sangjin Lee, Hyeongmin Lee, Taeoh Kim, Sangyoun Lee

ICIP, 2020
Paper

spn 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

spn Sampling Operator to Learn the Scalable Correlation Filter for Visual Tracking

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

IEEE Access (IF 3.367), 2019
Paper

spn 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

spn 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

spn Collabonet: Collaboration of Generative Models by Unsupervised Classification

Hyeongmin Lee, Taeoh Kim, Eungyeol Song, Sangyoun Lee

ICIP, 2018
Paper


Source