activity
20192021
most citedLearning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition

3 citations · 5 across the 3 of their papers we have counts for

collaborators

7 papers

cs.CV2021

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

Chajin Shin, Taeoh Kim, Sangjin Lee +1

Deep learning-based image inpainting algorithms have shown great performance via powerful learned prior from the numerous external natural images. However, they show unpleasant res…

cs.CV20202 cited

Smoother Network Tuning and Interpolation for Continuous-level Image Processing

Hyeongmin Lee, Taeoh Kim, Hanbin Son +3

In Convolutional Neural Network (CNN) based image processing, most studies propose networks that are optimized to single-level (or single-objective); thus, they underperform on oth…

cs.CV20203 cited

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

Taeoh Kim, Hyeongmin Lee, MyeongAh Cho +3

Deep-Learning-based video recognition has shown promising improvements along with the development of large-scale datasets and spatiotemporal network architectures. In image recogni…

cs.CV2020

Extrapolative-Interpolative Cycle-Consistency Learning for Video Frame Extrapolation

Sangjin Lee, Hyeongmin Lee, Taeoh Kim +1

Video frame extrapolation is a task to predict future frames when the past frames are given. Unlike previous studies that usually have been focused on the design of modules or cons…

cs.CV2020

Regularized Adaptation for Stable and Efficient Continuous-Level Learning on Image Processing Networks

Hyeongmin Lee, Taeoh Kim, Hanbin Son +3

In Convolutional Neural Network (CNN) based image processing, most of the studies propose networks that are optimized for a single-level (or a single-objective); thus, they underpe…

cs.CV2020

Relational Deep Feature Learning for Heterogeneous Face Recognition

MyeongAh Cho, Taeoh Kim, Ig-Jae Kim +2

Heterogeneous Face Recognition (HFR) is a task that matches faces across two different domains such as visible light (VIS), near-infrared (NIR), or the sketch domain. Due to the la…