Search Results for author: Seon Joo Kim

Found 39 papers, 19 papers with code

Cannot See the Forest for the Trees: Aggregating Multiple Viewpoints to Better Classify Objects in Videos

1 code implementation CVPR 2022 Sukjun Hwang, Miran Heo, Seoung Wug Oh, Seon Joo Kim

The set classifier is plug-and-playable to existing object trackers, and highly improves the performance of long-tailed object tracking.

Object Tracking

UBoCo: Unsupervised Boundary Contrastive Learning for Generic Event Boundary Detection

no code implementations CVPR 2022 Hyolim Kang, Jinwoo Kim, Taehyun Kim, Seon Joo Kim

Generic Event Boundary Detection (GEBD) is a newly suggested video understanding task that aims to find one level deeper semantic boundaries of events.

Boundary Detection Contrastive Learning +1

UBoCo : Unsupervised Boundary Contrastive Learning for Generic Event Boundary Detection

no code implementations29 Nov 2021 Hyolim Kang, Jinwoo Kim, Taehyun Kim, Seon Joo Kim

Generic Event Boundary Detection (GEBD) is a newly suggested video understanding task that aims to find one level deeper semantic boundaries of events.

Boundary Detection Contrastive Learning +1

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

1 code implementation22 Jun 2021 Hyolim Kang, Jinwoo Kim, KyungMin Kim, Taehyun Kim, Seon Joo Kim

Generic Event Boundary Detection (GEBD) is a newly introduced task that aims to detect "general" event boundaries that correspond to natural human perception.

Boundary Detection Contrastive Learning

Practical Single-Image Super-Resolution Using Look-Up Table

1 code implementation CVPR 2021 Younghyun Jo, Seon Joo Kim

We train a deep SR network with a small receptive field and transfer the output values of the learned deep model to the LUT.

Image Super-Resolution Single Image Super Resolution

Tackling the Ill-Posedness of Super-Resolution Through Adaptive Target Generation

1 code implementation CVPR 2021 Younghyun Jo, Seoung Wug Oh, Peter Vajda, Seon Joo Kim

By the one-to-many nature of the super-resolution (SR) problem, a single low-resolution (LR) image can be mapped to many high-resolution (HR) images.

Super-Resolution

Polygonal Point Set Tracking

no code implementations CVPR 2021 Gunhee Nam, Miran Heo, Seoung Wug Oh, Joon-Young Lee, Seon Joo Kim

Since the existing datasets are not suitable to validate our method, we build a new polygonal point set tracking dataset and demonstrate the superior performance of our method over the baselines and existing contour-based VOS methods.

Semantic Segmentation Video Object Segmentation +1

Temporally smooth online action detection using cycle-consistent future anticipation

no code implementations16 Apr 2021 Young Hwi Kim, Seonghyeon Nam, Seon Joo Kim

Many video understanding tasks work in the offline setting by assuming that the input video is given from the start to the end.

Autonomous Driving Online Action Detection +1

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

1 code implementation ICCV 2021 Dongyoung Kim, Jinwoo Kim, Seonghyeon Nam, Dongwoo Lee, Yeonkyung Lee, Nahyup Kang, Hyong-Euk Lee, ByungIn Yoo, Jae-Joon Han, Seon Joo Kim

Images in our dataset are mostly captured with illuminants existing in the scene, and the ground truth illumination is computed by taking the difference between the images with different illumination combination.

Single-shot Path Integrated Panoptic Segmentation

no code implementations3 Dec 2020 Sukjun Hwang, Seoung Wug Oh, Seon Joo Kim

Panoptic segmentation, which is a novel task of unifying instance segmentation and semantic segmentation, has attracted a lot of attention lately.

Instance Segmentation Panoptic Segmentation

Cross-Identity Motion Transfer for Arbitrary Objects through Pose-Attentive Video Reassembling

no code implementations ECCV 2020 Subin Jeon, Seonghyeon Nam, Seoung Wug Oh, Seon Joo Kim

To reduce the training-testing discrepancy of the self-supervised learning, a novel cross-identity training scheme is additionally introduced.

Self-Supervised Learning

Deep Space-Time Video Upsampling Networks

1 code implementation ECCV 2020 Jaeyeon Kang, Younghyun Jo, Seoung Wug Oh, Peter Vajda, Seon Joo Kim

Video super-resolution (VSR) and frame interpolation (FI) are traditional computer vision problems, and the performance have been improving by incorporating deep learning recently.

Computer Vision Motion Compensation +1

Unsupervised Keypoint Learning for Guiding Class-Conditional Video Prediction

1 code implementation NeurIPS 2019 Yunji Kim, Seonghyeon Nam, In Cho, Seon Joo Kim

To generate future frames, we first detect keypoints of a moving object and predict future motion as a sequence of keypoints.

Video Prediction

Copy-and-Paste Networks for Deep Video Inpainting

1 code implementation ICCV 2019 Sungho Lee, Seoung Wug Oh, DaeYeun Won, Seon Joo Kim

We propose a novel DNN-based framework called the Copy-and-Paste Networks for video inpainting that takes advantage of additional information in other frames of the video.

Image Inpainting Lane Detection +1

Onion-Peel Networks for Deep Video Completion

1 code implementation ICCV 2019 Seoung Wug Oh, Sungho Lee, Joon-Young Lee, Seon Joo Kim

Given a set of reference images and a target image with holes, our network fills the hole by referring the contents in the reference images.

Video Inpainting

Fast User-Guided Video Object Segmentation by Interaction-and-Propagation Networks

1 code implementation CVPR 2019 Seoung Wug Oh, Joon-Young Lee, Ning Xu, Seon Joo Kim

We propose a new multi-round training scheme for the interactive video object segmentation so that the networks can learn how to understand the user's intention and update incorrect estimations during the training.

Interactive Video Object Segmentation Semantic Segmentation +1

Video Object Segmentation using Space-Time Memory Networks

3 code implementations ICCV 2019 Seoung Wug Oh, Joon-Young Lee, Ning Xu, Seon Joo Kim

In our framework, the past frames with object masks form an external memory, and the current frame as the query is segmented using the mask information in the memory.

Ranked #4 on Interactive Video Object Segmentation on DAVIS 2017 (using extra training data)

Interactive Video Object Segmentation One-shot visual object segmentation +2

End-to-End Time-Lapse Video Synthesis from a Single Outdoor Image

no code implementations CVPR 2019 Seonghyeon Nam, Chongyang Ma, Menglei Chai, William Brendel, Ning Xu, Seon Joo Kim

Time-lapse videos usually contain visually appealing content but are often difficult and costly to create.

Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language

no code implementations NeurIPS 2018 Seonghyeon Nam, Yunji Kim, Seon Joo Kim

Our task aims to semantically modify visual attributes of an object in an image according to the text describing the new visual appearance.

Teaching Machines to Understand Baseball Games: Large-Scale Baseball Video Database for Multiple Video Understanding Tasks

no code implementations ECCV 2018 Minho Shim, Young Hwi Kim, Kyung-Min Kim, Seon Joo Kim

A major obstacle in teaching machines to understand videos is the lack of training data, as creating temporal annotations for long videos requires a huge amount of human effort.

Video Alignment Video Recognition

Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation

1 code implementation CVPR 2018 Younghyun Jo, Seoung Wug Oh, Jaeyeon Kang, Seon Joo Kim

We propose a novel end-to-end deep neural network that generates dynamic upsampling filters and a residual image, which are computed depending on the local spatio-temporal neighborhood of each pixel to avoid explicit motion compensation.

Data Augmentation Motion Compensation +2

Modelling the Scene Dependent Imaging in Cameras with a Deep Neural Network

no code implementations ICCV 2017 Seonghyeon Nam, Seon Joo Kim

Often called as the radiometric calibration, the process of recovering RAW images from processed images (JPEG format in the sRGB color space) is essential for many computer vision tasks that rely on physically accurate radiance values.

Computer Vision Deblurring +1

Deep Semantics-Aware Photo Adjustment

no code implementations26 Jun 2017 Seonghyeon Nam, Seon Joo Kim

Also, spatially varying photo adjustment methods have been studied by exploiting high-level features and semantic label maps.

Photo Retouching Scene Parsing

Building Emotional Machines: Recognizing Image Emotions through Deep Neural Networks

1 code implementation22 May 2017 Hye-Rin Kim, Yeong-Seok Kim, Seon Joo Kim, In-Kwon Lee

In this paper, we focus on two high level features, the object and the background, and assume that the semantic information of images is a good cue for predicting emotion.

Approaching the Computational Color Constancy as a Classification Problem through Deep Learning

no code implementations29 Aug 2016 Seoung Wug Oh, Seon Joo Kim

Computational color constancy refers to the problem of computing the illuminant color so that the images of a scene under varying illumination can be normalized to an image under the canonical illumination.

Color Constancy General Classification

Do It Yourself Hyperspectral Imaging With Everyday Digital Cameras

no code implementations CVPR 2016 Seoung Wug Oh, Michael S. Brown, Marc Pollefeys, Seon Joo Kim

In particular, due to the differences in spectral sensitivities of the cameras, different cameras yield different RGB measurements for the same spectral signal.

Illuminant Aware Gamut-Based Color Transfer

1 code implementation Pacific Graphics 2014 Rang Nguyen, Seon Joo Kim, Michael S. Brown

Our method is unique in its considera- tion of the scene illumination and the constraint that the mapped image must be within the color gamut of the target image.

Color Transfer Using Probabilistic Moving Least Squares

no code implementations CVPR 2014 Youngbae Hwang, Joon-Young Lee, In So Kweon, Seon Joo Kim

This paper introduces a new color transfer method which is a process of transferring color of an image to match the color of another image of the same scene.

Cannot find the paper you are looking for? You can Submit a new open access paper.