Publications

To check out AMI Lab's domestic publication list, please refer to this page
Information about computer vision and machine learning academic field * Top-tier conferences : CVPR, ICCV, ECCV, NeurIPS (NIPS), ICML, and ICLR are considered as high prestigious and top-tier conferences, which deem to have larger impacts than most SCI journals. According to Google scholar metrics, all these conferences are listed in the top 100 in all academic fields. Out of them, CVPR is the 5th rank (Science and Nature are the 1st and 3rd ranked) among all academic fields, In terms of the acceptance rate, oral presentations are about <4% and poster presentations about 25%, i.e., highly competitive. * Top-tier journals : IEEE TPAMI has the highest impact factor across all computer science categories. As of 2021, the impact factor of TPAMI is 24.314.

2022

Journals

Dense Relational Image Captioning via Multi-task Triple-Stream Networks

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), to appear (IF 24.314) [arXiv] [Github]
Dong-Jin Kim, Tae-Hyun Oh, Jinsoo Choi, In So Kweon

Robust and Efficient Estimation of Relative Pose for Cameras on Selfie Sticks

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2022 (IF 24.314) [PDF]
Kyungdon Joo, Hongdong Li, Tae-Hyun Oh, In So Kweon

Neural-Network-Based Automated Synthesis of Transformer Matching Circuits for RF Amplifier Design

IEEE Transactions on Microwave Theory and Techniques, to appear (IF 4.381) [PDF]
Dongyoon Lee, Gibeom Shin, Seunghoon Lee, Kyunghwan Kim, Tae-Hyun Oh, Ho-Jin Song

ENInst: Enhancing Weakly-supervised Low-shot Instance Segmentation

Under Review - IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
Moon Ye-Bin, Dongmin Choi, Yongjin Kwon, Junsik Kim, Tae-Hyun Oh

Adversarial Semi-Supervised Image Captioning

Under Review - IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
Dong-Jin Kim, Tae-Hyun Oh, Jinsoo Choi, In So Kweon

An Iterative Method for Unsupervised Robust Anomaly Detection under Data Contamination

Under Review - IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
Minkyung Kim, Jongmin Yu, Junsik Kim, Tae-Hyun Oh, Jun Kyun Choi

Multi-stage High Rank Pruning for Lightweight Human 3D Mesh Recovery Model

Under Review - The Visual Computer Journal (TVCJ)
Dong Hun Ryou, Kim Youwang, Tae-Hyun Oh

Conferences

ComMU: Dataset for Combinatorial Music Generation

Conference on Neural Information Processing Systems (NeurIPS) — Dataset Track, 2022 [Paper] [Project Page]
Lee Hyun*, Taehyun Kim*, Hyolim Kang, Minjoo Ki, Hyeonchan Hwang, Kwanho Park, Sharang Han, Seon Joo Kim (*equal contribution)

CLIP-Actor: Text-Driven Recommendation and Stylization for Animating Human Meshes

European Conference on Computer Vision (ECCV) 2022 [arXiv] [Project Page] [Code]
Kim Youwang*, Kim Ji-Yeon*, Tae-Hyun Oh (*equal contribution)

HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields

European Conference on Computer Vision (ECCV) 2022 [arXiv]
Kim Jun-Seong*, Kim Yu-Ji*, Moon Ye-Bin, Tae-Hyun Oh (*equal contribution)

Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers

European Conference on Computer Vision (ECCV) 2022 [arXiv] [Project Page] [Code]
Junhyeong Cho, Kim Youwang, Tae-Hyun Oh

FedPara: Low-Rank Hadamard Product For Communication-Efficient Federated Learning

International Conference on Learning Representations (ICLR) 2022 [arXiv]
Nam Hyeon-Woo, Moon Ye-Bin, Tae-Hyun Oh

Speech De-warping: Unsupervised Pre-training for Data-Efficient Text-to-Speech on Low Resource Languages

Workshop on Machine Learning for Audio Synthesis (in conj. with ICML) 2022 [URL]
Myungseo Song, Seongyeon Park, Bohyung Kim, Tae-Hyun Oh
* Accepted as a contributed talk (oral presentation)

Audio-Visual Fusion Layers for Event Type Aware Video Recognition

arXiv preprint 2022 [arXiv]
Arda Senocak, Junsik Kim, Tae-Hyun Oh, Hyeonggon Ryu, Dingzeyu Li, In So Kweon

FICGAN: Facial Identity Controllable GAN for De-identification

arXiv preprint 2022 [arXiv]
Yonghyun Jeong, Jooyoung Choi, Sungwon Kim, Youngmin Ro, Tae-Hyun Oh, Doyeon Kim, Heonseok Ha, Sungroh Yoon

2021

Journals

Lightweight Speaker Recognition in Poincaré Spaces

IEEE Signal Processing Letters (SPL) 2021 [PDF]
Jieun Lee*Kim Sung-Bin*, Seokhyeong Kang, Tae-Hyun Oh (*equal contribution)

Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2021 [Dataset] [Code(PyTorch)] [Featured by Seamless]
Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming-Hsuan Yang, In So Kweon

Conferences

Unified 3D Mesh Recovery of Humans and Animals by Learning Animal Exercise

British Machine Vision Conference (BMVC) 2021 [PDF] [Project Page]
Kim Youwang, Kim Ji-Yeon, Kyungdon Joo, Tae-Hyun Oh

CDS: Cross-Domain Self-supervised Pre-training

International Conference on Computer Vision (ICCV) 2021 [PDF] [Project Page]
Donghyun Kim, Kuniaki Saito, Tae-Hyun Oh, Bryan Plummer, Stan Sclaroff, Kate Saenko

Distilling Global and Local Logits with Densely Connected Relations

International Conference on Computer Vision (ICCV) 2021 [PDF]
Youmin Kim, Jinbae Park, YounHo Jang, Muhammad Ali, Tae-Hyun Oh, Sung-Ho Bae

Monocular Reconstruction of Neural Face Reflectance Fields

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021 [PDF] [Project Page]
Mallikarjun B R, Ayush Tewari, Tae-Hyun Oh, Tim Weyrich, Bernd Bickel, Hans-Peter Seidel, Hanspeter Pfister, Wojciech Matusik, Mohamed Elgharib, Christian Theobalt

MDARTS: Multi-objective Differentiable Neural Architecture Search

Design Automation and Test in Europe (DATE) 2021 [PDF]
Sunghoon Kim, Hyunjeong Kwon, Eunji Kwon, Youngchang Choi, Tae-Hyun Oh, Seokhyeong Kang

Supervoxel Attention Graphs for Long-Range Video Modeling

Winter Conference on Applications of Computer Vision (WACV) 2021 [PDF]
Yang Wang, Gedas Bertasius, Tae-Hyun Oh, Abhinav Gupta, Minh Hoai Nguyen, Lorenzo Torresani

2020

Journals

Globally Optimal Inlier Set Maximization for Atlanta World Understanding

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2020 [Project Page] [IEEE Xplore]
Kyungdon Joo, Tae-Hyun Oh, In So Kweon, Jean-Charles Bazin

Conferences

Listen to Look: Action Recognition by Previewing Audio

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020 [PDF] [Project Page]
Ruohan Gao, Tae-Hyun Oh, Kristen Grauman, Lorenzo Torresani

Linear RGB-D SLAM for Atlanta World

IEEE International Conference on Robotics and Automation (ICRA) 2020 [PDF]
Kyungdon Joo, Tae-Hyun Oh, Francois Rameau, Jean-Charles Bazin, In So Kweon

Globally Optimal Relative Pose Estimation for Camera on a Selfie Stick

IEEE International Conference on Robotics and Automation (ICRA) 2020 [PDF]
Kyungdon Joo, Hongdong Li, Tae-Hyun Oh, Yunsu Bok, In So Kweon

2019

Journals

High-fidelity Depth Upsampling using Self-learning Framework

Sensors 2019 [PDF] [Video1] [Video2] [Video3]
Inwook Shim, Tae-Hyun Oh, In So Kweon

Robust and Globally Optimal Manhattan Frame Estimation in Near Real Time

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2019 [Code and Project page] [arXiv] [IEEE Xplore]
Kyungdon Joo, Tae-Hyun Oh, Junsik Kim, In So Kweon

Gradient-based Camera Exposure Control for Outdoor Mobile Platforms

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) 2019 [Project Page] [IEEE Xplore] [arXiv]
Inwook Shim, Tae-Hyun Oh, Joon-Young Lee, Dong-Geol Choi, Jinwook Choi, In So Kweon

Conferences

Speech2Face: Learning the Face Behind a Voice

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019 [PDF] [Project Page]
Tae-Hyun Oh*, Tali Dekel*, Changil Kim*, Inbar Mosseri, William T. Freeman, Michael Rubinstein, Wojciech Matusik (*equal contribution)

Neural Inverse Knitting: From Images to Manufacturing Instructions

International Conference on Machine Learning (ICML) 2019 [PDF] [Project Page]
Alexandre Kaspar*, Tae-Hyun Oh*, Liane Makatura, Petr Kellnhofer, Jacqueline Aslarus, Wojciech Matusik (*equal contribution)
* Covered by more than 20 media (BBC News, Fortune, Engadget, ...)

Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019 [Project Page] [PDF] [Dataset] [code] [Slides] [Poster]
Dong-Jin Kim, Tae-Hyun Oh, Jinsoo Choi, In So Kweon

Noise-tolerant Audio-visual Online Person Verification using an Attention-based Neural Network Fusion

International Conference on Acoustics Speech and Signal Processing (ICASSP) 2019 [PDF]
Suwon Shon, Tae-Hyun Oh, James Glass

Variational Prototyping-Encoder: One-Shot Learning with Prototypical Images

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019 [PDF] [Project Page] Junsik Kim, Tae-Hyun Oh, Seokju Lee, Fei Pan, In So Kweon

Visuomotor Understanding for Representation Learning of Driving Scenes

British Machine Vision Conference (BMVC) 2019 [PDF] [Project Page] [Dataset]
Seokju Lee, Junsik Kim, Tae-Hyun Oh, Yongseop Jeong, Donggeun Yoo, Stephen Lin, In So Kweon

Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach

Conference on Empirical Methods in Natural Language Processing (EMNLP) 2019 [PDF] [Project Page]
Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, In So Kweon

2018

Journals

Fast Randomized Singular Value Thresholding for Low-rank Optimization

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2018 [Project Page] [arXiv]
Tae-Hyun Oh, Yasuyuki Matsushita, Yu-Wing Tai, In So Kweon
* Gold Prize (Acceptance Rate 0.8%), 21th HumanTech Paper Award by Samsung

Semantic Soft Segmentation

ACM Transactions on Graphics (SIGGRAPH) (TOG) 2018 [Project Page]
Yağiz Aksoy, Tae-Hyun Oh, Sylvain Paris, Marc Pollefeys, Wojciech Matusik
* Covered by international news media and featured as Tech. paper preview by SIGGRAPH

Conferences

Learning-based Video Motion Magnification

European Conference on Computer Vision (ECCV) 2018 [PDF] [Project Page] [Video Results] [Oral Presentation]
Tae-Hyun Oh*, Ronnachai Jaroensri*, Changil Kim, Mohamed Elgharib, Frédo Durand, William T. Freeman, Wojciech Matusik (*equal contribution)
* Accepted as a full oral paper (2.3% acceptance rate)

Co-domain Embedding using Deep Quadruplet Network for Unseen Traffic Sign Recognition

AAAI Conference on Artificial Intelligence (AAAI) 2018 [PDF] [Project Page]
Junsik Kim , Seokju Lee , Tae-Hyun Oh , In So Kweon

Disjoint Multi-task Learning between Heterogeneous Human-centric Tasks

Winter Conference on Applications of Computer Vision (WACV) 2018 [PDF]
Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, Youngjin Yoon, In So Kweon
* Accepted as a full oral paper

Contextually Customized Video Summaries via Natural Language

Winter Conference on Applications of Computer Vision (WACV) 2018 [PDF]
Jinsoo Choi, Tae-Hyun Oh, In So Kweon

Learning to Localize Sound Source in Visual Scenes

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018 [PDF] [Code & Dataset] [Featured by Seamless]
Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming-Hsuan Yang, In So Kweon

Globally Optimal Inlier Set Maximization for Atlanta Frame Estimation

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018 [PDF] [Project Page]
Kyungdon Joo, Tae-Hyun Oh, In So Kweon, Jean-Charles Bazin

Part-based Player Identification using Deep Convolutional Representation and Multi-scale Pooling

CVSports workshop in conjunction with CVPR 2018 [PDF]
Arda Senocak, Tae-Hyun Oh, Junsik Kim, In So Kweon

On Learning Associations of Faces and Voices

Asian Conference on Computer Vision (ACCV) 2018 [PDF] [Project Page]
Changil Kim, Hijung Valentina Shin, Tae-Hyun Oh, Alexandre Kaspar, Mohamed Elgharib, Wojciech Matusik

2017

Journals

A Closed-Form Solution to Rotation Estimation for Structure from Small Motion

IEEE Signal Processing Letters (SPL) 2017 [IEEE Xplore]
Hyowon Ha, Tae-Hyun Oh, In So Kweon

Conferences

Weakly-and Self-Supervised Learning for Content-aware Deep Image Retargeting

IEEE International Conference on Computer Vision (ICCV) 2017 [PDF]
Donghyeon Cho, Jinsun Park, Tae-Hyun Oh, Yu-Wing Tai, In So Kweon
* Selected as spotlight (2.61% acceptance rate)

Personalized Cinemagraphs using Semantic Understanding and Collaborative Learning

IEEE International Conference on Computer Vision (ICCV) 2017 [PDF]
{Tae-Hyun Oh, Kyungdon Joo}*, Neel Joshi, Baoyuan Wang, In So Kweon, Sing Bing Kang (*equal contribution)

2016

Journals

Human Attention Estimation for Natural Images: An Automatic Gaze Refinement Approach

arXiv 2016 [arXiv]
Jinsoo Choi, Tae-Hyun Oh, In So Kweon

Partial Sum Minimization of Singular Values in Robust PCA: Algorithm and Applications

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2016 [Project Page] [arXiv]
Tae-Hyun Oh, Yu-Wing Tai, Jean-Chales Bazin, Hyeongwoo Kim, In So Kweon

Conferences

Robust and Globally Optimal Manhattan Frame Estimation in Near Real Time

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016 [Code & Project Page]
{Tae-Hyun Oh, Kyungdon Joo}*, Junsik Kim, In So Kweon (*equal contribution)

Video-Story Composition via Plot Analysis

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016 [PDF] [Presentation] [Dataset]
Jinsoo Choi, Tae-Hyun Oh, In So Kweon
* Selected as spotlight (9.7% acceptance rate)

A Pseudo-Bayesian Algorithm for Robust PCA

Neural Information Processing Systems (NeurIPS) 2016 [PDF]
Tae-Hyun Oh, David Wipf, Yasuyuki Matsushita, In So Kweon

2015

Journals

Pseudo-Bayesian Robust PCA: Algorithms and Analysis

arXiv 2015 [arXiv]
Tae-Hyun Oh, David Wipf, Yasuyuki Matsushita, In So Kweon

Robust High Dynamic Range Imaging by Rank Minimization

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2015 [Code] [IEEE Xplore]
Tae-Hyun Oh, Joon-Young Lee, Yu-Wing Tai, In So Kweon

An Autonomous Driving System for Unknown Environments using a Unified Map

IEEE Transactions on Intelligence Transportation Systems (TITS) 2015 [IEEE Xplore] [Video]
Inwook Shim, Jongwon Choi, Seunghak Shin, Tae-Hyun Oh, Unghui Lee, Byungtae Ahn, Dong-Geol Choi, David Hyunchul Shim, In So Kweon
* Qualcomm Innovation Award 2013
* Youl-Jeong award (5th rank) from the Hyundai Motors Autonomous Vehicle Challenge 2012

Conferences

Fast Randomized Singular Value Thresholding for Nuclear Norm Minimization

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015 [Project Page]
Tae-Hyun Oh, Yasuyuki Matsushita, Yu-Wing Tai, In So Kweon

Line Meets As-Projective-As-Possible Image Stitching With Moving DLT

IEEE International Conference on Image Processing (ICIP) 2015 [PDF]
Kyungdon Joo, Namil Kim, Tae-Hyun Oh, In So Kweon
* Selected as the Top 10% paper

A Multi-View Structured-Light System for Highly Accurate 3D Modeling

International Conference on 3D Vision (3DV) 2015
Hyowon Ha, Tae-Hyun Oh, In So Kweon

2014

Conferences

Balanced Optical Flow Refinement by Bidirectional Constraint

IEEE International Conference on Image Processing (ICIP) 2014
Jongwon Choi, Hyeongwoo Kim, Tae-Hyun Oh, In So Kweon

Cost-Aware Depth Map Estimation for Lytro Camera

IEEE International Conference on Image Processing (ICIP) 2014
Min Jung Kim, Tae-Hyun Oh, In So Kweon

A Two Phase Approach for Pedestrian Detection

Workshop in conjunction with the 12th Asian Conference on Computer Vision (ACCVW) 2014
SoonMin Hwang, Tae-Hyun Oh, In So Kweon

2013

Conferences

Partial Sum Minimization of Singular Values in RPCA for Low-Level Vision

IEEE International Conference on Computer Vision (ICCV) 2013 [PDF]
Tae-Hyun Oh, Hyeongwoo Kim, Yu-Wing Tai, Jean-Chales Bazin, In So Kweon

High Dynamic Range Imaging by a Rank-1 Constraint

IEEE International Conference on Image Processing (ICIP) 2013 [PDF] [Code]
Tae-Hyun Oh, Joon-Young Lee, In So Kweon

Hierarchical 3D Line Restoration based on Angular Proximity in Structured Environments

IEEE International Conference on Image Processing (ICIP) 2013 [PDF]
Kyungdon Joo, Tae-Hyun Oh, Hyeongwoo Kim, In So Kweon

2012

Conferences

Autonomous Homing based on Laser-Camera Fusion System

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2012 [PDF]
Dong-Geol Choi, Inwook Shim, Yunsu Bok, Tae-Hyun Oh, In So Kweon

A Tensor Voting Approach for Multi-View 3D Scene Flow Estimation and Refinement

European Conference on Computer Vision (ECCV) 2012 [PDF]
Jaesik Park, Tae-Hyun Oh, Jiyoung Jung, Yu-Wing Tai, In So Kweon

Real-Time Motion Detection based on Discrete Cosine Transform

IEEE International Conference on Image Processing (ICIP) 2012 [PDF]
Tae-Hyun Oh, Joon-Young Lee, In So Kweon