[J12] K. Joo, Tae-Hyun Oh, I.S. Kweon, J.-C. Bazin, “Globally Optimal Inlier Set Maximization for Atlanta World Understanding,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), to appear.
[J11] K. Joo, Tae-Hyun Oh, J. Kim, I.S. Kweon, “Robust and Globally Optimal Manhattan Frame Estimation in Near Real Time,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019.
[J10] Y. Aksoy, Tae-Hyun Oh, S. Paris, M. Pollefeys, W. Matusik, “Semantic Soft Segmentation,” ACM Transactions on Graphics (ACM SIGGRAPH), 2018. (Selected as Video Trailer)
[J9] I. Shim, Tae-Hyun Oh, J.-Y. Lee, D.-G. Choi, J. Choi, I.S. Kweon, “Gradient-based Camera Exposure Control for Outdoor Mobile Platforms,” IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2019.
[J7] I. Shim, Tae-Hyun Oh, I.S. Kweon, “High-fidelity Depth Upsamplingusing Self-learning Framework,” Sensors, MDPI, 2018.
[J6] Y. Aksoy, Tae-Hyun Oh, S. Paris, M. Pollefeys, W. Matusik, “Semantic Soft Segmentation”, ACM Transactions on Graphics (SIGGRAPH), 2018.
[J5] Tae-Hyun Oh, Y. Matsushita, Y.-W. Tai, I.S. Kweon, “Fast Randomized Singular Value Thresholding for Low-rank Optimization,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018.
[J4] H. Ha, Tae-Hyun Oh, I.S. Kweon, “A Closed-Form Solution to Rotation Estimation for Structure from Small Motion,” IEEE Signal Processing Letters (SPL), 2017.
[J3] Tae-Hyun Oh, H. Kim, Y.-W. Tai, J.-C. Bazin, I.S. Kweon, “Partial Sum Minimization of Singular Values in Robust PCA: Algorithm and Applications,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016.
[J2] I. Shim, J. Choi, S. Shin, Tae-Hyun Oh, U. Lee, B. Ahn, D.-G. Choi, D.H. Shim, I.S. Kweon, “An Autonomous Driving System for Unknown Environments using a Unified Map,” IEEE Transactions on Intelligent Transportation Systems (TITS), 2015.
[J1] Tae-Hyun Oh, J.Y. Lee, Y.-W. Tai, I.S. Kweon, “Robust High Dynamic Range Imaging by Rank Minimization,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015.

[C32] D-J. Kim, J. Choi, Tae-Hyun Oh, I.S. Kweon, “Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach,” Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019 (Acceptance rate 23.8%)
[C31] S. Lee, J. Kim, Tae-Hyun Oh, Y. Jeong, D. Yoo, S. Lin, I.S. Kweon, “Visuomotor Understanding for Representation Learning of Driving Scenes,” British Machine Vision Conference (BMVC), 2019 (Acceptance rate 28%)

[C30] A. Kaspar*, Tae-Hyun Oh*, L. Makatura, P. Kellnhofer, J. Aslarus, W. Matusik, “Neural Inverse Knitting: From Images to Manufacturing Instructions,” International Conference on Machine Learning (ICML), 2019 (Acceptance rate 22.4%) (* Equally contributed)
[C29] Tae-Hyun Oh*, T. Dekel*, C. Kim*, I. Mosseri, W. T. Freeman, M. Rubinstein, W. Matusik, “Speech2Face: Learning the Face Behind a Voice,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. (25.2% acceptance rate) (* Equally contributed)
[C28] J. Kim, Tae-Hyun Oh, S. Lee, F. Pan, I.S. Kweon, “Variational Prototyping-Encoder: One-Shot Learning with Prototypical Images,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. (25.2% acceptance rate)
[C27] D.-J. Kim, J. Choi, Tae-Hyun Oh, I.S. Kweon, “Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. (25.2% acceptance rate)
[C26] S. Shon, Tae-Hyun Oh, J. Glass, “Noise-Tolerant Audio-Visual Online Person Verification using an Attention-based Neural Network Fusion,” International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019.
[C25] C. Kim, H. V. Shin, Tae-Hyun Oh, A. Kaspar, M. Elgharib, W. Matusik. “On Learning Associations of Faces and Voices,” Asian Conference on Computer Vision (ACCV), 2018.
[C24] Tae-Hyun Oh*, R. Jaroensri*, C. Kim, M. Elgharib, F. Durand, W. T. Freeman, W. Matusik, “Learning-based Video Motion Magnification,” European Conference on Computer Vision (ECCV), 2018. (Accepted as a full oral paper, 2.3% acceptance rate) (* Equally contributed)
[C23] A. Senocak, Tae-Hyun Oh, J. Kim, I.S. Kweon, “Part-based Player Identification using Deep Convolutional Representation and Multi-scale Pooling,” CVSports workshop in conjunction with CVPR, 2018. (Selected as an oral paper)
[C22] K. Joo, Tae-Hyun Oh, I.S. Kweon, J.-C. Bazin, “Globally Optimal Inlier Set Maximization for Atlanta Frame Estimation,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (29% acceptance rate)
[C21] A. Senocak, Tae-Hyun Oh, J. Kim, M.-H. Yang, I.S. Kweon, “Learning to Localize Sound Source in Visual Scenes,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (29% acceptance rate)
[C20] J. Choi, Tae-Hyun Oh, I. S. Kweon, “Contextually Customized Video Summaries via Natural Language,” IEEE Winter Conference on Applications of Computer Vision (WAVC), 2018.
[C19] D.-J. Kim, J. Choi, Tae-Hyun Oh, Y. Yoon, I.S. Kweon, “Disjoint Multi-task Learning between Heterogeneous Human-centric Tasks,” IEEE Winter Conference on Applications of Computer Vision (WAVC), 2018.
[C18] J. Kim, S. Lee, Tae-Hyun Oh, I.S. Kweon, “Co-domain Embedding using Deep Quadruplet Network for Unseen Traffic Sign Recognition,” AAAI Conference on Artificial Intelligence (AAAI), 2018. (24.6% acceptance rate) (Best Poster Award from Image Processing and Image Understanding Workshop (IPIU), Korea.)
[C17] Tae-Hyun Oh*, K. Joo*, N. Joshi, B. Wang, I.S. Kweon, S. B. Kang, “Personalized Cinemagraphs using Semantic Understanding and Collaborative Learning,” IEEE International Conference on Computer Vision, (ICCV), 2017. (28.9% acceptance rate) (*Equally contributed) (Best Poster Presentation Award in IWRCV 2018)
[C16] D. Cho, J. Park, Tae-Hyun Oh, Y.-W. Tai, I. S. Kweon, Weakly- and Self-Supervised Learning for Content-aware Deep Image Retargeting, IEEE International Conference on Computer Vision, (ICCV), 2017. (Selected as a spotlight paper, 2.61% acceptance rate)
[C15] Tae-Hyun Oh, D. Wipf, Y. Matsushita, I.S. Kweon, “A Pseudo-Bayesian Algorithm for Robust PCA,” Neural Information Processing Systems (NIPS), 2016 (23.6% acceptance rate)
[C14] J. Choi, Tae-Hyun Oh, I.S. Kweon, “Video-Story Composition via Plot Analysis,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. (Selected as a spotlight paper, 9.7% acceptance rate)
[C13] K. Joo*, Tae-Hyun Oh*, J. Kim, I.S. Kweon, “Globally Optimal Manhattan Frame Estimation in Real-time,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. (29.9% acceptance rate) (*Equally contributed)
[C12] H. Ha, Tae-Hyun Oh, I.S. Kweon, “A Multi-View Structured-Light System for Highly Accurate 3D Modeling,” International Conference on 3D Vision (3DV), 2015.
[C11] K. Joo, N. Kim, Tae-Hyun Oh, I.S. Kweon, Line Meets As-Projective-As-Possible Image Stitching With Moving DLT, IEEE International Conference on Image Processing (ICIP), 2015. (Selected as a Top 10% paper)
[C10] Tae-Hyun Oh, Y. Matsushita, Y.-W. Tai, I.S. Kweon, “Fast Randomized Singular Value Thresholding for Nuclear Norm Minimization,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun., 2015 (28.4% acceptance rate) (Received Gold Prize, 0.8% acceptance rate, 21th HumanTech Paper Award, Samsung)
[C9] S.M. Hwang, Tae-Hyun Oh, I.S. Kweon, “A Two Phase Approach for Pedestrian Detection,” Workshop in conjunction with the 12th Asian Conference on Computer Vision (ACCVW), 2014.
[C8] M. J. Kim, Tae-Hyun Oh, I.S. Kweon, “Cost-Aware Depth Map Estimation for Lytro Camera,” IEEE International Conference on Image Processing (ICIP), 2014.
[C7] J. Choi, H. Kim, Tae-Hyun Oh, I.S. Kweon, “Balanced Optical Flow Refinement by Bidirectional Constraint,” IEEE International Conference on Image Processing (ICIP), 2014.
[C6] Tae-Hyun Oh, H. Kim, Y.-W. Tai, J.-C. Bazin, I.S. Kweon, “Partial Sum Minimization of Singular Values in RPCA for Low-Level Vision,” IEEE International Conference on Computer Vision, (ICCV), 2013. (27.9% acceptance rate)
[C5] Tae-Hyun Oh, J.-Y. Lee, I.S. Kweon, “High Dynamic Range Imaging by a Rank-1 Constraint,” IEEE International Conference on Image Processing (ICIP), 2013.
[C4] K. Joo, Tae-Hyun Oh, H. Kim, I.S. Kweon, “Hierarchical 3D Line Restoration based on Angular Proximity in Structured Environments,” IEEE International Conference on Image Processing (ICIP), 2013.
[C3] D.-G. Choi, I. Shim, Y. Bok, Tae-Hyun Oh, I.S. Kweon, Autonomous Homing based on Laser-Camera Fusion System, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2012.
[C2] J. Park, Tae-Hyun Oh, J. Jung, Y.-W. Tai, I.S. Kweon, A Tensor Voting Approach for Multi-View 3D Scene Flow Estimation and Refinement, European Conference on Computer Vision (ECCV), 2012. (23.3% acceptance rate)
[C1] Tae-Hyun Oh, J.-Y. Lee, I.S. Kweon, “Real-Time Motion Detection based on Discrete Cosine Transform,” IEEE International Conference on Image Processing (ICIP), 2012.

– Semantic Soft Segmentation, ACM SIGGRAPH 2018.
– Learning-based Video Motion Magnification, ECCV 2018 (Oral)
– Weakly- and Self-Supervised Learning for Content-aware Deep Image Retargeting, ICCV 2017. (Spotligh)
– Video-Story Composition via Plot Analysis, CVPR 2016. (Spotlight)
– High Dynamic Range Imaging by a Rank-1 Constraint, ICIP 2013.

– Apparatus for controlling exposure of multi-view camera, system including the same, and method for controlling exposure of multi-view camera, {App.; DE102017201286A1, CN107968918A}, US Patent granted US10230900B2.
– Generating semantically meaningful video loops in a cinemagraph, US Patent granted US9779774B1.
– Automatic generation of semantic-based cinemagraphs, {App.; US20180025749A1, WO2018017440A1}.
– Method and apparatus for detecting smoke from image, App. CN104346618A, US Patent grated US9443149B2.
– Method and system for detecting matrix-based motion including frequency transform and filtering, US Patent granted US9111359B2.