Следене
Tae-Hyun Oh
Tae-Hyun Oh
Associate Professor, KAIST
Потвърден имейл адрес: csail.mit.edu - Начална страница
Заглавие
Позовавания
Позовавания
Година
Learning to localize sound source in visual scenes
A Senocak, TH Oh, J Kim, MH Yang, IS Kweon
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2018
3842018
Listen to look: Action recognition by previewing audio
R Gao, TH Oh, K Grauman, L Torresani
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2020
3082020
Partial sum minimization of singular values in Robust PCA: Algorithm and applications
TH Oh, YW Tai, JC Bazin, H Kim, IS Kweon
Pattern Analysis and Machine Intelligence, IEEE Transactions on 38 (4), 744-758, 2016
2672016
Robust High Dynamic Range Imaging by Rank Minimization
TH Oh, JY Lee, YW Tai, IS Kweon
Pattern Analysis and Machine Intelligence, IEEE Transactions on 37 (6), 1219 …, 2015
2262015
Speech2face: Learning the face behind a voice
TH Oh, T Dekel, C Kim, I Mosseri, WT Freeman, M Rubinstein, W Matusik
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2019
2172019
Learning-based video motion magnification
TH Oh, R Jaroensri, C Kim, M Elgharib, F Durand, WT Freeman, ...
Proceedings of the European conference on computer vision (ECCV), 633-648, 2018
2072018
Fast randomized singular value thresholding for nuclear norm minimization
TH Oh, Y Matsushita, YW Tai, I So Kweon
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2015
1822015
Semantic soft segmentation
Y Aksoy, TH Oh, S Paris, M Pollefeys, W Matusik
ACM Transactions on Graphics (TOG) 37 (4), 1-13, 2018
1552018
Cross-attention of disentangled modalities for 3d human mesh recovery with transformers
J Cho, K Youwang, TH Oh
European Conference on Computer Vision, 342-359, 2022
1392022
Fedpara: Low-rank hadamard product for communication-efficient federated learning
N Hyeon-Woo, M Ye-Bin, TH Oh
arXiv preprint arXiv:2108.06098, 2021
1322021
Dense relational captioning: Triple-stream networks for relationship-based captioning
DJ Kim, J Choi, TH Oh, IS Kweon
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2019
1102019
Cds: Cross-domain self-supervised pre-training
D Kim, K Saito, TH Oh, BA Plummer, S Sclaroff, K Saenko
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
104*2021
On learning associations of faces and voices
C Kim, HV Shin, TH Oh, A Kaspar, M Elgharib, W Matusik
Computer Vision–ACCV 2018: 14th Asian Conference on Computer Vision, Perth …, 2019
1002019
Weakly-and self-supervised learning for content-aware deep image retargeting
D Cho, J Park, TH Oh, YW Tai, I So Kweon
Proceedings of the IEEE international conference on computer vision, 4558-4567, 2017
1002017
Variational prototyping-encoder: One-shot learning with prototypical images
J Kim, TH Oh, S Lee, F Pan, IS Kweon
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2019
892019
Partial sum minimization of singular values in RPCA for low-level vision
TH Oh, H Kim, YW Tai, JC Bazin, I So Kweon
Proceedings of the IEEE international conference on computer vision, 145-152, 2013
872013
Image captioning with very scarce supervised data: Adversarial semi-supervised learning approach
DJ Kim, J Choi, TH Oh, IS Kweon
arXiv preprint arXiv:1909.02201, 2019
742019
An Autonomous Driving System for Unknown Environments Using a Unified Map
I Shim, J Choi, S Shin, TH Oh, U Lee, B Ahn, DG Choi, DH Shim, ...
Intelligent Transportation Systems, IEEE Transactions on 16 (4), 1999 - 2013, 2015
702015
Noise-tolerant audio-visual online person verification using an attention-based neural network fusion
S Shon, TH Oh, J Glass
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
652019
Learning to localize sound sources in visual scenes: Analysis and applications
A Senocak, TH Oh, J Kim, MH Yang, IS Kweon
IEEE transactions on pattern analysis and machine intelligence 43 (5), 1605-1619, 2019
632019
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20