Follow
Kevin J. Shih
Kevin J. Shih
Research Scientist, NVIDIA
Verified email at nvidia.com
Title
Cited by
Cited by
Year
Image inpainting for irregular holes using partial convolutions
G Liu, FA Reda, KJ Shih, TC Wang, A Tao, B Catanzaro
Proceedings of the European conference on computer vision (ECCV), 85-100, 2018
21642018
Where to look: Focus regions for visual question answering
KJ Shih, S Singh, D Hoiem
Computer Vision and Pattern Recognition 2016, 2015
5652015
Improving semantic segmentation via video propagation and label relaxation
Y Zhu, K Sapra, FA Reda, KJ Shih, S Newsam, A Tao, B Catanzaro
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2019
4432019
Graphical contrastive losses for scene graph parsing
J Zhang, KJ Shih, A Elgammal, A Tao, B Catanzaro
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2019
2302019
Sdc-net: Video prediction using spatially-displaced convolution
FA Reda, G Liu, KJ Shih, R Kirby, J Barker, D Tarjan, A Tao, B Catanzaro
Proceedings of the European conference on computer vision (ECCV), 718-733, 2018
1622018
Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis
R Valle, K Shih, R Prenger, B Catanzaro
arXiv preprint arXiv:2005.05957, 2020
1522020
Partial convolution based padding
G Liu, KJ Shih, TC Wang, FA Reda, K Sapra, Z Yu, A Tao, B Catanzaro
arXiv preprint arXiv:1811.11718, 2018
952018
Learning collections of part models for object recognition
I Endres, KJ Shih, J Jiaa, D Hoiem
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2013
882013
Unsupervised video interpolation using cycle consistency
FA Reda, D Sun, A Dundar, M Shoeybi, G Liu, KJ Shih, A Tao, J Kautz, ...
Proceedings of the IEEE/CVF international conference on computer Vision, 892-900, 2019
852019
Learning Interpretable Spatial Operations in a Rich 3D Blocks World
Y Bisk, KJ Shih, Y Choi, D Marcu
Proceedings of the Thirty-Second Conference on Artificial Intelligence (AAAI-18), 2018
712018
One TTS alignment to rule them all
R Badlani, A Łańcucki, KJ Shih, R Valle, W Ping, B Catanzaro
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
612022
Part localization using multi-proposal consensus for fine-grained categorization
KJ Shih, A Mallya, S Singh, D Hoiem
BMVC 2015, 2015
592015
RAD-TTS: Parallel flow-based TTS with robust alignment learning and diverse synthesis
KJ Shih, R Valle, R Badlani, A Lancucki, W Ping, B Catanzaro
ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit …, 2021
392021
Recognition of items depicted in images
K Shih, W Di, V Jagadeesh, R Piramuthu
US Patent App. 14/973,582, 2016
362016
Partial convolution for padding, inpainting, and image synthesis
G Liu, A Dundar, KJ Shih, TC Wang, FA Reda, K Sapra, Z Yu, X Yang, ...
IEEE Transactions on Pattern Analysis and Machine Intelligence 45 (5), 6096-6110, 2022
332022
Video prediction using spatially displaced convolution
G Liu, K Shih, R Kirby, J Barker, D Tarjan, A Tao, B Catanzaro
US Patent App. 16/360,853, 2019
302019
Unsupervised disentanglement of pose, appearance and background from images and videos
A Dundar, KJ Shih, A Garg, R Pottorf, A Tao, B Catanzaro
IEEE Transactions on Pattern Analysis and Machine Intelligence 44 (7), 3883-3894, 2021
272021
Revisiting image-language networks for open-ended phrase detection
BA Plummer, KJ Shih, Y Li, K Xu, S Lazebnik, S Sclaroff, K Saenko
IEEE transactions on pattern analysis and machine intelligence 44 (4), 2155-2167, 2020
262020
An interpretable model for scene graph generation
J Zhang, K Shih, A Tao, B Catanzaro, A Elgammal
arXiv preprint arXiv:1811.09543, 2018
222018
Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks
T Gupta, K Shih, S Singh, D Hoiem
arXiv preprint arXiv:1704.00260, 2017
222017
The system can't perform the operation now. Try again later.
Articles 1–20