Yao-Hung Hubert Tsai
Yao-Hung Hubert Tsai
Verified email at andrew.cmu.edu - Homepage
Title
Cited by
Cited by
Year
Multimodal transformer for unaligned multimodal language sequences
YHH Tsai, S Bai, PP Liang, JZ Kolter, LP Morency, R Salakhutdinov
Proceedings of the conference. Association for Computational Linguistics …, 2019
1812019
Learning cross-domain landmarks for heterogeneous domain adaptation
YHH Tsai, YR Yeh, YCF Wang
Proceedings of the IEEE conference on computer vision and pattern …, 2016
1312016
Learning cross-domain landmarks for heterogeneous domain adaptation
YHH Tsai, YR Yeh, YCF Wang
Proceedings of the IEEE conference on computer vision and pattern …, 2016
1312016
Learning robust visual-semantic embeddings
YH Hubert Tsai, LK Huang, R Salakhutdinov
Proceedings of the IEEE International Conference on Computer Vision, 3571-3580, 2017
1172017
Learning factorized multimodal representations
YHH Tsai, PP Liang, A Zadeh, LP Morency, R Salakhutdinov
arXiv preprint arXiv:1806.06176, 2018
1122018
Unsupervised domain adaptation with label and structural consistency
CA Hou, YHH Tsai, YR Yeh, YCF Wang
IEEE Transactions on Image Processing 25 (12), 5552-5562, 2016
832016
Unsupervised domain adaptation with imbalanced cross-domain data
TMH Hsu, WY Chen, CA Hou, YHH Tsai, YR Yeh, YCF Wang
Proceedings of the IEEE International Conference on Computer Vision, 4121-4129, 2015
492015
Video relationship reasoning using gated spatio-temporal energy graph
YHH Tsai, S Divvala, LP Morency, R Salakhutdinov, A Farhadi
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2019
472019
Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel
YHH Tsai, S Bai, M Yamada, LP Morency, R Salakhutdinov
arXiv preprint arXiv:1908.11775, 2019
392019
Capsules with inverted dot-product attention routing
YHH Tsai, N Srivastava, H Goh, R Salakhutdinov
arXiv preprint arXiv:2002.04764, 2020
372020
Transfer neural trees for heterogeneous domain adaptation
WY Chen, TMH Hsu, YHH Tsai, YCF Wang, MS Chen
European Conference on Computer Vision, 399-414, 2016
372016
Improving one-shot learning through fusing side information
YHH Tsai, R Salakhutdinov
arXiv preprint arXiv:1710.08347, 2017
312017
Learning representations from imperfect time series data via tensor rank regularization
PP Liang, Z Liu, YHH Tsai, Q Zhao, R Salakhutdinov, LP Morency
arXiv preprint arXiv:1907.01011, 2019
262019
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
WN Hsu, B Bolte, YHH Tsai, K Lakhotia, R Salakhutdinov, A Mohamed
arXiv preprint arXiv:2106.07447, 2021
232021
HuBERT: How much can a bad teacher benefit ASR pre-training?
WN Hsu, YHH Tsai, B Bolte, R Salakhutdinov, A Mohamed
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
222021
Strong and simple baselines for multimodal utterance embeddings
PP Liang, YC Lim, YHH Tsai, R Salakhutdinov, LP Morency
arXiv preprint arXiv:1906.02125, 2019
212019
Domain-constraint transfer coding for imbalanced unsupervised domain adaptation
YHH Tsai, CA Hou, WY Chen, YR Yeh, YCF Wang
Thirtieth AAAI Conference on Artificial Intelligence, 2016
212016
Self-supervised learning from a multi-view perspective
YHH Tsai, Y Wu, R Salakhutdinov, LP Morency
arXiv preprint arXiv:2006.05576, 2020
202020
Recognizing heterogeneous cross-domain data via generalized joint distribution adaptation
YT Hsieh, SY Tao, YHH Tsai, YR Yeh, YCF Wang
2016 IEEE International Conference on Multimedia and Expo (ICME), 1-6, 2016
142016
Multimodal routing: Improving local and global interpretability of multimodal language analysis
YHH Tsai, MQ Ma, M Yang, R Salakhutdinov, LP Morency
Proceedings of the Conference on Empirical Methods in Natural Language …, 2020
102020
The system can't perform the operation now. Try again later.
Articles 1–20