| Hubert: Self-supervised speech representation learning by masked prediction of hidden units WN Hsu, B Bolte, YHH Tsai, K Lakhotia, R Salakhutdinov, A Mohamed IEEE/ACM transactions on audio, speech, and language processing 29, 3451-3460, 2021 | 4686 | 2021 |
| 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 | 2514 | 2019 |
| Learning factorized multimodal representations YHH Tsai, PP Liang, A Zadeh, LP Morency, R Salakhutdinov arXiv preprint arXiv:1806.06176, 2018 | 672 | 2018 |
| 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 | 379 | 2019 |
| Self-supervised learning from a multi-view perspective YHH Tsai, Y Wu, R Salakhutdinov, LP Morency arXiv preprint arXiv:2006.05576, 2020 | 285 | 2020 |
| 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 | 259 | 2016 |
| Learning robust visual-semantic embeddings YH Hubert Tsai, LK Huang, R Salakhutdinov Proceedings of the IEEE International conference on Computer Vision, 3571-3580, 2017 | 228 | 2017 |
| 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 | 214 | 2021 |
| 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 | 133 | 2019 |
| Multimodal routing: Improving local and global interpretability of multimodal language analysis YHH Tsai, M Ma, M Yang, R Salakhutdinov, LP Morency Proceedings of the 2020 conference on empirical methods in natural language …, 2020 | 130 | 2020 |
| 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 | 129 | 2016 |
| Capsules with inverted dot-product attention routing YHH Tsai, N Srivastava, H Goh, R Salakhutdinov arXiv preprint arXiv:2002.04764, 2020 | 124 | 2020 |
| 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 | 115 | 2019 |
| 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 | 93 | 2015 |
| 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 | 80 | 2016 |
| Improving one-shot learning through fusing side information YHH Tsai, R Salakhutdinov arXiv preprint arXiv:1710.08347, 2017 | 65 | 2017 |
| Complex transformer: A framework for modeling complex-valued sequence M Yang, MQ Ma, D Li, YHH Tsai, R Salakhutdinov ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 61 | 2020 |
| Self-supervised representation learning with relative predictive coding YHH Tsai, MQ Ma, M Yang, H Zhao, LP Morency, R Salakhutdinov arXiv preprint arXiv:2103.11275, 2021 | 49 | 2021 |
| A note on connecting barlow twins with negative-sample-free contrastive learning YHH Tsai, S Bai, LP Morency, R Salakhutdinov arXiv preprint arXiv:2104.13712, 2021 | 46 | 2021 |
| 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 | 43 | 2016 |
Ruslan SalakhutdinovUPMC Professor, Machine Learning Department, CMUVerified email at cs.cmu.edu
