Yao-Hung Hubert Tsai
Artificial Intelligence · 2016–2021
A researcher in the Science corpus: 13 papers; trusts 2,128 researchers and is trusted by 118 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 389 citations into it; #3,706 of 36,961 by trust here, #3,857 by citations
- Computer Vision and Pattern Recognition — 261 citations into it; #4,752 of 21,973 by trust here, #6,105 by citations
- Representation & Self-Supervised Learning — 150 citations into it; #941 of 3,156 by trust here, #668 by citations
- Natural Language Processing — 78 citations into it
- Signal Processing — 78 citations into it; #1,225 of 7,592 by trust here, #477 by citations
- Model Architectures — 60 citations into it; #2,064 of 2,288 by trust here, #1,186 by citations
- Speech & Audio — 52 citations into it; #315 of 1,080 by trust here, #257 by citations
- Optimization & Training — 36 citations into it
Whom Yao-Hung Hubert Tsai trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Diederik P. Kingma
- Kaiming He
- Alex Krizhevsky
- Yoshua Bengio
- Ross B. Girshick
- Ilya Sutskever
- Yann LeCun
- Ruslan Salakhutdinov
- Jimmy Ba
Who trusts Yao-Hung Hubert Tsai overall
- Edgar Schönfeld
- Percy Liang
- Wenmeng Yu
- Ruslan Salakhutdinov
- Wei-Ning Hsu
- Jun Shu
- Amir Zadeh
- Shuhao Cao
- Chao Zhang
- Louis-philippe Morency
Papers from Yao-Hung Hubert Tsai's perspective
Ordered by how strongly the researchers Yao-Hung Hubert Tsai trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Multimodal Transformer for Unaligned Multimodal Language Sequences (2019) — 2,255 citations
- Learning Robust Visual-Semantic Embeddings (2017) — 197 citations
- HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units (2021) — 4,844 citations
- Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel (2019) — 333 citations
- Learning Factorized Multimodal Representations (2018) — 551 citations
- Improving One-Shot Learning through Fusing Side Information (2017) — 53 citations
- Self-supervised Learning from a Multi-view Perspective (2020) — 234 citations
- Video Relationship Reasoning Using Gated Spatio-Temporal Energy Graph (2019) — 112 citations
- Hubert: How Much Can a Bad Teacher Benefit ASR Pre-Training? (2021) — 184 citations
- Capsules with Inverted Dot-Product Attention Routing (2020) — 93 citations
- Conditional Contrastive Learning: Removing Undesirable Information in Self-Supervised Representations (2021) — 27 citations
- Learning Neural Networks with Adaptive Regularization (2019) — 19 citations
- Transfer Neural Trees for Heterogeneous Domain Adaptation (2016) — 93 citations