Shiyu Chang
Artificial Intelligence · 2011–2022
A researcher in the Science corpus: 41 papers; trusts 3,168 researchers and is trusted by 510 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 936 citations into it; #2,431 of 36,961 by trust here, #1,631 by citations
- Computer Vision and Pattern Recognition — 677 citations into it; #2,691 of 21,973 by trust here, #1,445 by citations
- Natural Language Processing — 307 citations into it; #1,632 of 5,725 by trust here, #1,026 by citations
- Generative Models — 152 citations into it; #481 of 1,963 by trust here, #588 by citations
- Model Architectures — 131 citations into it; #833 of 2,288 by trust here, #991 by citations
- Representation & Self-Supervised Learning — 130 citations into it
- Optimization & Training — 82 citations into it
- Evaluation & Benchmarks — 81 citations into it; #3,045 of 3,155 by trust here, #1,900 by citations
Whom Shiyu Chang trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Kaiming He
- Yoshua Bengio
- Diederik P. Kingma
- Ilya Sutskever
- Yann LeCun
- Ross B. Girshick
- Karen Simonyan
- Alex Graves
Who trusts Shiyu Chang overall
- Meng-Hao Guo
- Zizhao Zhang
- Yingying Deng
- Zhangyang Wang
- Vincent Wenchen Zheng
- Kai Han
- Yunhe Wang
- Salman Hameed Khan
- Dongjun Kim
- Yi Tay
Papers from Shiyu Chang's perspective
Ordered by how strongly the researchers Shiyu Chang 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
- Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering (2017) — 166 citations
- R3: Reinforced Ranker-Reader for Open-Domain Question Answering (2018) — 200 citations
- R3: Reinforced Reader-Ranker for Open-Domain Question Answering (2017) — 64 citations
- Fast Generation for Convolutional Autoregressive Models (2017) — 67 citations
- TransGAN: Two Transformers Can Make One Strong GAN (2021) — 234 citations
- Learning Locally-Adaptive Decision Functions for Person Verification (2013) — 528 citations
- Diverse Few-Shot Text Classification with Multiple Metrics (2018) — 225 citations
- Few-shot Text Classification with Distributional Signatures (2019) — 184 citations
- Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader (2019) — 126 citations
- Towards cross-category knowledge propagation for learning visual concepts (2011) — 83 citations
- AutoGAN: Neural Architecture Search for Generative Adversarial Networks (2019) — 289 citations
- Studying Very Low Resolution Recognition Using Deep Networks (2016) — 236 citations
- Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control (2019) — 159 citations
- Dilated Recurrent Neural Networks (2017) — 351 citations
- Image Super-Resolution via Dual-State Recurrent Networks (2018) — 241 citations
- Learning Corresponded Rationales for Text Matching (2018) — 8 citations
- A Co-Matching Model for Multi-choice Reading Comprehension (2018) — 96 citations
- Fast Wavenet Generation Algorithm (2016) — 88 citations
- Deriving Machine Attention from Human Rationales (2018) — 113 citations
- TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up (2021) — 500 citations