Wenzhe Shi

Computer Vision and Pattern Recognition · 2016–2017

A researcher in the Science corpus: 7 papers; trusts 703 researchers and is trusted by 1,279 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 219 citations into it; #1,192 of 21,575 by trust here, #554 by citations
• Media Technology — 77 citations into it; #154 of 3,621 by trust here, #13 by citations
• Generative Models — 53 citations into it; #341 of 1,956 by trust here, #103 by citations
• Artificial Intelligence — 48 citations into it
• Model Architectures — 23 citations into it
• Computational Mechanics — 19 citations into it
• Evaluation & Benchmarks — 18 citations into it
• Optimization & Training — 16 citations into it

Whom Wenzhe Shi trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Diederik P. Kingma
2. Yann LeCun
3. Geoffrey E. Hinton
4. Kaiming He
5. Matthew D. Zeiler
6. Alex Krizhevsky
7. Yoshua Bengio
8. Rob Fergus
9. Karen Simonyan
10. Ilya Sutskever

Who trusts Wenzhe Shi overall

1. Eirikur Agustsson
2. Yulun Zhang
3. Kai Zhang
4. Fabian Mentzer
5. Saeed Anwar
6. Radu Timofte
7. Wangmeng Zuo
8. Zizhao Zhang
9. Luc Van Gool
10. Yapeng Tian

Papers from Wenzhe Shi's perspective

Ordered by how strongly the researchers Wenzhe Shi trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Gradient-based learning applied to document recognition
5. ImageNet: A large-scale hierarchical image database
6. Long Short-Term Memory
7. Attention is All you Need (Neural Information Processing Systems)
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. ImageNet Large Scale Visual Recognition Challenge
10. Going deeper with convolutions

Their papers

• Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (2016) — 12,248 citations
• Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (2016) — 6,030 citations
• Amortised MAP Inference for Image Super-resolution (2016) — 448 citations
• Lossy Image Compression with Compressive Autoencoders (2017) — 1,156 citations
• Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation (2016) — 740 citations
• Fast Face-Swap Using Convolutional Neural Networks (2016) — 454 citations
• Is the deconvolution layer the same as a convolutional layer? (2016) — 148 citations