Sunghyun Cho

Computer Vision and Pattern Recognition · with Lee · 2009–2020

A researcher in the Science corpus: 6 papers; trusts 927 researchers and is trusted by 331 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 166 citations into it; #2,177 of 21,575 by trust here, #6,031 by citations
• Media Technology — 80 citations into it; #184 of 3,621 by trust here, #620 by citations
• Artificial Intelligence — 27 citations into it
• Evaluation & Benchmarks — 19 citations into it
• Generative Models — 17 citations into it
• Computational Mechanics — 11 citations into it
• Model Architectures — 8 citations into it
• Atomic and Molecular Physics, and Optics — 6 citations into it

Whom Sunghyun Cho trusts overall

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

1. Kaiming He
2. Anat Levin
3. Geoffrey E. Hinton
4. Alex Krizhevsky
5. Ross B. Girshick
6. Diederik P. Kingma
7. Rob Fergus
8. Karen Simonyan
9. Yann LeCun
10. Yoshua Bengio

Who trusts Sunghyun Cho overall

1. Jin-shan Pan
2. Michael Hirsch
3. Ayan Chakrabarti
4. Li Xu
5. Tomer Michaeli
6. Ming-Hsuan Yang
7. Wei-Sheng Lai
8. Zhe Hu
9. Jaesung Rim
10. Tae Hyun Kim

Papers from Sunghyun Cho's perspective

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

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

Their papers

• Fast motion deblurring (2009) — 1,265 citations
• Edge-based blur kernel estimation using patch priors (2013) — 496 citations
• Weakly Supervised Learning of Instance Segmentation With Inter-Pixel Relations (2019) — 654 citations
• SRFeat: Single Image Super-Resolution with Feature Discrimination (2018) — 187 citations
• A no-reference metric for evaluating the quality of motion deblurring (2013) — 114 citations
• Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms (2020) — 492 citations