Takayuki Okatani

Computer Vision and Pattern Recognition · 2018–2019

A researcher in the Science corpus: 6 papers; trusts 1,317 researchers and is trusted by 28 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 210 citations into it; #5,371 of 21,575 by trust here, #7,340 by citations
• Artificial Intelligence — 107 citations into it; #9,636 of 35,345 by trust here, #15,866 by citations
• Multimodal Learning — 43 citations into it
• Media Technology — 36 citations into it; #1,839 of 3,621 by trust here, #1,696 by citations
• Model Architectures — 36 citations into it
• Natural Language Processing — 22 citations into it
• Generative Models — 21 citations into it
• Optimization & Training — 16 citations into it

Whom Takayuki Okatani trusts overall

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

1. Geoffrey E. Hinton
2. Kaiming He
3. Diederik P. Kingma
4. Alex Krizhevsky
5. Yoshua Bengio
6. Ilya Sutskever
7. Yann LeCun
8. Ross B. Girshick
9. Jimmy Ba
10. Alex Graves

Who trusts Takayuki Okatani overall

1. Zhou Yu
2. Masanori Suganuma
3. Van-Quang Nguyen
4. Robik Shrestha
5. Duy-Kien Nguyen
6. Peng Gao
7. Jun Yu
8. Tuong Khanh Long Do
9. Shubham Agarwal
10. Tianwen Qian

Papers from Takayuki Okatani's perspective

Ordered by how strongly the researchers Takayuki Okatani 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. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
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

• Improved Fusion of Visual and Language Representations by Dense Symmetric Co-attention for Visual Question Answering (2018) — 305 citations
• Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps With Accurate Object Boundaries (2018) — 425 citations
• Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search (2018) — 92 citations
• Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration (2019) — 266 citations
• Efficient Attention Mechanism for Handling All the Interactions between Many Inputs with Application to Visual Dialog (2019) — 7 citations
• Deep Structured Energy-Based Image Inpainting (2018) — 16 citations