James Thewlis

Computer Vision and Pattern Recognition · 2016–2018

A researcher in the Science corpus: 4 papers; trusts 1,028 researchers and is trusted by 8 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 152 citations into it; #9,532 of 21,575 by trust here, #11,286 by citations
• Representation & Self-Supervised Learning — 51 citations into it; #2,236 of 3,145 by trust here, #2,910 by citations
• Artificial Intelligence — 41 citations into it; #28,583 of 35,345 by trust here, #23,077 by citations
• Aerospace Engineering — 21 citations into it
• Evaluation & Benchmarks — 12 citations into it
• Signal Processing — 12 citations into it
• Media Technology — 9 citations into it
• Model Architectures — 9 citations into it

Whom James Thewlis trusts overall

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

1. Yoshua Bengio
2. Ross B. Girshick
3. Geoffrey E. Hinton
4. David G. Lowe
5. Alex Krizhevsky
6. Kaiming He
7. Yann LeCun
8. Karen Simonyan
9. Andrew Zisserman
10. Diederik P. Kingma

Who trusts James Thewlis overall

1. David Novotný
2. Andrea Vedaldi
3. Riza Alp Güler
4. Hakan Bilen
5. Mihir Sahasrabudhe
6. Zhixin Shu
7. Olivia Wiles
8. Pitchaporn Rewatbowornwong
9. Tomas Jakab
10. Samuel Albanie

Papers from James Thewlis's perspective

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

• Fully-trainable deep matching (2016) — 42 citations
• Unsupervised object learning from dense equivariant image labelling (2017) — 26 citations
• Cross Pixel Optical Flow Similarity for Self-Supervised Learning (2018) — 68 citations
• Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings (2017) — 171 citations