Pavel Tokmakov

Computer Vision and Pattern Recognition · 2016–2023

A researcher in the Science corpus: 4 papers; trusts 899 researchers and is trusted by 165 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 128 citations into it; #2,770 of 21,575 by trust here, #4,690 by citations
• Artificial Intelligence — 48 citations into it; #26,018 of 35,345 by trust here, #22,463 by citations
• Computational Mechanics — 23 citations into it; #9,854 of 10,001 by trust here, #2,509 by citations
• Computer Graphics and Computer-Aided Design — 21 citations into it; #1,550 of 1,584 by trust here, #526 by citations
• Representation & Self-Supervised Learning — 20 citations into it; #2,454 of 3,145 by trust here, #2,488 by citations
• Generative Models — 17 citations into it
• Model Architectures — 15 citations into it
• Evaluation & Benchmarks — 14 citations into it

Whom Pavel Tokmakov trusts overall

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

1. Alex Graves
2. Thomas Brox
3. Geoffrey E. Hinton
4. Karen Simonyan
5. Kaiming He
6. Alex Krizhevsky
7. Jitendra Malik
8. Ross B. Girshick
9. Yoshua Bengio
10. Yann LeCun

Who trusts Pavel Tokmakov overall

1. Wenguan Wang
2. Xiankai Lu
3. Linjie Yang
4. Mennatullah Siam
5. Ning Xu
6. Jianbing Shen
7. Carl Doersch
8. Siyang Li
9. Hongmei Song
10. Paul Voigtlaender

Papers from Pavel Tokmakov's perspective

Ordered by how strongly the researchers Pavel Tokmakov 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. Long Short-Term Memory
6. Attention is All you Need (Neural Information Processing Systems)
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

• Learning Motion Patterns in Videos (2016) — 278 citations
• Zero-1-to-3: Zero-shot One Image to 3D Object (2023) — 1,787 citations
• Learning Video Object Segmentation with Visual Memory (2017) — 342 citations
• Learning Compositional Representations for Few-Shot Recognition (2018) — 134 citations