Paul Vernaza

Computer Vision and Pattern Recognition · 2012–2018

A researcher in the Science corpus: 5 papers; trusts 649 researchers and is trusted by 24 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 83 citations into it; #7,616 of 21,575 by trust here, #5,565 by citations
• Artificial Intelligence — 70 citations into it; #12,967 of 35,345 by trust here, #7,728 by citations
• Reinforcement Learning — 20 citations into it; #1,573 of 2,242 by trust here, #992 by citations
• Generative Models — 17 citations into it
• Model Architectures — 11 citations into it
• Probabilistic & Bayesian Methods — 10 citations into it; #1,209 of 1,525 by trust here, #1,390 by citations
• Optimization & Training — 7 citations into it
• Aerospace Engineering — 5 citations into it

Whom Paul Vernaza trusts overall

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

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

Who trusts Paul Vernaza overall

1. Jiwoon Ahn
2. Nicholas Rhinehart
3. Suha Kwak
4. Henrik Kretzschmar
5. Meng Tang
6. Dong Zhang
7. Kris M. Kitani
8. Sunghyun Cho
9. Nachiket Deo
10. Sergio Casas

Papers from Paul Vernaza's perspective

Ordered by how strongly the researchers Paul Vernaza 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. Long Short-Term Memory
5. ImageNet: A large-scale hierarchical image database
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

• DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents (2017) — 1,103 citations
• Deep Network Flow for Multi-object Tracking (2017) — 213 citations
• Learning Random-Walk Label Propagation for Weakly-Supervised Semantic Segmentation (2017) — 279 citations
• r2p2: A ReparameteRized Pushforward Policy for Diverse, Precise Generative Path Forecasting (2018) — 257 citations
• Efficient high dimensional maximum entropy modeling via symmetric partition functions (2012) — 23 citations