Pengfei Xu

Computer Vision and Pattern Recognition · with Wang · 2016–2020

A researcher in the Science corpus: 4 papers; trusts 171 researchers and is trusted by 2 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 101 citations into it; #19,009 of 21,575 by trust here, #11,950 by citations
• Artificial Intelligence — 86 citations into it; #31,131 of 35,345 by trust here, #17,776 by citations
• Efficiency & Compression — 62 citations into it
• Model Architectures — 33 citations into it
• Optimization & Training — 21 citations into it

Whom Pengfei Xu trusts overall

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

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

Who trusts Pengfei Xu overall

1. William Grant Hatcher

Papers from Pengfei Xu's perspective

Ordered by how strongly the researchers Pengfei Xu 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. Long Short-Term Memory
4. ImageNet: A large-scale hierarchical image database
5. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
6. Gradient-based learning applied to document recognition
7. Attention is All you Need (Neural Information Processing Systems)
8. Going deeper with convolutions
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• Dual Dynamic Inference: Enabling More Efficient, Adaptive, and Controllable Deep Inference (2019) — 93 citations
• Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference (2020) — 49 citations
• Drawing early-bird tickets: Towards more efficient training of deep networks (2019) — 285 citations
• Benchmarking State-of-the-Art Deep Learning Software Tools (2016) — 343 citations