Songyuan Li

Computer Vision and Pattern Recognition · 2020–2021

A researcher in the Science corpus: 2 papers; trusts 309 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 100 citations into it
• Artificial Intelligence — 94 citations into it
• Natural Language Processing — 25 citations into it
• Model Architectures — 20 citations into it
• Optimization & Training — 7 citations into it
• Probabilistic & Bayesian Methods — 7 citations into it

Whom Songyuan Li trusts overall

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

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

Papers from Songyuan Li's perspective

Ordered by how strongly the researchers Songyuan Li 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. Going deeper with convolutions
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• Recent Advances and Trends in Multimodal Deep Learning: A Review (2021) — 71 citations
• Few-Shot Class-Incremental Learning via Feature Space Composition (2020) — 6 citations