Weiyang Liu
Computer Vision and Pattern Recognition · 2016–2022
A researcher in the Science corpus: 15 papers; trusts 1,759 researchers and is trusted by 389 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 435 citations into it; #2,648 of 21,973 by trust here, #1,867 by citations
- Artificial Intelligence — 371 citations into it; #9,060 of 36,961 by trust here, #5,171 by citations
- Representation & Self-Supervised Learning — 131 citations into it
- Optimization & Training — 91 citations into it; #1,399 of 2,605 by trust here, #759 by citations
- Signal Processing — 86 citations into it; #4,633 of 7,592 by trust here, #530 by citations
- Model Architectures — 85 citations into it; #1,081 of 2,288 by trust here, #793 by citations
- Meta & Continual Learning — 41 citations into it
- Evaluation & Benchmarks — 38 citations into it
Whom Weiyang Liu trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Krizhevsky
- Geoffrey E. Hinton
- Yann LeCun
- Karen Simonyan
- Yoshua Bengio
- X. Zhang
- Ilya Sutskever
- Christian Szegedy
- Ross B. Girshick
Who trusts Weiyang Liu overall
- Rongmei Lin
- L. Yu
- Feng Wang
- Zhen Liu
- Yandong Wen
- Jiankang Deng
- Mei Wang
- Ying Zhang
- Weihong Deng
- Tianyang Hu
Papers from Weiyang Liu's perspective
Ordered by how strongly the researchers Weiyang Liu trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- SphereFace: Deep Hypersphere Embedding for Face Recognition (2017) — 3,098 citations
- Large-Margin Softmax Loss for Convolutional Neural Networks (2016) — 1,593 citations
- Additive Margin Softmax for Face Verification (2018) — 1,380 citations
- Angular Visual Hardness (2019) — 60 citations
- Deep Hyperspherical Learning (2017) — 153 citations
- Iterative Learning with Open-set Noisy Labels (2018) — 357 citations
- Decoupled Networks (2018) — 87 citations
- Regularizing Neural Networks via Minimizing Hyperspherical Energy (2019) — 48 citations
- Pre-training Molecular Graph Representation with 3D Geometry (2021) — 466 citations
- Continual Learning by Modeling Intra-Class Variation (2022) — 19 citations
- Learning with Hyperspherical Uniformity (2021) — 50 citations
- Provable Lifelong Learning of Representations (2021) — 20 citations
- SphereFace Revived: Unifying Hyperspherical Face Recognition (2021) — 60 citations
- Orthogonal Over-Parameterized Training (2020) — 55 citations
- Learning towards Minimum Hyperspherical Energy (2018) — 172 citations