Stephen Lin
Computer Vision and Pattern Recognition · ACM Transactions on Graphics · 2007–2021
A researcher in the Science corpus: 22 papers; trusts 2,744 researchers and is trusted by 3,787 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 712 citations into it; #795 of 21,973 by trust here, #441 by citations
- Artificial Intelligence — 407 citations into it; #1,705 of 36,961 by trust here, #846 by citations
- Model Architectures — 125 citations into it; #159 of 2,288 by trust here, #97 by citations
- Representation & Self-Supervised Learning — 107 citations into it; #1,776 of 3,156 by trust here, #742 by citations
- Evaluation & Benchmarks — 63 citations into it
- Media Technology — 46 citations into it; #594 of 3,630 by trust here, #838 by citations
- Optimization & Training — 40 citations into it
- Generative Models — 36 citations into it
Whom Stephen Lin trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Ross B. Girshick
- Geoffrey E. Hinton
- Alex Krizhevsky
- Diederik P. Kingma
- Yoshua Bengio
- Yann LeCun
- Karen Simonyan
- Ilya Sutskever
- Shaoqing Ren
Who trusts Stephen Lin overall
- Syed Waqas Zamir
- Ze Liu
- Jianwei Yang
- Xingyi Zhou
- Han Hu
- Xizhou Zhu
- Zheng Zhang
- Dacheng Tao
- Wenhai Wang
- Salman Hameed Khan
Papers from Stephen Lin's perspective
Ordered by how strongly the researchers Stephen Lin trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- 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
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (2021) — 33,967 citations
- Deformable ConvNets V2: More Deformable, Better Results (2018) — 2,639 citations
- Local Relation Networks for Image Recognition (2019) — 564 citations
- Video Swin Transformer (2021) — 2,180 citations
- GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond (2019) — 1,934 citations
- RepPoints: Point Set Representation for Object Detection (2019) — 1,092 citations
- Graph Embedding and Extensions: A General Framework for Dimensionality Reduction (2007) — 2,974 citations
- 3D shape regression for real-time facial animation (2013) — 379 citations
- An Empirical Study of Spatial Attention Mechanisms in Deep Networks (2019) — 543 citations
- Semantic colorization with internet images (2011) — 268 citations
- Distilling Localization for Self-Supervised Representation Learning (2020) — 59 citations
- A High-Quality Denoising Dataset for Smartphone Cameras (2018) — 988 citations
- What makes instance discrimination good for transfer learning? (2020) — 183 citations
- Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning (2020) — 477 citations
- RepPoints V2: Verification Meets Regression for Object Detection (2020) — 134 citations
- Super resolution using edge prior and single image detail synthesis (2010) — 345 citations
- Deep Metric Transfer for Label Propagation with Limited Annotated Data (2018) — 68 citations
- Disentangled Non-Local Neural Networks (2020) — 378 citations
- Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation (2020) — 103 citations
- Exposure (2017) — 401 citations