Ran Su
Computer Vision and Pattern Recognition · 2018
A researcher in the Science corpus: 3 papers; trusts 6 researchers and is trusted by 0 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 50 citations into it
- Artificial Intelligence — 21 citations into it
- Model Architectures — 8 citations into it
- Optimization & Training — 5 citations into it
Whom Ran Su trusts
Their strongest outbound trust, strongest first, inferred from their citations.
- Thomas Brox (in Computer Vision and Pattern Recognition)
- Olaf Ronneberger (in Computer Vision and Pattern Recognition)
- Philipp Fischer (in Computer Vision and Pattern Recognition)
- Diederik P. Kingma (in Artificial Intelligence)
- William T. Freeman (in Computer Vision and Pattern Recognition)
- Jimmy Ba (in Artificial Intelligence)
Papers from Ran Su's perspective
Ordered by how strongly the researchers Ran Su trusts endorse each paper. Same corpus, a different order for every researcher.
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Fully convolutional networks for semantic segmentation
- U-Net: Convolutional Networks for Biomedical Image Segmentation (International Conference on Medical Image Computing and Computer-Assisted Intervention)
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Gradient-based learning applied to document recognition
- Going deeper with convolutions
Their papers
- RA-UNet: A Hybrid Deep Attention-Aware Network to Extract Liver and Tumor in CT Scans (2018) — 439 citations
- DUNet: A deformable network for retinal vessel segmentation (2018) — 819 citations
- ACPred-FL: a sequence-based predictor using effective feature representation to improve the prediction of anti-cancer peptides (2018) — 384 citations