Xiangyu Zhang
Computer Vision and Pattern Recognition · with Li · 2017–2019
A researcher in the Science corpus: 16 papers; trusts 2,605 researchers and is trusted by 7,380 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 559 citations into it; #432 of 21,973 by trust here, #388 by citations
- Artificial Intelligence — 362 citations into it; #971 of 36,961 by trust here, #1,093 by citations
- Model Architectures — 145 citations into it
- Efficiency & Compression — 105 citations into it; #8 of 1,273 by trust here, #23 by citations
- Evaluation & Benchmarks — 66 citations into it; #1,133 of 3,155 by trust here, #869 by citations
- Optimization & Training — 55 citations into it
- Media Technology — 33 citations into it; #913 of 3,630 by trust here, #308 by citations
- Neural Architecture Search & AutoML — 23 citations into it; #159 of 283 by trust here, #48 by citations
Whom Xiangyu Zhang trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Krizhevsky
- Ross B. Girshick
- Geoffrey E. Hinton
- X. Zhang
- Karen Simonyan
- Christian Szegedy
- Shaoqing Ren
- Yann LeCun
- Ilya Sutskever
Who trusts Xiangyu Zhang overall
- Jiahui Yu
- Liang-Chieh Chen
- Han Cai
- Ji Lin
- Mingxing Tan
- Song Han
- Yukang Chen
- Quoc V. Le
- Kai Han
- Thomas S. Huang
Papers from Xiangyu Zhang's perspective
Ordered by how strongly the researchers Xiangyu Zhang 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
- Attention is All you Need (Neural Information Processing Systems)
- 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
- ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices (2017) — 8,533 citations
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design (2018) — 6,472 citations
- MegDet: A Large Mini-Batch Object Detector (2017) — 336 citations
- Objects365: A Large-Scale, High-Quality Dataset for Object Detection (2019) — 1,074 citations
- Channel Pruning for Accelerating Very Deep Neural Networks (2017) — 2,781 citations
- Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network (2017) — 1,617 citations
- Single Path One-Shot Neural Architecture Search with Uniform Sampling (2019) — 1,036 citations
- CrowdHuman: A Benchmark for Detecting Human in a Crowd (2018) — 866 citations
- Light-Head R-CNN: In Defense of Two-Stage Object Detector (2017) — 393 citations
- DetNet: A Backbone network for Object Detection (2018) — 280 citations
- DetNAS: Neural Architecture Search on Object Detection (2019) — 94 citations
- Meta-SR: A Magnification-Arbitrary Network for Super-Resolution (2019) — 519 citations
- DetNet: Design Backbone for Object Detection (2018) — 228 citations
- MetaAnchor: Learning to Detect Objects with Customized Anchors (2018) — 151 citations
- ExFuse: Enhancing Feature Fusion for Semantic Segmentation (2018) — 323 citations
- MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning (2019) — 640 citations