Boxin Shi

Computer Vision and Pattern Recognition · with Xu · 2010–2020

A researcher in the Science corpus: 12 papers; trusts 600 researchers and is trusted by 1 researcher here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 287 citations into it; #21,520 of 21,575 by trust here, #6,671 by citations
• Artificial Intelligence — 197 citations into it
• Efficiency & Compression — 104 citations into it
• Model Architectures — 47 citations into it
• Generative Models — 45 citations into it
• Computational Mechanics — 44 citations into it
• Optimization & Training — 37 citations into it
• Representation & Self-Supervised Learning — 17 citations into it

Whom Boxin Shi trusts overall

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

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

Who trusts Boxin Shi overall

1. Kai Han

Papers from Boxin Shi's perspective

Ordered by how strongly the researchers Boxin Shi trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Gradient-based learning applied to document recognition
5. ImageNet: A large-scale hierarchical image database
6. Long Short-Term Memory
7. Attention is All you Need (Neural Information Processing Systems)
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• DIST: Rendering Deep Implicit Signed Distance Function With Differentiable Sphere Tracing (2019) — 310 citations
• CARS: Continuous Evolution for Efficient Neural Architecture Search (2019) — 269 citations
• AdderNet: Do We Really Need Multiplications in Deep Learning? (2019) — 236 citations
• Robust Photometric Stereo via Low-Rank Matrix Completion and Recovery (2010) — 344 citations
• Reborn Filters: Pruning Convolutional Neural Networks with Limited Data (2020) — 33 citations
• Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks (2020) — 41 citations
• On Positive-Unlabeled Classification in GAN (2020) — 39 citations
• Frequency Domain Compact 3D Convolutional Neural Networks (2020) — 32 citations
• Distilling portable Generative Adversarial Networks for Image Translation (2020) — 89 citations
• Bringing Giant Neural Networks Down to Earth with Unlabeled Data (2019) — 11 citations
• Data-Free Learning of Student Networks (2019) — 440 citations
• Active Printed Materials for Complex Self-Evolving Deformations (2014) — 502 citations