Xiaodan Song

Computer Vision and Pattern Recognition · 2007–2022

A researcher in the Science corpus: 11 papers; trusts 543 researchers and is trusted by 15 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 228 citations into it; #12,542 of 21,575 by trust here, #2,587 by citations
• Artificial Intelligence — 226 citations into it; #20,072 of 35,345 by trust here, #3,539 by citations
• Model Architectures — 92 citations into it
• Optimization & Training — 87 citations into it
• Efficiency & Compression — 46 citations into it; #752 of 1,264 by trust here, #350 by citations
• Natural Language Processing — 33 citations into it; #4,824 of 5,688 by trust here, #2,172 by citations
• Large Language Models — 19 citations into it; #461 of 799 by trust here, #339 by citations
• Computational Mechanics — 16 citations into it

Whom Xiaodan Song trusts overall

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

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

Who trusts Xiaodan Song overall

1. Charu C. Aggarwal
2. Santo Fortunato
3. E. Kassens-Noor
4. Emre Kıcıman
5. Bruno Gonçalves
6. Albert Bifet
7. Kate Ehrlich
8. Siwei Ma
9. Jianwen Zhang
10. Sitaram Asur

Papers from Xiaodan Song's perspective

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

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

Their papers

• Large Batch Optimization for Deep Learning: Training BERT in 76 minutes (2019) — 1,222 citations
• SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization (2019) — 184 citations
• MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices (2020) — 1,053 citations
• A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation (2021) — 44 citations
• BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models (2020) — 335 citations
• Auto-scaling Vision Transformers without Training (2022) — 28 citations
• Evolutionary spectral clustering by incorporating temporal smoothness (2007) — 413 citations
• Reducing BERT Pre-Training Time from 3 Days to 76 Minutes (2019) — 126 citations
• MobileBERT: Task-Agnostic Compression of BERT by Progressive Knowledge Transfer (2019) — 20 citations
• A Practical Convolutional Neural Network as Loop Filter for Intra Frame (2018) — 42 citations
• Why we twitter: understanding microblogging usage and communities (2007) — 3,211 citations