Shanghang Zhang

Artificial Intelligence · AAAI Conference on Artificial Intelligence · 2017–2023

A researcher in the Science corpus: 14 papers; trusts 1,073 researchers and is trusted by 10 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 440 citations into it; #25,502 of 35,345 by trust here, #12,244 by citations
• Computer Vision and Pattern Recognition — 414 citations into it; #11,524 of 21,575 by trust here, #8,612 by citations
• Representation & Self-Supervised Learning — 182 citations into it
• Model Architectures — 64 citations into it
• Radiology, Nuclear Medicine and Imaging — 63 citations into it; #1,867 of 3,265 by trust here, #2,073 by citations
• Evaluation & Benchmarks — 42 citations into it
• Optimization & Training — 39 citations into it
• Meta & Continual Learning — 35 citations into it

Whom Shanghang Zhang trusts overall

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

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

Who trusts Shanghang Zhang overall

1. Luca Ciampi
2. Vishwanath A. Sindagi
3. Corey Snyder
4. Tian Zhou
5. Haixu Wu
6. Carlos Santiago
7. Yixiong Zou
8. Abhimanyu Das
9. Gerald Woo
10. Vishal M. Patel

Papers from Shanghang Zhang's perspective

Ordered by how strongly the researchers Shanghang Zhang 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. Long Short-Term Memory
5. ImageNet: A large-scale hierarchical image database
6. Attention is All you Need (Neural Information Processing Systems)
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. Going deeper with convolutions

Their papers

• Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models (2022) — 229 citations
• Instance Adaptive Self-Training for Unsupervised Domain Adaptation (2020) — 349 citations
• Delving Deep into the Generalization of Vision Transformers under Distribution Shifts (2021) — 138 citations
• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting (2020) — 8,143 citations
• ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation (2023) — 80 citations
• Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation (2022) — 98 citations
• Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting (2022) — 383 citations
• Self-Supervised Pretraining Improves Self-Supervised Pretraining (2021) — 137 citations
• Revisiting Mid-Level Patterns for Cross-Domain Few-Shot Recognition (2020) — 19 citations
• Compositional Few-Shot Recognition with Primitive Discovery and Enhancing (2020) — 33 citations
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation (2020) — 338 citations
• Adversarial Multiple Source Domain Adaptation (2018) — 619 citations
• Topology adaptive graph convolutional networks (2017) — 392 citations
• Understanding Traffic Density from Large-Scale Web Camera Data (2017) — 145 citations