Saining Xie
Computer Vision and Pattern Recognition · 2014–2025
A researcher in the Science corpus: 35 papers; trusts 3,825 researchers and is trusted by 16,274 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 1,348 citations into it; #120 of 21,973 by trust here, #124 by citations
- Artificial Intelligence — 1,052 citations into it; #283 of 36,961 by trust here, #226 by citations
- Model Architectures — 265 citations into it; #108 of 2,288 by trust here, #89 by citations
- Representation & Self-Supervised Learning — 246 citations into it; #144 of 3,156 by trust here, #81 by citations
- Evaluation & Benchmarks — 172 citations into it
- Optimization & Training — 149 citations into it
- Multimodal Learning — 115 citations into it
- Large Language Models — 110 citations into it
Whom Saining Xie trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Krizhevsky
- Geoffrey E. Hinton
- Ross B. Girshick
- Yoshua Bengio
- Yann LeCun
- Ilya Sutskever
- Christian Szegedy
- Diederik P. Kingma
- Karen Simonyan
Who trusts Saining Xie overall
- Kaiming He
- Christoph Feichtenhofer
- Ross B. Girshick
- Iasonas Kokkinos
- Alan L. Yuille
- Trevor Darrell
- Abhinav Kumar Gupta
- Xinlei Chen
- Yoshua Bengio
- Luc Van Gool
Papers from Saining Xie's perspective
Ordered by how strongly the researchers Saining Xie trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- 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
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Aggregated Residual Transformations for Deep Neural Networks (2016) — 11,783 citations
- Momentum Contrast for Unsupervised Visual Representation Learning (2019) — 15,360 citations
- Deeply-Supervised Nets (2014) — 2,494 citations
- Holistically-Nested Edge Detection (2015) — 3,918 citations
- Masked Autoencoders Are Scalable Vision Learners (2021) — 12,173 citations
- An Empirical Study of Training Self-Supervised Vision Transformers (2021) — 2,433 citations
- Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification (2017) — 1,502 citations
- A ConvNet for the 2020s (2022) — 8,792 citations
- Rethinking Spatiotemporal Feature Learning For Video Understanding (2017) — 265 citations
- SLIP: Self-supervision meets Language-Image Pre-training (2021) — 639 citations
- Masked Feature Prediction for Self-Supervised Visual Pre-Training (2021) — 867 citations
- Scalable Diffusion Models with Transformers (2022) — 6,663 citations
- Exploring Randomly Wired Neural Networks for Image Recognition (2019) — 389 citations
- Decoupling Representation and Classifier for Long-Tailed Recognition (2019) — 1,567 citations
- Benchmarking Detection Transfer Learning with Vision Transformers (2021) — 211 citations
- On Network Design Spaces for Visual Recognition (2019) — 150 citations
- PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding (2020) — 838 citations
- Hyper-class augmented and regularized deep learning for fine-grained image classification (2015) — 177 citations
- Top-Down Learning for Structured Labeling with Convolutional Pseudoprior (2015) — 39 citations
- ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders (2023) — 1,840 citations