Yonglong Tian
Computer Vision and Pattern Recognition · 2014–2023
A researcher in the Science corpus: 17 papers; trusts 2,854 researchers and is trusted by 3,664 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 710 citations into it; #818 of 21,973 by trust here, #971 by citations
- Artificial Intelligence — 522 citations into it; #4,907 of 36,961 by trust here, #2,482 by citations
- Representation & Self-Supervised Learning — 265 citations into it; #196 of 3,156 by trust here, #141 by citations
- Evaluation & Benchmarks — 63 citations into it
- Model Architectures — 56 citations into it
- Optimization & Training — 53 citations into it
- Generative Models — 42 citations into it
- Signal Processing — 42 citations into it; #488 of 7,592 by trust here, #286 by citations
Whom Yonglong Tian trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Geoffrey E. Hinton
- Alex Krizhevsky
- Ross B. Girshick
- Diederik P. Kingma
- Yoshua Bengio
- Ilya Sutskever
- Yann LeCun
- Karen Simonyan
- Andrew Zisserman
Who trusts Yonglong Tian overall
- Xiaodan Liang
- Ishan Misra
- Xinlong Wang
- Kaiming He
- Chengxu Zhuang
- Jiaming Song
- Phillip Isola
- Bingchen Zhao
- Chunhua Shen
- Spyros Gidaris
Papers from Yonglong Tian's perspective
Ordered by how strongly the researchers Yonglong Tian 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)
- 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
- Contrastive Multiview Coding (2019) — 2,769 citations
- Supervised Contrastive Learning (2020) — 6,562 citations
- Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need? (2020) — 1,074 citations
- Contrastive Representation Distillation (2019) — 1,372 citations
- DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection (2014) — 165 citations
- Deep Learning Strong Parts for Pedestrian Detection (2015) — 515 citations
- DeepID-Net: Deformable deep convolutional neural networks for object detection (2014) — 450 citations
- Representation Learning on Graphs with Jumping Knowledge Networks (2018) — 2,401 citations
- Divide and Contrast: Self-supervised Learning from Uncurated Data (2021) — 113 citations
- Pedestrian detection aided by deep learning semantic tasks (2014) — 440 citations
- Through-Wall Human Pose Estimation Using Radio Signals (2018) — 675 citations
- Learning to Infer and Execute 3D Shape Programs (2019) — 162 citations
- RF-based 3D skeletons (2018) — 408 citations
- What makes for good views for contrastive learning (2020) — 1,584 citations
- Improving CLIP Training with Language Rewrites (2023) — 296 citations
- ProbGAN: Towards Probabilistic GAN with Theoretical Guarantees (2018) — 32 citations
- DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks (2017) — 134 citations