Tsung-Yi Lin
Computer Vision and Pattern Recognition · 2013–2022
A researcher in the Science corpus: 32 papers; trusts 3,415 researchers and is trusted by 18,753 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 1,180 citations into it; #59 of 21,973 by trust here, #36 by citations
- Artificial Intelligence — 723 citations into it; #383 of 36,961 by trust here, #224 by citations
- Model Architectures — 189 citations into it; #1,247 of 2,288 by trust here, #533 by citations
- Representation & Self-Supervised Learning — 137 citations into it
- Evaluation & Benchmarks — 114 citations into it; #37 of 3,155 by trust here, #17 by citations
- Optimization & Training — 101 citations into it; #1,450 of 2,605 by trust here, #582 by citations
- Multimodal Learning — 77 citations into it; #529 of 1,215 by trust here, #424 by citations
- Aerospace Engineering — 73 citations into it; #2,863 of 6,431 by trust here, #2,251 by citations
Whom Tsung-Yi Lin trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Ross B. Girshick
- Kaiming He
- Alex Krizhevsky
- Geoffrey E. Hinton
- Shaoqing Ren
- Piotr Doll'ar
- Yann LeCun
- Ilya Sutskever
- David G. Lowe
- Diederik P. Kingma
Who trusts Tsung-Yi Lin overall
- Kaiming He
- Ross B. Girshick
- Chunhua Shen
- Liang-Chieh Chen
- Trevor Darrell
- Xinlei Chen
- Abhinav Kumar Gupta
- Xiaogang Wang
- Jitendra Malik
- Yi Yang
Papers from Tsung-Yi Lin's perspective
Ordered by how strongly the researchers Tsung-Yi Lin 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
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- Microsoft COCO: Common Objects in Context (2014) — 54,126 citations
- Feature Pyramid Networks for Object Detection (2016) — 27,484 citations
- Focal Loss for Dense Object Detection (2017) — 32,959 citations
- Microsoft COCO Captions: Data Collection and Evaluation Server (2015) — 2,946 citations
- Learning to Refine Object Segments (2016) — 857 citations
- Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation (2020) — 1,320 citations
- Open-vocabulary Object Detection via Vision and Language Knowledge Distillation (2021) — 1,353 citations
- Bottleneck Transformers for Visual Recognition (2021) — 1,200 citations
- A MultiPath Network for Object Detection (2016) — 218 citations
- NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection (2019) — 1,781 citations
- DropBlock: A regularization method for convolutional networks (2018) — 1,053 citations
- Class-Balanced Loss Based on Effective Number of Samples (2019) — 3,183 citations
- Revisiting ResNets: Improved Training and Scaling Strategies (2021) — 365 citations
- Focal Loss for Dense Object Detection (2017) — 3,418 citations
- Magic3D: High-Resolution Text-to-3D Content Creation (2022) — 1,645 citations
- Learning deep representations for ground-to-aerial geolocalization (2015) — 418 citations
- A Unified Sequence Interface for Vision Tasks (2022) — 193 citations
- Open-Vocabulary Image Segmentation (2021) — 97 citations
- Zero-Shot Detection via Vision and Language Knowledge Distillation (2021) — 90 citations
- Learning Data Augmentation Strategies for Object Detection (2019) — 607 citations