Karan Desai

Computer Vision and Pattern Recognition · 2019–2021

A researcher in the Science corpus: 4 papers; trusts 1,097 researchers and is trusted by 43 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 204 citations into it; #15,436 of 21,575 by trust here, #5,464 by citations
• Artificial Intelligence — 195 citations into it; #20,754 of 35,345 by trust here, #6,956 by citations
• Representation & Self-Supervised Learning — 62 citations into it; #855 of 3,145 by trust here, #1,191 by citations
• Multimodal Learning — 61 citations into it; #256 of 1,211 by trust here, #456 by citations
• Evaluation & Benchmarks — 59 citations into it; #2,273 of 3,147 by trust here, #1,103 by citations
• Natural Language Processing — 55 citations into it
• Reinforcement Learning — 26 citations into it; #1,995 of 2,242 by trust here, #1,932 by citations
• Optimization & Training — 21 citations into it

Whom Karan Desai trusts overall

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

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

Who trusts Karan Desai overall

1. Jianfeng Wang
2. Jiasen Lu
3. Axel Sauer
4. Hieu Pham
5. Xiaowei Hu
6. Ajay Jain
7. Jianwei Yang
8. Zhiyuan Fang
9. Mandela Patrick
10. Yiwu Zhong

Papers from Karan Desai's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
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

• nocaps: novel object captioning at scale (2019) — 658 citations
• RedCaps: web-curated image-text data created by the people, for the people (2021) — 213 citations
• Continual Reinforcement Learning in 3D Non-stationary Environments (2019) — 49 citations
• VirTex: Learning Visual Representations from Textual Annotations (2020) — 484 citations