Michael Cogswell

Computer Vision and Pattern Recognition · 2014–2018

A researcher in the Science corpus: 9 papers; trusts 754 researchers and is trusted by 940 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 153 citations into it; #1,429 of 21,575 by trust here, #706 by citations
• Artificial Intelligence — 113 citations into it; #2,884 of 35,345 by trust here, #989 by citations
• Natural Language Processing — 50 citations into it; #5,657 of 5,688 by trust here, #2,333 by citations
• Evaluation & Benchmarks — 32 citations into it
• Multimodal Learning — 32 citations into it
• Model Architectures — 25 citations into it
• Representation & Self-Supervised Learning — 19 citations into it
• Safety, Robustness & Interpretability — 15 citations into it; #316 of 2,251 by trust here, #54 by citations

Whom Michael Cogswell trusts overall

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

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

Who trusts Michael Cogswell overall

1. Rahaf Aljundi
2. Liang-Chieh Chen
3. Quanshi Zhang
4. Yixin Liu
5. José Manuel Álvarez
6. Chunhua Shen
7. George Papandreou
8. Alexander Gerhard Schwing
9. Iasonas Kokkinos
10. Andrea Vedaldi

Papers from Michael Cogswell's perspective

Ordered by how strongly the researchers Michael Cogswell 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. Long Short-Term Memory
5. Attention is All you Need (Neural Information Processing Systems)
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
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

• Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization (2016) — 28,183 citations
• Reducing Overfitting in Deep Networks by Decorrelating Representations (2015) — 461 citations
• Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models (2016) — 657 citations
• Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles (2016) — 199 citations
• Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization (2016) — 1,698 citations
• Diverse Beam Search for Improved Description of Complex Scenes (2018) — 289 citations
• Grad-CAM: Why did you say that? (2016) — 616 citations
• Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks (2015) — 343 citations
• Combining the Best of Graphical Models and ConvNets for Semantic Segmentation (2014) — 16 citations