Vincent Dumoulin
Computer Vision and Pattern Recognition · 2013–2021
A researcher in the Science corpus: 19 papers; trusts 1,676 researchers and is trusted by 9,793 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 370 citations into it; #299 of 21,973 by trust here, #246 by citations
- Artificial Intelligence — 349 citations into it; #491 of 36,961 by trust here, #376 by citations
- Generative Models — 132 citations into it; #75 of 1,963 by trust here, #47 by citations
- Representation & Self-Supervised Learning — 75 citations into it; #366 of 3,156 by trust here, #581 by citations
- Model Architectures — 55 citations into it; #486 of 2,288 by trust here, #209 by citations
- Optimization & Training — 50 citations into it; #226 of 2,605 by trust here, #108 by citations
- Reinforcement Learning — 49 citations into it
- Evaluation & Benchmarks — 41 citations into it
Whom Vincent Dumoulin trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Diederik P. Kingma
- Yoshua Bengio
- Yann LeCun
- Kaiming He
- Ilya Sutskever
- Karen Simonyan
- Matthew D. Zeiler
- Alex Graves
Who trusts Vincent Dumoulin overall
- Yoshua Bengio
- Fei Ye
- Chunyuan Li
- Trevor Darrell
- Jeff Donahue
- Jun-Yan Zhu
- Andrea Vedaldi
- Sergey Levine
- Zhe Gan
- Dacheng Tao
Papers from Vincent Dumoulin's perspective
Ordered by how strongly the researchers Vincent Dumoulin trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- 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
- Improved Training of Wasserstein GANs (2017) — 11,031 citations
- FiLM: Visual Reasoning with a General Conditioning Layer (2017) — 4,130 citations
- Adversarially Learned Inference (2016) — 1,346 citations
- A Learned Representation For Artistic Style (2016) — 1,271 citations
- Theano: A Python framework for fast computation of mathematical expressions (2016) — 2,380 citations
- Deconvolution and Checkerboard Artifacts (2016) — 1,756 citations
- Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples (2019) — 701 citations
- Pylearn2: a machine learning research library (2013) — 305 citations
- Blocks and Fuel: Frameworks for deep learning (2015) — 188 citations
- Exploring the structure of a real-time, arbitrary neural artistic stylization network (2017) — 312 citations
- Feature-wise transformations (2018) — 229 citations
- Learning Visual Reasoning Without Strong Priors (2017) — 65 citations
- Discriminative Regularization for Generative Models (2016) — 67 citations
- A guide to convolution arithmetic for deep learning (2016) — 1,697 citations
- The Hanabi Challenge: A New Frontier for AI Research (2019) — 429 citations
- Generative Adversarial Networks: An Overview (2017) — 3,805 citations
- Learning a Universal Template for Few-shot Dataset Generalization (2021) — 117 citations
- An Effective Anti-Aliasing Approach for Residual Networks (2020) — 36 citations
- Blocks and Fuel (2015)