Arka Pal

Computer Vision and Pattern Recognition · with Higgins · 2016–2018

A researcher in the Science corpus: 6 papers; trusts 187 researchers and is trusted by 34 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 120 citations into it; #7,847 of 21,575 by trust here, #4,001 by citations
• Artificial Intelligence — 102 citations into it; #18,153 of 35,345 by trust here, #6,193 by citations
• Representation & Self-Supervised Learning — 54 citations into it; #714 of 3,145 by trust here, #211 by citations
• Generative Models — 49 citations into it; #410 of 1,956 by trust here, #160 by citations
• Reinforcement Learning — 40 citations into it; #2,002 of 2,242 by trust here, #861 by citations
• Optimization & Training — 16 citations into it
• Management Science and Operations Research — 12 citations into it
• Probabilistic & Bayesian Methods — 11 citations into it

Whom Arka Pal trusts overall

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

1. Diederik P. Kingma
2. Geoffrey E. Hinton
3. Yoshua Bengio
4. Alex Krizhevsky
5. Max Welling
6. Yann LeCun
7. Ilya Sutskever
8. J. Urgen Schmidhuber
9. Ruslan Salakhutdinov
10. Kaiming He

Who trusts Arka Pal overall

1. Francesco Locatello
2. Fei Ye
3. Irina Higgins
4. Sergey Levine
5. Adrian G. Bors
6. Bernhard Schölkopf
7. Yoshua Bengio
8. Yilun Du
9. Stefan Bauer
10. Loic Matthey

Papers from Arka Pal's perspective

Ordered by how strongly the researchers Arka Pal 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. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. Attention is All you Need (Neural Information Processing Systems)
7. ImageNet: A large-scale hierarchical image database
8. Going deeper with convolutions
9. Learning Multiple Layers of Features from Tiny Images
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• DARLA: Improving Zero-Shot Transfer in Reinforcement Learning (2017) — 447 citations
• Understanding disentangling in β-VAE (2018) — 962 citations
• Early Visual Concept Learning with Unsupervised Deep Learning (2016) — 184 citations
• SCAN: Learning Abstract Hierarchical Compositional Visual Concepts (2017) — 53 citations
• SCAN: Learning Hierarchical Compositional Visual Concepts (2017) — 134 citations
• beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework (2016) — 6,058 citations