Jonathan P. Dandois
Environmental Engineering · 2013–2015
A researcher in the Science corpus: 2 papers; trusts 25 researchers and is trusted by 20 researchers here, as inferred from the citation graph.
Subfields
- Environmental Engineering — 25 citations into it; #817 of 5,479 by trust here, #2,178 by citations
- Ecology — 20 citations into it; #1,289 of 10,717 by trust here, #5,833 by citations
- Geology — 14 citations into it
- Computer Vision and Pattern Recognition — 12 citations into it
- Aerospace Engineering — 9 citations into it
- Nature and Landscape Conservation — 8 citations into it
- Ecological Modeling — 7 citations into it
- Global and Planetary Change — 5 citations into it; #1,710 of 10,225 by trust here, #5,940 by citations
Whom Jonathan P. Dandois trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- David G. Lowe
- Gregory P. Asner
- Steve Harwin
- Noah Snavely
- Arko Lucieer
- J. Jenkins
- Yasutaka Furukawa
- Peter J. Rousseeuw
- Jeffrey Scott Evans
- George Vosselman
Who trusts Jonathan P. Dandois overall
- Dimitrios Stateras
- Michael Alonzo
- M. Nowak
- Stefano Puliti
- Tetsuji Ota
- Luke Wallace
- Julián Tomastík
- Dionissios P. Kalivas
- Hans-Erik Andersen
- Katarzyna Dziób
Papers from Jonathan P. Dandois's perspective
Ordered by how strongly the researchers Jonathan P. Dandois trusts endorse each paper. Same corpus, a different order for every researcher.
- Distinctive Image Features from Scale-Invariant Keypoints
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- ImageNet Large Scale Visual Recognition Challenge
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Going deeper with convolutions
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)