Matthew B. Blaschko
Computer Vision and Pattern Recognition · 2001–2020
A researcher in the Science corpus: 23 papers; trusts 1,881 researchers and is trusted by 6,606 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 302 citations into it; #495 of 21,973 by trust here, #1,094 by citations
- Artificial Intelligence — 213 citations into it; #1,624 of 36,961 by trust here, #2,777 by citations
- Statistics and Probability — 66 citations into it; #3,125 of 13,188 by trust here, #4,822 by citations
- Evaluation & Benchmarks — 40 citations into it
- Radiology, Nuclear Medicine and Imaging — 39 citations into it; #1,534 of 3,295 by trust here, #2,625 by citations
- Statistical Learning Theory — 33 citations into it; #746 of 1,040 by trust here, #922 by citations
- Representation & Self-Supervised Learning — 33 citations into it; #960 of 3,156 by trust here, #1,022 by citations
- Optimization & Training — 32 citations into it; #559 of 2,605 by trust here, #1,197 by citations
Whom Matthew B. Blaschko trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Andrew Zisserman
- Geoffrey E. Hinton
- David G. Lowe
- Arthur Gretton
- Alex Krizhevsky
- Diederik P. Kingma
- Kaiming He
- Yoshua Bengio
- Yann LeCun
- Ross B. Girshick
Who trusts Matthew B. Blaschko overall
- Andrea Vedaldi
- Sebastian Nowozin
- Christoph H. Lampert
- Rahaf Aljundi
- Vittorio Ferrari
- Piotr Doll'ar
- Andrew Zisserman
- Luc Van Gool
- Maxim Berman
- Bernt Schiele
Papers from Matthew B. Blaschko's perspective
Ordered by how strongly the researchers Matthew B. Blaschko 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)
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- 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
- Fine-Grained Visual Classification of Aircraft (2013) — 3,021 citations
- Beyond sliding windows: Object localization by efficient subwindow search (2008) — 844 citations
- Learning to Localize Objects with Structured Output Regression (2008) — 380 citations
- Efficient Subwindow Search: A Branch and Bound Framework for Object Localization (2009) — 414 citations
- Encoder Based Lifelong Learning (2017) — 348 citations
- Learning a category independent object detection cascade (2011) — 185 citations
- Understanding Objects in Detail with Fine-Grained Attributes (2014) — 119 citations
- Unsupervised Object Discovery: A Comparison (2010) — 221 citations
- A Test of Relative Similarity For Model Selection in Generative Models (2015) — 88 citations
- The Lovasz-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks (2017) — 997 citations
- The Lov´asz-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks
- AOWS: Adaptive and Optimal Network Width Search With Latency Constraints (2020) — 30 citations
- A low variance consistent test of relative dependency (2014) — 8 citations
- B-tests: Low Variance Kernel Two-Sample Tests (2013) — 24 citations
- Scattering Networks for Hybrid Representation Learning (2018) — 99 citations
- Non Maximal Suppression in Cascaded Ranking Models (2013) — 20 citations
- B-test: A Non-parametric, Low Variance Kernel Two-sample Test (2013) — 101 citations
- Optimization for Medical Image Segmentation: Theory and Practice When Evaluating With Dice Score or Jaccard Index (2020) — 353 citations
- Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory and Practice (2019) — 345 citations
- A Discriminatively Trained Fully Connected Conditional Random Field Model for Blood Vessel Segmentation in Fundus Images (2017) — 471 citations