Stefan Roth
Computer Vision and Pattern Recognition · International Journal of Computer Vision · 2001–2020
A researcher in the Science corpus: 36 papers; trusts 3,135 researchers and is trusted by 14,780 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 783 citations into it; #152 of 21,973 by trust here, #209 by citations
- Artificial Intelligence — 259 citations into it; #6,688 of 36,961 by trust here, #9,549 by citations
- Evaluation & Benchmarks — 93 citations into it; #96 of 3,155 by trust here, #67 by citations
- Aerospace Engineering — 89 citations into it
- Media Technology — 88 citations into it; #102 of 3,630 by trust here, #370 by citations
- Probabilistic & Bayesian Methods — 46 citations into it; #576 of 1,526 by trust here, #991 by citations
- Model Architectures — 41 citations into it
- Computational Mechanics — 39 citations into it; #594 of 10,021 by trust here, #1,877 by citations
Whom Stefan Roth trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Diederik P. Kingma
- Kaiming He
- Alex Krizhevsky
- Yann LeCun
- Ross B. Girshick
- Yoshua Bengio
- Pedro F. Felzenszwalb
- Karen Simonyan
- Ilya Sutskever
Who trusts Stefan Roth overall
- Kai Zhang
- Luc Van Gool
- Deqing Sun
- Wangmeng Zuo
- Bernt Schiele
- Jitendra Malik
- Michael J. Black
- Julien Mairal
- Lei Zhang
- Yoshua Bengio
Papers from Stefan Roth's perspective
Ordered by how strongly the researchers Stefan Roth 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
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- 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
- The Cityscapes Dataset for Semantic Urban Scene Understanding (2016) — 13,806 citations
- Playing for Data: Ground Truth from Computer Games (2016) — 2,267 citations
- A Database and Evaluation Methodology for Optical Flow (2007) — 2,924 citations
- Pictorial structures revisited: People detection and articulated pose estimation (2009) — 942 citations
- Fields of Experts: a framework for learning image priors (2005) — 1,236 citations
- MOT16: A Benchmark for Multi-Object Tracking (2016) — 2,130 citations
- Fields of Experts (2009) — 876 citations
- MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking (2015) — 870 citations
- Monocular 3D pose estimation and tracking by detection (2010) — 590 citations
- People-tracking-by-detection and people-detection-by-tracking (2008) — 1,005 citations
- Secrets of optical flow estimation and their principles (2010) — 1,631 citations
- UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss (2017) — 637 citations
- Shrinkage Fields for Effective Image Restoration (2014) — 555 citations
- A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind Them (2013) — 693 citations
- Learning Optical Flow (2008) — 302 citations
- The Cityscapes Dataset (2015) — 399 citations
- Discrete-continuous optimization for multi-target tracking (2012) — 372 citations
- Piecewise Rigid Scene Flow (2013) — 244 citations
- Benchmarking Denoising Algorithms with Real Photographs (2017) — 693 citations
- Learning People Detectors for Tracking in Crowded Scenes (2013) — 96 citations