Mathieu Salzmann
Computer Vision and Pattern Recognition · 2010–2020
A researcher in the Science corpus: 32 papers; trusts 3,471 researchers and is trusted by 2,923 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 745 citations into it; #962 of 21,973 by trust here, #1,254 by citations
- Artificial Intelligence — 441 citations into it; #2,175 of 36,961 by trust here, #2,902 by citations
- Representation & Self-Supervised Learning — 102 citations into it; #734 of 3,156 by trust here, #1,045 by citations
- Model Architectures — 89 citations into it; #313 of 2,288 by trust here, #1,043 by citations
- Optimization & Training — 68 citations into it
- Aerospace Engineering — 63 citations into it; #6,098 of 6,431 by trust here, #2,373 by citations
- Computational Mechanics — 57 citations into it; #5,661 of 10,021 by trust here, #3,038 by citations
- Efficiency & Compression — 57 citations into it
Whom Mathieu Salzmann trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Kaiming He
- Alex Krizhevsky
- Diederik P. Kingma
- Ross B. Girshick
- Yann LeCun
- Yoshua Bengio
- Karen Simonyan
- Andrew Zisserman
- Ilya Sutskever
Who trusts Mathieu Salzmann overall
- Sebastian Ruder
- Chang Xu
- Dacheng Tao
- Zhiwu Huang
- Gabriella Csurka
- Jacopo Cavazza
- Luc Van Gool
- Yi Yang
- Trevor Darrell
- Yu Cheng
Papers from Mathieu Salzmann's perspective
Ordered by how strongly the researchers Mathieu Salzmann trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- 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
- Boundary-Aware Instance Segmentation (2016) — 160 citations
- Unsupervised Domain Adaptation by Domain Invariant Projection (2013) — 462 citations
- Learning cross-modality similarity for multinomial data (2011) — 203 citations
- Structured Prediction of 3D Human Pose with Deep Neural Networks (2016) — 280 citations
- Discrete-Continuous Depth Estimation from a Single Image (2014) — 380 citations
- Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation (2016) — 260 citations
- Evaluating the Search Phase of Neural Architecture Search (2019) — 375 citations
- Beyond Sharing Weights for Deep Domain Adaptation (2016) — 473 citations
- Learning to Find Good Correspondences (2017) — 529 citations
- Encouraging LSTMs to Anticipate Actions Very Early (2017) — 181 citations
- Learning the Number of Neurons in Deep Networks (2016) — 427 citations
- Shape-aware Instance Segmentation (2016) — 31 citations
- Learning to Recognize Objects from Unseen Modalities (2010) — 29 citations
- Learning Monocular 3D Human Pose Estimation from Multi-view Images (2018) — 258 citations
- Segmentation-Driven 6D Object Pose Estimation (2018) — 318 citations
- Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices (2013) — 312 citations
- Effective Use of Synthetic Data for Urban Scene Semantic Segmentation (2018) — 164 citations
- Learning Trajectory Dependencies for Human Motion Prediction (2019) — 559 citations
- Domain Adaptation on the Statistical Manifold (2014) — 140 citations
- Compression-aware Training of Deep Networks (2017) — 182 citations