Shimon Ullman
Computer Vision and Pattern Recognition · 1979–2018
A researcher in the Science corpus: 17 papers; trusts 1,866 researchers and is trusted by 6,602 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 199 citations into it; #493 of 21,973 by trust here, #2,257 by citations
- Artificial Intelligence — 113 citations into it; #3,404 of 36,961 by trust here, #7,482 by citations
- Cognitive Neuroscience — 42 citations into it; #1,755 of 11,026 by trust here, #1,830 by citations
- Multimodal Learning — 32 citations into it
- Natural Language Processing — 26 citations into it
- Aerospace Engineering — 21 citations into it
- Representation & Self-Supervised Learning — 15 citations into it; #849 of 3,156 by trust here, #1,624 by citations
- Evaluation & Benchmarks — 14 citations into it
Whom Shimon Ullman trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- David G. Lowe
- Ross B. Girshick
- Kaiming He
- Karen Simonyan
- Ilya Sutskever
- Yoshua Bengio
- Andrew Zisserman
- Diederik P. Kingma
Who trusts Shimon Ullman overall
- Jitendra Malik
- Trevor Darrell
- Andrew Zisserman
- Thomas Serre
- Antonio Torralba
- Kristen Grauman
- Alan L. Yuille
- Dileep George
- Luc Van Gool
- Doris Y. Tsao
Papers from Shimon Ullman's perspective
Ordered by how strongly the researchers Shimon Ullman 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)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- 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
- Class-Specific, Top-Down Segmentation (2002) — 494 citations
- Cross-generalization: learning novel classes from a single example by feature replacement (2005) — 220 citations
- Combining Top-Down and Bottom-Up Segmentation (2004) — 354 citations
- Uncovering shared structures in multiclass classification (2007) — 356 citations
- Human Pose Estimation Using Deep Consensus Voting (2016) — 169 citations
- Using Linking Features in Learning Non-parametric Part Models (2012) — 53 citations
- Atoms of recognition in human and computer vision (2016) — 169 citations
- View-Invariant Recognition Using Corresponding Object Fragments (2004) — 49 citations
- Object recognition and segmentation by a fragment-based hierarchy. (2007) — 256 citations
- From simple innate biases to complex visual concepts (2012) — 78 citations
- VQA With No Questions-Answers Training (2018) — 13 citations
- Visual Concept Recognition and Localization via Iterative Introspection (2016) — 23 citations
- Anatomy of hierarchy: Feedforward and feedback pathways in macaque visual cortex (2013) — 722 citations
- Class-Based Feature Matching Across Unrestricted Transformations (2008) — 13 citations
- Visual features of intermediate complexity and their use in classification (2002) — 677 citations
- Recognition by Linear Combinations of Models (1991)
- The interpretation of structure from motion (1979)