Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
One-shot learning of object categories
20061.9k citationsLi Fei-Fei, Rob Fergus et al.profile →
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture
This map shows the geographic impact of Rob Fergus's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Rob Fergus with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Rob Fergus more than expected).
This network shows the impact of papers produced by Rob Fergus. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Rob Fergus. The network helps show where Rob Fergus may publish in the future.
Co-authorship network of co-authors of Rob Fergus
This figure shows the co-authorship network connecting the top 25 collaborators of Rob Fergus.
A scholar is included among the top collaborators of Rob Fergus based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with Rob Fergus. Rob Fergus is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
All Works
20 of 20 papers shown
1.
Răileanu, Roberta, et al.. (2021). Automatic Data Augmentation for Generalization in Reinforcement Learning. arXiv (Cornell University). 34.20 indexed citations
2.
Rives, Alexander, Joshua Meier, Tom Sercu, et al.. (2021). Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proceedings of the National Academy of Sciences. 118(15).1429 indexed citations breakdown →
3.
Yarats, Denis, Ilya Kostrikov, & Rob Fergus. (2021). Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels. International Conference on Learning Representations.25 indexed citations
4.
Kostrikov, Ilya, Rob Fergus, Jonathan Tompson, & Ofir Nachum. (2021). Offline Reinforcement Learning with Fisher Divergence Critic Regularization. International Conference on Machine Learning. 5774–5783.15 indexed citations
5.
Marino, Kenneth, Abhinav Gupta, Rob Fergus, & Arthur Szlam. (2019). Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies. International Conference on Learning Representations.2 indexed citations
6.
Sukhbaatar, Sainbayar, Zeming Lin, Ilya Kostrikov, et al.. (2018). Intrinsic motivation and automatic curricula via asymmetric self-play. International Conference on Learning Representations.27 indexed citations
7.
Zhang, Amy, Adam Lerer, Sainbayar Sukhbaatar, Rob Fergus, & Arthur Szlam. (2018). Composable Planning with Attributes. International Conference on Machine Learning. 5842–5851.4 indexed citations
8.
Lake, Brenden M., Wojciech Zaremba, Rob Fergus, & Todd M. Gureckis. (2015). Deep neural networks predict category typicality ratings for images. Cognitive Science.33 indexed citations
9.
Sukhbaatar, Sainbayar, Arthur Szlam, Jason Weston, & Rob Fergus. (2015). Weakly Supervised Memory Networks.. arXiv (Cornell University).42 indexed citations
10.
Zeiler, Matthew D. & Rob Fergus. (2013). Visualizing and Understanding Convolutional Neural Networks. arXiv (Cornell University).271 indexed citations
11.
Wan, Li, Matthew D. Zeiler, Sixin Zhang, Yann Lecun, & Rob Fergus. (2013). Regularization of Neural Networks using DropConnect. International review of cytology. 25. 279–96.957 indexed citations breakdown →
Zeiler, Matthew D., Graham W. Taylor, Leonid Sigal, Iain Matthews, & Rob Fergus. (2011). Facial Expression Transfer with Input-Output Temporal Restricted Boltzmann Machines. Neural Information Processing Systems. 24. 1629–1637.21 indexed citations
14.
Silberman, Nathan, et al.. (2010). Case for automated detection of diabetic retinopathy. National Conference on Artificial Intelligence. 85–90.41 indexed citations
15.
Fergus, Rob, Yair Weiss, & Antonio Torralba. (2009). Semi-Supervised Learning in Gigantic Image Collections. Neural Information Processing Systems. 22. 522–530.138 indexed citations
Torralba, Antonio, Rob Fergus, & Yair Weiss. (2008). Small codes and large image databases for recognition. 1–8.507 indexed citations breakdown →
18.
Weiss, Yair, Antonio Torralba, & Rob Fergus. (2008). Spectral Hashing. neural information processing systems. 21. 1753–1760.1437 indexed citations breakdown →
19.
Russell, Bryan, Antonio Torralba, Ce Liu, Rob Fergus, & William T. Freeman. (2007). Object Recognition by Scene Alignment. Neural Information Processing Systems. 20. 1241–1248.75 indexed citations
20.
Fei-Fei, Li, Rob Fergus, & Pietro Perona. (2003). A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories.256 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.