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.
The Pascal Visual Object Classes (VOC) Challenge
200912.0k citationsMark Everingham, Luc Van Gool et al.International Journal of Computer Visionprofile →
The Pascal Visual Object Classes Challenge: A Retrospective
20144.4k citationsMark Everingham, S. M. Ali Eslami et al.International Journal of Computer Visionprofile →
This map shows the geographic impact of John Winn'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 John Winn with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites John Winn more than expected).
This network shows the impact of papers produced by John Winn. 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 John Winn. The network helps show where John Winn may publish in the future.
Co-authorship network of co-authors of John Winn
This figure shows the co-authorship network connecting the top 25 collaborators of John Winn.
A scholar is included among the top collaborators of John Winn 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 John Winn. John Winn is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Winn, John, Matteo Venanzi, Tom Minka, et al.. (2021). Enterprise Alexandria: Online High-Precision Enterprise Knowledge Base Construction with Typed Entities.1 indexed citations
3.
Winn, John, et al.. (2019). Alexandria: Unsupervised High-Precision Knowledge Base Construction using a Probabilistic Program.5 indexed citations
4.
Minka, Tom, et al.. (2017). Belief Propagation with Strings.1 indexed citations
Eslami, S. M. Ali, Daniel Tarlow, Pushmeet Kohli, & John Winn. (2014). Just-In-Time Learning for Fast and Flexible Inference. Neural Information Processing Systems. 27. 154–162.4 indexed citations
7.
Heess, Nicolas, Daniel Tarlow, & John Winn. (2013). Learning to Pass Expectation Propagation Messages. Neural Information Processing Systems. 26. 3219–3227.7 indexed citations
8.
Shotton, Jamie, Toby Sharp, Pushmeet Kohli, et al.. (2013). Decision Jungles: Compact and Rich Models for Classification. Neural Information Processing Systems. 26. 234–242.58 indexed citations
9.
Lazic, Nevena, Chris Bishop, & John Winn. (2013). Structural Expectation Propagation (SEP): Bayesian Structure Learning for Networks with Latent Variables. International Conference on Artificial Intelligence and Statistics. 379–387.4 indexed citations
Buchan, Iain, John Winn, & Chris Bishop. (2009). A Unified Modeling Approach to Data-Intensive Healthcare. Research Explorer (The University of Manchester). 91–97.20 indexed citations
15.
Everingham, Mark, Luc Van Gool, Christopher K. I. Williams, John Winn, & Andrew Zisserman. (2009). The Pascal Visual Object Classes (VOC) Challenge. International Journal of Computer Vision. 88(2). 303–338.12010 indexed citations breakdown →
Winn, John & Antonio Criminisi. (2006). Object Class Recognition at a Glance. Computer Vision and Pattern Recognition.22 indexed citations
18.
Winn, John & Chris Bishop. (2005). Variational Message Passing. Journal of Machine Learning Research. 6(23). 661–694.415 indexed citations breakdown →
19.
Bishop, Chris & John Winn. (2003). Structured Variational Distributions in VIBES. International Conference on Artificial Intelligence and Statistics. 33–40.23 indexed citations
20.
Bishop, Chris, David J. Spiegelhalter, & John Winn. (2002). VIBES: A Variational Inference Engine for Bayesian Networks. Neural Information Processing Systems. 15. 793–800.57 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.