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.
CONDENSATION—Conditional Density Propagation for Visual Tracking
19983.4k citationsMichael Isard, Andrew BlakeInternational Journal of Computer Visionprofile →
Object retrieval with large vocabularies and fast spatial matching
20071.9k citationsJames Philbin, Ondřej Chum et al.profile →
Dryad
20071.7k citationsMichael Isard, Mihai Budiu et al.profile →
Lost in quantization: Improving particular object retrieval in large scale image databases
2008942 citationsJames Philbin, Ondřej Chum et al.profile →
Quincy
2009595 citationsMichael Isard, Jon Currey et al.profile →
Total Recall: Automatic Query Expansion with a Generative Feature Model for Object Retrieval
2007580 citationsOndřej Chum, James Philbin et al.profile →
DryadLINQ: a system for general-purpose distributed data-parallel computing using a high-level language
2008503 citationsYuan Yu, Michael Isard et al.Operating Systems Design and Implementationprofile →
This map shows the geographic impact of Michael Isard'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 Michael Isard with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Michael Isard more than expected).
This network shows the impact of papers produced by Michael Isard. 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 Michael Isard. The network helps show where Michael Isard may publish in the future.
Co-authorship network of co-authors of Michael Isard
This figure shows the co-authorship network connecting the top 25 collaborators of Michael Isard.
A scholar is included among the top collaborators of Michael Isard 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 Michael Isard. Michael Isard 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.
McSherry, Frank, Michael Isard, & Derek G. Murray. (2015). Scalability! but at what cost?. 14–14.147 indexed citations
2.
Gog, Ionel, Jana Giceva, Malte Schwarzkopf, et al.. (2015). Broom: sweeping out garbage collection from big data systems. 2–2.58 indexed citations
3.
Ke, Qifa & Michael Isard. (2012). A Multi-View Embedding Space for Internet Images, Tags, and Their Semantics. International Journal of Computer Vision.6 indexed citations
4.
Fetterly, Dennis, Maya Haridasan, Michael Isard, & Sundararaman Swaminathan. (2011). TidyFS: a simple and small distributed file system. USENIX Annual Technical Conference. 34–34.12 indexed citations
5.
Yu, Yuan, Michael Isard, Dennis Fetterly, et al.. (2009). Some sample programs written in DryadLINQ. World Journal of Surgical Oncology. 19(1). 37–46.7 indexed citations
6.
Popa, Lucian, Mihai Budiu, Yuan Yu, & Michael Isard. (2009). DryadInc: reusing work in large-scale computations. IEEE International Conference on Cloud Computing Technology and Science. 21.60 indexed citations
7.
Isard, Michael, John MacCormick, & Kannan Achan. (2008). Continuously-adaptive discretization for message-passing algorithms. Neural Information Processing Systems. 21. 737–744.15 indexed citations
8.
Yu, Yuan, Michael Isard, Dennis Fetterly, et al.. (2008). DryadLINQ: a system for general-purpose distributed data-parallel computing using a high-level language. Operating Systems Design and Implementation. 1–14.503 indexed citations breakdown →
9.
Philbin, James, Ondřej Chum, Michael Isard, Josef Šivic, & Andrew Zisserman. (2008). Lost in quantization: Improving particular object retrieval in large scale image databases. 1–8.942 indexed citations breakdown →
10.
Isard, Michael & Andrew Birrell. (2007). Automatic mutual exclusion. 3.39 indexed citations
11.
Isard, Michael & John MacCormick. (2005). Dense motion and disparity estimation via loopy belief propagation.2 indexed citations
Blank, Tom, et al.. (2004). An Internet Protocol (IP) Sound System. Journal of the Audio Engineering Society.9 indexed citations
14.
Lillibridge, Mark, Sameh Elnikety, Andrew Birrell, Mike Burrows, & Michael Isard. (2003). A Cooperative Backup System. Infoscience (Ecole Polytechnique Fédérale de Lausanne).6 indexed citations
15.
Sigal, Leonid, et al.. (2003). Attractive People: Assembling Loose-Limbed Models using Non-parametric Belief Propagation. Neural Information Processing Systems. 16. 1539–1546.63 indexed citations
16.
Lillibridge, Mark, Sameh Elnikety, Andrew Birrell, Mike Burrows, & Michael Isard. (2003). A cooperative internet backup scheme. USENIX Annual Technical Conference. 3–3.111 indexed citations
17.
Sullivan, J.L., Andrew Blake, Michael Isard, & John MacCormick. (2001). Bayesian Object Localisation in Images. International Journal of Computer Vision. 44(2). 111–135.39 indexed citations
18.
Blake, Andrew, et al.. (1998). Learning Multi-Class Dynamics. Neural Information Processing Systems. 11. 389–395.32 indexed citations
19.
Blake, Andrew & Michael Isard. (1996). The CONDENSATION Algorithm - Conditional Density Propagation and Applications to Visual Tracking. Neural Information Processing Systems. 9. 361–367.32 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.