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.
Online Learning for Matrix Factorization and Sparse Coding
20101.6k citationsJulien Mairal, Francis Bach et al.Journal of Machine Learning Researchprofile →
Online dictionary learning for sparse coding
20091.4k citationsJulien Mairal, Francis Bach et al.profile →
Non-local sparse models for image restoration
20091.2k citationsJulien Mairal, Francis Bach et al.profile →
Learning mid-level features for recognition
2010702 citationsY-Lan Boureau, Francis Bach et al.profile →
Optimization with Sparsity-Inducing Penalties
2011391 citationsFrancis Bachnow publishers, Inc. eBooksprofile →
Peers — A (Enhanced Table)
Peers by citation overlap · career bar shows stage (early→late)
cites ·
hero ref
This map shows the geographic impact of Francis Bach'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 Francis Bach with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Francis Bach more than expected).
This network shows the impact of papers produced by Francis Bach. 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 Francis Bach. The network helps show where Francis Bach may publish in the future.
Co-authorship network of co-authors of Francis Bach
This figure shows the co-authorship network connecting the top 25 collaborators of Francis Bach.
A scholar is included among the top collaborators of Francis Bach 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 Francis Bach. Francis Bach is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Bach, Francis. (2011). Optimization with Sparsity-Inducing Penalties. now publishers, Inc. eBooks.391 indexed citations breakdown →
9.
Duchenne, Olivier, Francis Bach, In-So Kweon, & Jean Ponce. (2011). A Tensor-Based Algorithm for High-Order Graph Matching. IEEE Transactions on Pattern Analysis and Machine Intelligence. 33(12). 2383–2395.225 indexed citations
10.
Mairal, Julien, Francis Bach, Jean Ponce, & Guillermo Sapiro. (2010). Online Learning for Matrix Factorization and Sparse Coding. Journal of Machine Learning Research. 11(1). 19–60.1597 indexed citations breakdown →
11.
Boureau, Y-Lan, Francis Bach, Yann LeCun, & Jean Ponce. (2010). Learning mid-level features for recognition. 2559–2566.702 indexed citations breakdown →
12.
Duchenne, Olivier, Francis Bach, In-So Kweon, & Jean Ponce. (2009). A tensor-based algorithm for high-order graph matching. 2009 IEEE Conference on Computer Vision and Pattern Recognition. 1980–1987.76 indexed citations
13.
Mairal, Julien, Francis Bach, Jean Ponce, Guillermo Sapiro, & Andrew Zisserman. (2009). Non-local sparse models for image restoration. 2272–2279.1199 indexed citations breakdown →
14.
Mairal, Julien, Francis Bach, Jean Ponce, & Guillermo Sapiro. (2009). Online dictionary learning for sparse coding. 689–696.1414 indexed citations breakdown →
Bach, Francis. (1952). BUTAZOLIDINE. The Lancet. 260(6724). 92–92.4 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.