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.
Countries citing papers authored by Erik Learned-Miller
Since
Specialization
Citations
This map shows the geographic impact of Erik Learned-Miller'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 Erik Learned-Miller with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Erik Learned-Miller more than expected).
Fields of papers citing papers by Erik Learned-Miller
This network shows the impact of papers produced by Erik Learned-Miller. 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 Erik Learned-Miller. The network helps show where Erik Learned-Miller may publish in the future.
Co-authorship network of co-authors of Erik Learned-Miller
This figure shows the co-authorship network connecting the top 25 collaborators of Erik Learned-Miller.
A scholar is included among the top collaborators of Erik Learned-Miller 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 Erik Learned-Miller. Erik Learned-Miller is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Singh, Ashish, Hang Su, Huaizu Jiang, et al.. (2019). Half&Half: New Tasks and Benchmarks for Studying Visual Common Sense.. Computer Vision and Pattern Recognition. 1–4.1 indexed citations
4.
Thomas, Philip S. & Erik Learned-Miller. (2019). Concentration Inequalities for Conditional Value at Risk. International Conference on Machine Learning. 6225–6233.6 indexed citations
Chang, Haw-Shiuan, Erik Learned-Miller, & Andrew McCallum. (2017). Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples. Neural Information Processing Systems. 30. 1002–1012.53 indexed citations
Huang, Gary B., et al.. (2012). Bounding the probability of error for high precision optical character recognition. Journal of Machine Learning Research. 13(1). 363–387.2 indexed citations
11.
Huang, Gary B., Honglak Lee, & Erik Learned-Miller. (2012). Learning hierarchical representations for face verification. ScholarWorks@UMassAmherst (University of Massachusetts Amherst).2 indexed citations
12.
Huang, Gary B., Marwan Mattar, Honglak Lee, & Erik Learned-Miller. (2012). Learning to Align from Scratch. ScholarWorks@UMassAmherst (University of Massachusetts Amherst). 25. 764–772.158 indexed citations
Walls, Robert J., Erik Learned-Miller, & Brian Neil Levine. (2011). Forensic triage for mobile phones with DEC0DE. ScholarWorks@UMassAmherst (University of Massachusetts Amherst). 7–7.27 indexed citations
Learned-Miller, Erik & Parvez Ahammad. (2004). Joint MRI Bias Removal Using Entropy Minimization Across Images. ScholarWorks@UMassAmherst (University of Massachusetts Amherst). 17. 761–768.16 indexed citations
20.
Learned-Miller, Erik, et al.. (2004). Learning Hyper-Features for Visual Identification. ScholarWorks@UMassAmherst (University of Massachusetts Amherst). 17. 425–432.20 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.