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.
Bilinear CNN Models for Fine-Grained Visual Recognition
20151.3k citationsTsung‐Yu Lin, Aruni RoyChowdhury et al.profile →
Countries citing papers authored by Subhransu Maji
Since
Specialization
Citations
This map shows the geographic impact of Subhransu Maji'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 Subhransu Maji with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Subhransu Maji more than expected).
This network shows the impact of papers produced by Subhransu Maji. 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 Subhransu Maji. The network helps show where Subhransu Maji may publish in the future.
Co-authorship network of co-authors of Subhransu Maji
This figure shows the co-authorship network connecting the top 25 collaborators of Subhransu Maji.
A scholar is included among the top collaborators of Subhransu Maji 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 Subhransu Maji. Subhransu Maji is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Maji, Subhransu, Tamir Hazan, & Tommi Jaakkola. (2014). Active Boundary Annotation using Random MAP Perturbations. DSpace@MIT (Massachusetts Institute of Technology). 604–613.5 indexed citations
Hazan, Tamir, Subhransu Maji, Joseph Keshet, & Tommi Jaakkola. (2013). Learning Efficient Random Maximum A-Posteriori Predictors with Non-Decomposable Loss Functions. DSpace@MIT (Massachusetts Institute of Technology). 26. 1887–1895.10 indexed citations
Maji, Subhransu & Gregory Shakhnarovich. (2012). Part Annotations via Pairwise Correspondence.. National Conference on Artificial Intelligence.10 indexed citations
Yang, Allen Y., Subhransu Maji, Kirak Hong, Posu Yan, & S. Shankar Sastry. (2009). Distributed compression and fusion of nonnegative sparse signals for multiple-view object recognition. International Conference on Information Fusion. 1867–1874.7 indexed citations
20.
Maji, Subhransu & Jitendra Malik. (2009). Fast and Accurate Digit Classification. UC Berkeley.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.