Subhransu Maji

82 papers receiving 7.8k citations

Hit Papers

Bilinear CNN Models for Fine-Grained Visual Recognition2008202620142020201520142011200820154008001.2k

Peers

Subhransu Maji
Comparison fields: 5 of 177
  • Computer Vision and Pattern Recognition 6.1k
  • Artificial Intelligence 2.8k
  • Media Technology 773
  • Computational Mechanics 588
  • Aerospace Engineering 407
Replace Hanzi Mao with:
Hanzi Mao United States
Derek Hoiem United States
Enhua Wu China
Guosheng Lin Singapore
James Hays United States
Gabriel Brostow United Kingdom
Mathieu Salzmann Switzerland
Bryan Russell United States
Song Bai China
Bastian Leibe Germany
Subhransu Maji relative to Hanzi Mao United States Hanzi Mao's profile →
Citations per field
00.5×200×400×554×
Hanzi Mao · 1×
Citations per year

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).

Fields of papers citing papers by Subhransu Maji

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

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.

All Works

20 of 20 papers shown
#WorkIndexed citations
1 0
2 1
3 4
4 3
5 61
6
Unsupervised Discovery of Object Landmarks via Contrastive Learning
3
7 106
8 63
9 245
10 11
11
Bilinear CNN Models for Fine-Grained Visual Recognitionbreakdown →
1334
12
Face Identification with Bilinear CNNs.
12
13
Active Boundary Annotation using Random MAP Perturbations
5
14 7
15
Learning Efficient Random Maximum A-Posteriori Predictors with Non-Decomposable Loss Functions
10
16
Part Annotations via Pairwise Correspondence.
10
17 170
18 1
19
Semantic contours from inverse detectorsbreakdown →
944
20
Distributed compression and fusion of nonnegative sparse signals for multiple-view object recognition
7

About Subhransu Maji

Subhransu Maji is a scholar working on Computer Vision and Pattern Recognition, Ecological Modeling and Computer Graphics and Computer-Aided Design, having authored 85 papers that have together received 8.1k indexed citations. Recurring topics across this work include Advanced Image and Video Retrieval Techniques (33 papers), Advanced Neural Network Applications (17 papers) and Domain Adaptation and Few-Shot Learning (16 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (6.1k citations), Computer Graphics and Computer-Aided Design (336 citations) and Media Technology (773 citations). Subhransu Maji has collaborated with scholars based in United States, United Kingdom and Switzerland. Frequent co-authors include Jitendra Malik, Tsung‐Yu Lin, Aruni RoyChowdhury, Andrea Vedaldi, Mircea Cimpoi, Alexander C. Berg, Lubomir Bourdev, Iasonas Kokkinos, Bharath Hariharan and Pablo Arbeláez. Their work appears in journals such as The Astrophysical Journal, IEEE Transactions on Pattern Analysis and Machine Intelligence and Journal of Materials Chemistry A.

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.

Explore authors with similar magnitude of impact

Rankless by CCL
2026