Amir Najafi
- Artificial Intelligence top 10%
- Computer Vision and Pattern Recognition top 10%
- Radiology, Nuclear Medicine and Imaging
- Computational Mechanics
- Media Technology
- Co-authors
- Yoshua BengioIoannis MitliagkasAlex LambChristopher BeckhamVikas VermaDavid López-PazEmad FatemizadehAaron Courville
- Topics
- Adversarial Robustness in Machine Learning (2 papers)Domain Adaptation and Few-Shot Learning (2 papers)Genetic Associations and Epidemiology (1 paper)
- Cited by
- Computer Vision and Pattern RecognitionArtificial IntelligenceRadiology, Nuclear Medicine and Imaging
- Journals
- IEEE Transactions on Pattern Analysis and Machine IntelligenceIEEE/ACM Transactions on Computational Biology and BioinformaticsarXiv (Cornell University)
In The Last Decade
Amir Najafi
6 papers receiving 220 citations
Peers
Comparison fields: 5 of 56
- Artificial Intelligence 156
- Computer Vision and Pattern Recognition 125
- Radiology, Nuclear Medicine and Imaging 33
- Computational Mechanics 14
- Media Technology 9
Countries citing papers authored by Amir Najafi
This map shows the geographic impact of Amir Najafi'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 Amir Najafi with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Amir Najafi more than expected).
Fields of papers citing papers by Amir Najafi
This network shows the impact of papers produced by Amir Najafi. 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 Amir Najafi. The network helps show where Amir Najafi may publish in the future.
Co-authorship network of co-authors of Amir Najafi
This figure shows the co-authorship network connecting the top 25 collaborators of Amir Najafi. A scholar is included among the top collaborators of Amir Najafi 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 Amir Najafi. Amir Najafi is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | Robustness to Adversarial Perturbations in Learning from Incomplete Data | 5 |
| 2 | A New Formulation for Cost-Sensitive Two Group Support Vector Machine with Multiple Error Rate | 1 |
| 3 | 179 | |
| 4 | Manifold Mixup: Learning Better Representations by Interpolating Hidden States | 11 |
| 5 | 7 | |
| 6 | 25 | |
| 7 | 0 |
About Amir Najafi
Amir Najafi is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Genetics, having authored 7 papers that have together received 228 indexed citations. Recurring topics across this work include Adversarial Robustness in Machine Learning (2 papers), Domain Adaptation and Few-Shot Learning (2 papers) and Genetic Associations and Epidemiology (1 paper). The work is most often cited by research in Computer Vision and Pattern Recognition (125 citations), Artificial Intelligence (156 citations) and Radiology, Nuclear Medicine and Imaging (33 citations). Amir Najafi has collaborated with scholars based in Iran and Japan. Frequent co-authors include Yoshua Bengio, Ioannis Mitliagkas, Alex Lamb, Christopher Beckham, Vikas Verma, David López-Paz, Emad Fatemizadeh, Aaron Courville, Seyed Abolfazl Motahari and Vikas Verma. Their work appears in journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE/ACM Transactions on Computational Biology and Bioinformatics and arXiv (Cornell University).
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.