Harsh Mehta
- Computer Vision and Pattern Recognition top 10%
- Artificial Intelligence
- Human-Computer Interaction
- Media Technology
- Aerospace Engineering
- Co-authors
- Eugene IeJason BaldridgeVihan JainAlexander KuNarendra ShekokarYoav ArtziPiotr MirowskiVijay Katkar
- Topics
- Multimodal Machine Learning Applications (3 papers)Natural Language Processing Techniques (2 papers)Domain Adaptation and Few-Shot Learning (2 papers)
- Journals
- Journal of Mathematical Analysis and ApplicationsInternational Journal of Nanoscience2022 6th International Conference on Computing Methodologies and Communication (ICCMC)
- Partner nations
- IndiaUnited States
In The Last Decade
Harsh Mehta
10 papers receiving 100 citations
Peers
Comparison fields: 5 of 28
- Computer Vision and Pattern Recognition 83
- Artificial Intelligence 63
- Human-Computer Interaction 11
- Media Technology 8
- Aerospace Engineering 7
Countries citing papers authored by Harsh Mehta
This map shows the geographic impact of Harsh Mehta'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 Harsh Mehta with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Harsh Mehta more than expected).
Fields of papers citing papers by Harsh Mehta
This network shows the impact of papers produced by Harsh Mehta. 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 Harsh Mehta. The network helps show where Harsh Mehta may publish in the future.
Co-authorship network of co-authors of Harsh Mehta
This figure shows the co-authorship network connecting the top 25 collaborators of Harsh Mehta. A scholar is included among the top collaborators of Harsh Mehta 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 Harsh Mehta. Harsh Mehta is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | 3 | |
| 2 | 10 | |
| 3 | 3 | |
| 4 | 15 | |
| 5 | 49 | |
| 6 | 3 | |
| 7 | 2 | |
| 8 | 7 | |
| 9 | SDP Descriptors for FLUTE | 1 |
| 10 | 12 |
About Harsh Mehta
Harsh Mehta is a scholar working on Computer Graphics and Computer-Aided Design, Media Technology and Computer Vision and Pattern Recognition, having authored 10 papers that have together received 105 indexed citations. Recurring topics across this work include Multimodal Machine Learning Applications (3 papers), Natural Language Processing Techniques (2 papers) and Domain Adaptation and Few-Shot Learning (2 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (83 citations), Human-Computer Interaction (11 citations) and Artificial Intelligence (63 citations). Harsh Mehta has collaborated with scholars based in India and United States. Frequent co-authors include Eugene Ie, Jason Baldridge, Vihan Jain, Alexander Ku, Narendra Shekokar, Yoav Artzi, Piotr Mirowski, Vijay Katkar, S. Kanagaraj and Santosh Kumar Bharti. Their work appears in journals such as Journal of Mathematical Analysis and Applications, International Journal of Nanoscience and 2022 6th International Conference on Computing Methodologies and Communication (ICCMC).
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.