Devi Parikh Google Scholar: h-index, Total Citations, and Citation Map
Devi Parikh's h-index is 99 (199 i10-index, 139,224+ total citations across 284+ publications) according to Google Scholar as of October 2026. Devi Parikh is affiliated with Previously: FAIR and GenAI @ Meta. Georgia Tech.
Devi Parikh is a researcher affiliated with Previously: FAIR and GenAI @ Meta. Georgia Tech, specializing in Generative AI, AI for Creativity, Computer Vision. Their work has been cited 139,224 times. This profile visualizes their global influence, highlighting strong citation networks in United States.
Devi Parikh's Citation Metrics
Bibliometric impact based on 284 indexed publications.
- H-Index
- 99
- i10-Index
- 199
- Total Citations
- 139,224
- Citing Countries
- 86
As of October 2026.
Devi Parikh has an h-index of 99 and 139,224 total citations across 284 publications, with research cited by institutions in 86 countries.
Download Exports (PNG, CSV, Poster)
Free Viewing Devi Parikh's citation map is always free. Pay once to download poster, PNG, and CSV files for offline use or your visa packet.
Showing partial map from open academic databases
Upgrade ($39.98) for the complete Google Scholar crawl.
Global Impact Map
Visualizing the geographic distribution of institutions that have cited your work.
Starting…
Pins will appear here as institutions are resolved — no need to refresh.
Grad-cam: Visual explanations from deep networks via gradient-based localization
201743,395
Top Citing Countries
Top Citing Institutions
Visa Evidence Package
Views and exports tuned for EB-1A, O-1A, and EB-2 NIW petitions. Sustained acclaim, geographic reach, and independent-citation filtering are the strongest evidence categories immigration adjudicators look for.
Significant Contributions
Auto-detected research lines — a seminal paper and the follow-up work building on it. Review and edit before using in a petition. Each Free PDF opens in a new tab — EB-1A organises this into the structure USCIS applies to Criterion 5 of 8 CFR § 204.5(h)(3)(v); EB-1B re-frames it under § 204.5(i)(3) (outstanding researcher); NIW presents it under prong 2 of Matter of Dhanasar.
746 citing papers could not be classified (no author data) — excluded from the percentages above.
The researcher pioneered hierarchical co-attention mechanisms for visual question answering, establishing a foundational framework that enabled subsequent advancements in visual dialog and robust reasoning.
The researcher pioneered the use of relative attributes for visual understanding, establishing a foundational framework that enabled subsequent advances in semantic scene analysis and user-centric visual prediction.
The researcher pioneered embodied question answering, establishing a foundational framework for grounded multimodal interaction that has been extensively adopted and extended by the independent research community.
Citation trend (last 10 years)Click to expand
Citation Trend (Last 10 Years)
Related Guides
Learn how to use citation maps for your research and visa applications.
About Devi Parikh's research
Devi Parikh is a researcher in Generative AI, AI for Creativity and Computer Vision at Previously: FAIR and GenAI @ Meta. Georgia Tech. Their work has been cited 139,224 times across 284 publications (h-index 99), according to Google Scholar.
Their most-cited work, “Grad-cam: Visual explanations from deep networks via gradient-based localization” (2017), has accumulated 43,395 citations. Other influential works include “The llama 3 herd of models” (2024) with 19,156 citations and “VQA: Visual Question Answering” (2015) with 8,707 citations.
Citations of Devi Parikh's research come primarily from United States, China and United Kingdom, reflecting international research impact across 5+ countries. The interactive citation map above shows the full geographic distribution of the institutions citing this work.
