Devi Parikh
Impact in
- Computer Vision and Pattern Recognition top 0.01%
- Multimodal Machine Learning Applications
- Advanced Image and Video Retrieval Techniques
- Human Pose and Action Recognition
- Advanced Neural Network Applications
- Video Analysis and Summarization
- Artificial Intelligence top 0.02%
- Domain Adaptation and Few-Shot Learning
- Topic Modeling
- Explainable Artificial Intelligence (XAI)
Papers in
-
- Multimodal Machine Learning Applications 66
- Advanced Image and Video Retrieval Techniques 63
- Image Retrieval and Classification Techniques 22
- Human Pose and Action Recognition 18
- Advanced Neural Network Applications 15
- Visual Attention and Saliency Detection 11
-
- Domain Adaptation and Few-Shot Learning 43
- Topic Modeling 11
- Co-authors
- Dhruv Batra (43 shared papers)Ramakrishna Vedantam (6 shared papers)Abhishek Das (13 shared papers)Ramprasaath R. Selvaraju (4 shared papers)Michael Cogswell (2 shared papers)C. Lawrence Zitnick (17 shared papers)Jiasen Lu (8 shared papers)Kristen Grauman (7 shared papers)
- Journals
- IEEE Transactions on Pattern Analysis and Machine Intelligence (6 papers)International Journal of Computer Vision (3 papers)Advances in computer vision and pattern recognition (2 papers)ACS Catalysis (2 papers)Lecture notes in computer science (16 papers)
- Partner nations
- United StatesJapanIsrael
In The Last Decade
Devi Parikh
128 papers receiving 30.8k citations
Devi Parikh's Hit Papers
Peers
Comparison fields: 5 of 212
- Computer Vision and Pattern Recognition 19.5k
- Artificial Intelligence 15.6k
- Health Informatics 498
- Radiology, Nuclear Medicine and Imaging 2.8k
- Media Technology 1.1k
Countries citing papers authored by Devi Parikh
This map shows the geographic impact of Devi Parikh'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 Devi Parikh with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Devi Parikh more than expected).
Fields of papers citing papers by Devi Parikh
This network shows the impact of papers produced by Devi Parikh. 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 Devi Parikh. The network helps show where Devi Parikh may publish in the future.
Co-authors
The 25 scholars most cited alongside Devi Parikh, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
Showing the 20 most-cited of 130 papers — load more, or switch the sort, to bring in the rest.
| # | Work | ||
|---|---|---|---|
| 1 | Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization Hit paper breakdown → | 2017 | 14104 |
| 2 | CIDEr: Consensus-based image description evaluation Hit paper breakdown → | 2015 | 3089 |
| 3 | VQA: Visual Question Answering Hit paper breakdown → | 2015 | 2738 |
| 4 | Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering Hit paper breakdown → | 2017 | 1300 |
| 5 | Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning Hit paper breakdown → | 2017 | 1163 |
| 6 | Relative attributes Hit paper breakdown → | 2011 | 652 |
| 7 | Graph R-CNN for Scene Graph Generation Hit paper breakdown → | 2018 | 590 |
| 8 | Joint Unsupervised Learning of Deep Representations and Image Clusters Hit paper breakdown → | 2016 | 502 |
| 9 | Open Catalyst 2020 (OC20) Dataset and Community Challenges Hit paper breakdown → | 2021 | 497 |
| 10 | VQA: Visual Question Answering Hit paper breakdown → | 2016 | 388 |
| 11 | ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks Hit paper breakdown → | 2019 | 378 |
| 12 | A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories Hit paper breakdown → | 2016 | 370 |
| 13 | iCoseg: Interactive co-segmentation with intelligent scribble guidance Hit paper breakdown → | 2010 | 370 |
| 14 | Deep Learning the City: Quantifying Urban Perception at a Global Scale Hit paper breakdown → | 2016 | 349 |
| 15 | 2017 | 304 | |
| 16 | 2018 | 280 | |
| 17 | 12-in-1: Multi-Task Vision and Language Representation Learning Hit paper breakdown → | 2020 | 278 |
| 18 | Visual Dialog | 2017 | 238 |
| 19 | 2012 | 225 | |
| 20 | Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors Hit paper breakdown → | 2022 | 218 |
About Devi Parikh
Devi Parikh is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence, Signal Processing, Aerospace Engineering and Computer Networks and Communications, having authored 130 papers that have together received 31.8k indexed citations. Recurring topics across this work include Multimodal Machine Learning Applications (66 papers), Advanced Image and Video Retrieval Techniques (63 papers), Domain Adaptation and Few-Shot Learning (43 papers), Image Retrieval and Classification Techniques (22 papers), Human Pose and Action Recognition (18 papers), Advanced Neural Network Applications (15 papers), Visual Attention and Saliency Detection (11 papers) and Topic Modeling (11 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (19.5k citations), Artificial Intelligence (15.6k citations), Health Informatics (498 citations), Radiology, Nuclear Medicine and Imaging (2.8k citations) and Media Technology (1.1k citations). Devi Parikh has collaborated with scholars based in United States, Japan and Israel. Frequent co-authors include Dhruv Batra, Ramakrishna Vedantam, Abhishek Das, Ramprasaath R. Selvaraju, Michael Cogswell, C. Lawrence Zitnick, Jiasen Lu, Kristen Grauman, Stanislaw Antol and Aishwarya Agrawal. Their work appears in journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, International Journal of Computer Vision, Advances in computer vision and pattern recognition, ACS Catalysis and Lecture notes in computer science.
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.