D-Index & Metrics Best Publications

D-Index & Metrics

Discipline name D-index D-index (Discipline H-index) only includes papers and citation values for an examined discipline in contrast to General H-index which accounts for publications across all disciplines. Citations Publications World Ranking National Ranking
Computer Science D-index 74 Citations 41,972 199 World Ranking 623 National Ranking 383

Research.com Recognitions

Awards & Achievements

2016 - Fellow of Alfred P. Sloan Foundation

Overview

What is she best known for?

The fields of study she is best known for:

  • Artificial intelligence
  • Machine learning
  • Computer vision

Her primary scientific interests are in Artificial intelligence, Question answering, Visualization, Natural language processing and Image. The various areas that Devi Parikh examines in her Artificial intelligence study include Context, Machine learning and Computer vision. She has included themes like Artificial neural network, Natural language, Knowledge extraction and Embodied cognition in her Question answering study.

Devi Parikh works mostly in the field of Visualization, limiting it down to concerns involving Reinforcement learning and, occasionally, Contextual image classification, Research software and World Wide Web. The study incorporates disciplines such as Object, Semantics and Image retrieval in addition to Natural language processing. Her research investigates the connection between Image and topics such as Sentence that intersect with issues in Benchmark.

Her most cited work include:

  • Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization (3161 citations)
  • VQA: Visual Question Answering (1720 citations)
  • CIDEr: Consensus-based image description evaluation (1517 citations)

What are the main themes of her work throughout her whole career to date?

Artificial intelligence, Machine learning, Question answering, Natural language processing and Image are her primary areas of study. The concepts of her Artificial intelligence study are interwoven with issues in Context, Computer vision and Pattern recognition. Devi Parikh interconnects Contextual image classification, Classifier and Training set in the investigation of issues within Machine learning.

Devi Parikh combines subjects such as Natural language, Embodied cognition and Reinforcement learning with her study of Question answering. In her research, Human–computer interaction is intimately related to Dialog box, which falls under the overarching field of Natural language processing. Her work investigates the relationship between Visualization and topics such as Closed captioning that intersect with problems in Language model.

She most often published in these fields:

  • Artificial intelligence (71.96%)
  • Machine learning (28.72%)
  • Question answering (29.73%)

What were the highlights of her more recent work (between 2019-2021)?

  • Artificial intelligence (71.96%)
  • Human–computer interaction (18.24%)
  • Machine learning (28.72%)

In recent papers she was focusing on the following fields of study:

Her primary areas of investigation include Artificial intelligence, Human–computer interaction, Machine learning, Embodied cognition and Transformer. Her study of Question answering is a part of Artificial intelligence. Her research in Human–computer interaction focuses on subjects like Dialog box, which are connected to Observer and Forgetting.

Her work carried out in the field of Machine learning brings together such families of science as Context, Sequential decision and Visualization. Her biological study deals with issues like Pattern recognition, which deal with fields such as Closed captioning and Reinforcement learning. Her Transformer research is multidisciplinary, relying on both Spatial intelligence and Spatial relation.

Between 2019 and 2021, her most popular works were:

  • Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization (317 citations)
  • Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization (317 citations)
  • 12-in-1: Multi-Task Vision and Language Representation Learning (78 citations)

In her most recent research, the most cited papers focused on:

  • Artificial intelligence
  • Machine learning
  • Computer vision

Her primary areas of study are Artificial intelligence, Machine learning, Transformer, Reinforcement learning and Context. Her work in Artificial intelligence addresses subjects such as Set, which are connected to disciplines such as Natural language processing and Task analysis. As a part of the same scientific study, Devi Parikh usually deals with the Machine learning, concentrating on Visualization and frequently concerns with Closed captioning, Discriminative model, Convolutional neural network, Pattern recognition and Contextual image classification.

Her Reinforcement learning research is multidisciplinary, incorporating elements of Object, Visual Objects and Multi-task learning. Her research integrates issues of Contrast, Spatial relation, Layer and Baseline in her study of Context. Devi Parikh focuses mostly in the field of Knowledge extraction, narrowing it down to topics relating to Question answering and, in certain cases, Human–computer interaction.

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

Best Publications

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

Ramprasaath R. Selvaraju;Michael Cogswell;Abhishek Das;Ramakrishna Vedantam.
international conference on computer vision (2017)

4009 Citations

VQA: Visual Question Answering

Stanislaw Antol;Aishwarya Agrawal;Jiasen Lu;Margaret Mitchell.
international conference on computer vision (2015)

2676 Citations

CIDEr: Consensus-based image description evaluation

Ramakrishna Vedantam;C. Lawrence Zitnick;Devi Parikh.
computer vision and pattern recognition (2015)

1731 Citations

VQA: Visual Question Answering

Aishwarya Agrawal;Jiasen Lu;Stanislaw Antol;Margaret Mitchell.
arXiv: Computation and Language (2015)

1635 Citations

Relative attributes

Devi Parikh;Kristen Grauman.
international conference on computer vision (2011)

916 Citations

Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning

Jiasen Lu;Caiming Xiong;Devi Parikh;Richard Socher.
computer vision and pattern recognition (2017)

777 Citations

Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering

Yash Goyal;Tejas Khot;Douglas Summers-Stay;Dhruv Batra.
computer vision and pattern recognition (2017)

767 Citations

Hierarchical Question-Image Co-Attention for Visual Question Answering

Jiasen Lu;Jianwei Yang;Dhruv Batra;Devi Parikh.
arXiv: Computer Vision and Pattern Recognition (2016)

553 Citations

Visual Dialog

Abhishek Das;Satwik Kottur;Khushi Gupta;Avi Singh.
computer vision and pattern recognition (2017)

529 Citations

ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks

Jiasen Lu;Dhruv Batra;Devi Parikh;Stefan Lee.
neural information processing systems (2019)

515 Citations

Best Scientists Citing Devi Parikh

Kristen Grauman

Kristen Grauman

Facebook (United States)

Publications: 70

Li Fei-Fei

Li Fei-Fei

Stanford University

Publications: 65

Trevor Darrell

Trevor Darrell

University of California, Berkeley

Publications: 59

Anton van den Hengel

Anton van den Hengel

University of Adelaide

Publications: 58

Hanwang Zhang

Hanwang Zhang

Nanyang Technological University

Publications: 54

Jianfeng Gao

Jianfeng Gao

Microsoft (United States)

Publications: 53

Chunhua Shen

Chunhua Shen

University of Adelaide

Publications: 50

Ali Farhadi

Ali Farhadi

University of Washington

Publications: 50

Yi Yang

Yi Yang

Zhejiang University

Publications: 48

Xiaogang Wang

Xiaogang Wang

Chinese University of Hong Kong

Publications: 47

Tao Xiang

Tao Xiang

University of Surrey

Publications: 47

Qi Tian

Qi Tian

Huawei Technologies (China)

Publications: 43

Dacheng Tao

Dacheng Tao

University of Sydney

Publications: 39

Jianfei Cai

Jianfei Cai

Monash University

Publications: 39

Antonio Torralba

Antonio Torralba

MIT

Publications: 39

Profile was last updated on December 6th, 2021.
Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).
The ranking d-index is inferred from publications deemed to belong to the considered discipline.

If you think any of the details on this page are incorrect, let us know.

Contact us
Something went wrong. Please try again later.