World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
55
Citations
9063
World Ranking
4405
National Ranking
2056

Research.com Recognitions

  • 2011 - IEEE Fellow For contributions to multimedia content analysis

Overview

Ajay Divakaran is affiliated with SRI International in the United States and has contributed extensively to the field of computer science, particularly in artificial intelligence and computer vision. Their body of work includes research that spans several interrelated subfields such as domain adaptation, few-shot learning, explainable AI, and multimodal machine learning applications.

The scientist's recent scholarly publications demonstrate engagement with contemporary challenges in machine learning and computer vision. Notable papers include:

  • Confidence Calibration for Domain Generalization under Covariate Shift, 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
  • Detecting Out-Of-Context Objects Using Graph Contextual Reasoning Network, 2022, Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
  • Generating and evaluating explanations of attended and error-inducing input regions for VQA models, 2021, Applied AI Letters
  • Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks, 2020, arXiv (Cornell University)
  • Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2, 2022, arXiv (Cornell University)

Their research contributions are distributed across a range of publication venues, mainly:

  • arXiv (Cornell University) with 29 publications
  • 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
  • Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
  • Applied AI Letters
  • 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Frequent collaborators include:

  • Karan Sikka (14 joint publications)
  • Yi Yao (9 joint publications)
  • Michael Cogswell (9 joint publications)
  • Yunye Gong (7 joint publications)
  • Meng Ye (7 joint publications)

Ajay Divakaran's scholarly output spans various main topics and subfields such as:

  • Main field: Computer Science (70 publications)
  • Subfields: Artificial Intelligence (46 publications), Computer Vision and Pattern Recognition (22 publications), Radiology, Nuclear Medicine and Imaging (4 publications), Cognitive Neuroscience (4 publications), Cancer Research (2 publications)
  • Main research topics: Domain Adaptation and Few-Shot Learning (28 publications), Multimodal Machine Learning Applications (22 publications), Topic Modeling (16 publications), Adversarial Robustness in Machine Learning (8 publications), Advanced Neural Network Applications (8 publications), Explainable Artificial Intelligence (XAI) (8 publications), COVID-19 diagnosis using AI (8 publications)

Ajay Divakaran was awarded IEEE Fellow status in 2011 for contributions to multimedia content analysis, recognizing their impact within this research community.

Best Publications

  • Algorithms and system for segmentation and structure analysis in soccer video

    Peng Xu;Lexing Xie;Shih-Fu Chang;A. Divakaran

  • Speech denoising using nonnegative matrix factorization with priors

    K.W. Wilson;B. Raj;P. Smaragdis;A. Divakaran

  • ZERO-SHOT OBJECT DETECTION

    Ankan Bansal;Karan Sikka;Gaurav Sharma;Rama Chellappa

  • Structure analysis of soccer video with hidden Markov models

    Lexing Xie;Shih-Fu Chang;Ajay Divakaran;Huifang Sun

  • Structure analysis of soccer video with domain knowledge and hidden Markov models

    Lexing Xie;Peng Xu;Shih-Fu Chang;Ajay Divakaran

  • MPEG-7 visual motion descriptors

    S. Jeannin;A. Divakaran

  • Audio analysis for surveillance applications

    R. Radhakrishnan;A. Divakaran;A. Smaragdis

  • Recognition and volume estimation of food intake using a mobile device

    Manika Puri;Zhiwei Zhu;Qian Yu;Ajay Divakaran

  • Recognizing salient video events through learning-based multimodal analysis of visual features and audio-based analytics

    Hui Cheng;Ajay Divakaran;Elizabeth Shriberg;Harpreet Singh Sawhney

  • Method and apparatus for transcoding of compressed image

    Anthony Vetro;Ajay Divakaran;Huifang Sun

  • Survey of compressed-domain features used in audio-visual indexing and analysis

    Hualu Wang;Ajay Divakaran;Anthony Vetro;Shih-Fu Chang

  • Evaluation of low-level features and their combinations for complex event detection in open source videos

    Amir Tamrakar;Saad Ali;Qian Yu;Jingen Liu

  • “Snap-n-Eat” Food Recognition and Nutrition Estimation on a Smartphone

    Weiyu Zhang;Qian Yu;Behjat Siddiquie;Ajay Divakaran

  • Audio events detection based highlights extraction from baseball, golf and soccer games in a unified framework

    Ziyou Xiong;R. Radhakrishnan;A. Divakaran;T.S. Huang

  • Transcoding method of compressed video

    Vetro A;Divakaran A;Sun H

  • Temporal-context-based video browsing interface for PVR-enabled television systems

    Samuel Shipman;Ajay Divakaran

  • A highlight scene detection and video summarization system using audio feature for a personal video recorder

    I. Otsuka;K. Nakane;A. Divakaran;K. Hatanaka

  • Food recognition using visual analysis and speech recognition

    Manika Puri;Zhiwei Zhu;Jeffrey Lubin;Tom Pschar

  • Multi-camera calibration, object tracking and query generation

    F. Porikli;A. Divakaran

  • Generation of sports highlights using motion activity in combination with a common audio feature extraction framework

    Z. Xiong;Regunathan Radhakrishnan;Ajay Divakaran

Frequent Co-Authors

Anthony Vetro
Anthony Vetro Mitsubishi Electric (United States)
Huifang Sun
Huifang Sun Mitsubishi Electric (United States)
Lexing Xie
Lexing Xie Australian National University
Shih-Fu Chang
Shih-Fu Chang Columbia University
Harpreet Sawhney
Harpreet Sawhney Microsoft (United States)
Thomas S. Huang
Thomas S. Huang University of Illinois at Urbana-Champaign
Clifton Forlines
Clifton Forlines Draper Labs
B.S. Manjunath
B.S. Manjunath University of California, Santa Barbara
Yong Rui
Yong Rui Lenovo (China)
Shunichi Sekiguchi
Shunichi Sekiguchi Mitsubishi Electric (Japan)

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

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring Computer Science in the USA opens doors to a variety of related degree options and career paths, especially through flexible online programs. Students who are interested in the intersection of technology and law can pursue a criminal justice degree online accredited to prepare for roles that blend digital forensics and cyber law.

Those aiming to blend technology with business may consider the cheapest accredited online accounting degree for a strong background in digital finance, or pursue a best data science master's programs to specialize in analytics, machine learning, or big data—skills sought after in many industries.

Additionally, for students interested in technology's role in the built environment, an online bachelor's in construction management can provide expertise at the intersection of engineering, management, and innovation.

These pathways offer the flexibility of online study, diverse career opportunities, and the potential for specialization, all vital in today’s digital-driven job market.

Best Scientists Citing Ajay Divakaran

Trending Scientists

Recently Published Articles