PeopleofSuperintelligence

Researcher

Sagnik Dhar

Sagnik Dhar is a computer vision researcher and software engineering director whose CVPR 2011 paper "Baby talk: Understanding and generating simple image descriptions" generated natural language descriptions of images. A Narotam Sekhsaria Foundation scholar, they studied computer science at Stony Brook University and wrote a 2010 thesis on predicting the aesthetics and interestingness of photos, advised by Dimitris Samaras, Tamara Berg and Alexander Berg. In 2011, they also published a CVPR paper with Vicente Ordonez and Tamara Berg under the thesis title, and in 2021 the Baby talk paper received the Longuet-Higgins Prize. After earlier work at Honda Research Institute and Sportvision, they work as Director, Software Engineering at Cariad, a Volkswagen Group company building automotive software.

Works
7
Citations
1,870
h-index
3

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2010

    A thesis at Stony Brook

    They study for a Master of Science in Computer Science at Stony Brook University on a Narotam Sekhsaria Foundation Scholarship. In 2010, they write the thesis "High Level Describable Attributes for Predicting Aesthetics and Interestingness" in the Department of Computer Science, advised by Dimitris Samaras, Tamara Berg and Alexander Berg.

  2. 2011

    The Baby talk paper

    In 2011, they coauthor "Baby talk: Understanding and generating simple image descriptions" at CVPR with Girish Kulkarni, Visruth Premraj, Siming Li, Yejin Choi, Alexander C. Berg and Tamara L. Berg. The system generates natural language descriptions from images, combining statistics from parsed text data with recognition algorithms from computer vision.

  3. 2011

    Aesthetics and interestingness paper

    Their second CVPR paper in 2011, written with Vicente Ordonez and Tamara L. Berg, carries the title of the thesis. It predicts image cues a person might use to judge a photo, grouped as compositional, content and sky-illumination attributes, and feeds them to an aesthetics classifier that also predicts the interestingness of Flickr photos.

  4. 2021

    A Longuet-Higgins Prize

    In 2021, the Baby talk paper wins the Longuet-Higgins Prize, a test-of-time award for CVPR papers with a significant impact on computer vision research. Dhar is one of its seven authors and one of three then-master's students among them.

  5. By 2022

    Director at Cariad

    By 2022, they work in California as Director, Software Engineering for Interior, Infotainment & Digital Experience at Cariad, a Volkswagen Group company building automotive software. Their earlier employers include Honda Research Institute and Sportvision.

Career

  1. 2011–2013Stony Brook University
  2. Volkswagen GroupDirector, Software Engineering for Interior, Infotainment & Digital Experience

Education

  1. 2010Stony Brook UniversityMaster of Science in Computer Science

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. BabyTalk: Understanding and Generating Simple Image Descriptions2013 · IEEE Transactions on Pattern Analysis and Machine Intelligence · 839 citationsWith Alexander Berg, Girish Kulkarni and Tamara Berg
  2. Baby talk: Understanding and generating simple image descriptions2011 · 521 citationsWith Alexander Berg, Girish Kulkarni and Tamara Berg
  3. High level describable attributes for predicting aesthetics and interestingness2011 · 508 citationsWith Tamara Berg
  4. Selective Querying and Other Proposals for a Less Congested Gnutella Network2007 · Springer eBooks · 2 citations
  5. Statistical Analysis and Compression of DNA using Weighted Probability Approach and Modified Run-Length Encoding2007 · Indian International Conference on Artificial Intelligence · 0 citations

From OpenAlex, as of 21 October 2026.

  1. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Stony Brook University. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  2. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Stony Brook University. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  3. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Stony Brook University. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  4. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Sagnik Dhar yet. Send us a free-licensed photo.

  1. Sagnik Dhar - NSF PG Scholarship Programme pg.nsfoundation.co.in. Checked 20 October 2026.
  2. "High Level Describable Attributes for Predicting Aesthetics and Intere" by Sagnik Dhar commons.library.stonybrook.edu. Checked 20 October 2026.
  3. Baby Talk: Understanding and Generating Simple Image Descriptions | ML Anthology mlanthology.org. Checked 20 October 2026.
  4. High Level Describable Attributes for Predicting Aesthetics and Interestingness | ML Anthology mlanthology.org. Checked 20 October 2026.
  5. PAMITC AWARDS | CVPR 2021 cvpr2021.thecvf.com. Checked 20 October 2026.
  6. Allen School News Archive » Gray sheep, golden cows, and everything in between: Yejin Choi earns Longuet-Higgins Prize in computer vision for enabling more precise image captions via natural language generation news.cs.washington.edu. Checked 20 October 2026.