🧑‍🔬 Tamara Berg

Affiliations

• University of North Carolina at Chapel Hill · Chapel Hill, United States — current · 2013–2026 on 49 papers
• Meta (United States) · Menlo Park, United States — 2020–2022 on 7 papers
• Meta (United Kingdom) · London, United Kingdom — 2021–2022 on 2 papers
• Stony Brook University · Stony Brook, United States — 2008–2013 on 21 papers
• University of California, Berkeley · Berkeley, United States — 2004–2007 on 4 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

Topics

Question answering1Vision & language1

Papers

The most cited first (OpenAlex and our library).

1. ReferItGame: Referring to Objects in Photographs of Natural Scenes (2014 · 1 276 citations)
   The paper studies referring expression generation (REG), which means producing phrases that single out one object in an image.
2. Modeling Context in Referring Expressions (2016 · 1 165 citations)
   The paper addresses generating and comprehending referring expressions: phrases that single out one object in an image so a listener can find it.
3. TVQA: Localized, Compositional Video Question Answering (2018 · 669 citations)
   Video question answering has fallen behind image-based QA, partly because existing video QA datasets have notable weaknesses.

Also in our library

1 more work of theirs is in our library without a page here yet; it will appear as we publish them.

Co-authors here

4 co-authors with a page, the most papers together first.

• Licheng Yu ×2
• Alexander C. Berg
• Mohit Bansal
• Vicente Ordonez

Cited by

Papers of our library cite their works 534 times (of the 140 884 papers whose bibliographies we read); 54 citing papers with a page here →.

This page in Markdown → https://md.research.elamur.ai/free/en/authors/tamara-berg/