Elamur Research⌕
☰
home / authors / Roozbeh Mottaghi

Roozbeh Mottaghi

Roozbeh Mottaghi has 2 papers in our library, in 2017–2022, most of them on Question answering, Evaluation & benchmarks, Vision & language; often with Abhinav Gupta, Aniruddha Kembhavi, Christopher Clark.

2 papers in our library · 2017–2022

OpenAlex · h-index 36 · 124 works · 9,852 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 779 times in our library · 10 more in our library without a page yet · ⭐ Paper Stars ranking: #2855

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓University of WashingtonSeattle · United States2017–2026 · 17 paperscurrent🔬Allen Institute for Artificial IntelligenceSeattle · United States2015–2022 · 40 papers🎓Stanford UniversityStanford · United States2014–2016 · 5 papers🎓University of California, Los AngelesLos Angeles · United States2011–2013 · 5 papers🎓Simon Fraser UniversityBurnaby · Canada2005–2007 · 5 papers🏢MetaMenlo Park · United States2023–2024 · 4 papers🎓Georgia Institute of TechnologyAtlanta · United States2008–2009 · 2 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.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksArtificial Intelligence · 2 worksComputer Vision and Pattern Recognition · 2 worksArts and Humanities · 1 workEngineering · 1 workLanguage and Linguistics · 1 workControl and Systems Engineering · 1 work

🧭 Topics 3Research subjects and languages the work is about.Evaluation & benchmarks · 1 workQuestion answering · 1 workVision & language · 1 work

 Works by year

2020s

20221 paper

2010s

20171 paper

 Papers

The most cited first (OpenAlex and our library).

  1. A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge (2022 · 509 citations)
    Large pretrained vision–language models have nearly saturated many Visual Question Answering benchmarks. One reason is that the questions in these benchmarks are formulaic, need little knowledge beyond the picture, and require only shallow inference. A-OKVQA, an extension of the authors' earlier OK-VQA, addresses…
  2. AI2-THOR: An Interactive 3D Environment for Visual AI (2017 · 421 citations)
    AI2-THOR, developed mainly at the Allen Institute for AI, is a simulation platform for embodied and visual AI.

All works

12 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetKenneth Marino et al.2019 · 1,056 citations
  2. A-OKVQA: A Benchmark for Visual Question Answering using World KnowledgeLecture notes in computer scienceDustin Schwenk, Apoorv Khandelwal, Christopher Clark, et al.2022 · 509 citations
  3. AI2-THOR: An Interactive 3D Environment for Visual AIarXiv:1712.05474Eric Kolve, Roozbeh Mottaghi, Winson Han, et al.2017 · 421 citations
  4. Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetMitchell Wortsman et al.2019 · 249 citations
  5. RoboTHOR: An Open Simulation-to-Real Embodied AI Platform ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetMatt Deitke et al.2020 · 231 citations
  6. Visual Semantic Planning Using Deep Successor Representations ↗IEEE International Conference on Computer Vision (ICCV) · no summary yetYuke Zhu et al.2017 · 143 citations
  7. Bottom-Up Segmentation for Top-Down Detection ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetSanja Fidler et al.2013 · 129 citations
  8. Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetRoozbeh Mottaghi et al.2013 · 35 citations
  9. Human-Machine CRFs for Identifying Bottlenecks in Scene Understanding ↗IEEE Transactions on Pattern Analysis and Machine Intelligence · no summary yetRoozbeh Mottaghi et al.2015 · 24 citations
  10. Situated Instruction Following ↗Lecture notes in computer science · no summary yetSo Yeon Min et al.2024 · 5 citations
  11. Human-Machine CRFs for Identifying Bottlenecks in Holistic Scene Understanding ↗arXiv (Cornell University) · no summary yetRoozbeh Mottaghi et al.2014 · 1 citation
  12. 1Human-Machine CRFs for Identifying Bottlenecks in Holistic Scene Understanding ↗no summary yetRoozbeh Mottaghi et al.2016

 Co-authors here

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

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 779 times (of the 149,439 papers whose bibliographies we read); 132 citing papers with a page here →.

Updated

↑ back to top

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