World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
30
Citations
9852
World Ranking
13826
National Ranking
5493

Overview

Roozbeh Mottaghi is a researcher affiliated with the University of Washington in the United States, specializing in computer science with a strong focus on computer vision, artificial intelligence, and related subfields. Their work encompasses a wide range of topics including multimodal machine learning applications, human pose and action recognition, domain adaptation and few-shot learning, reinforcement learning in robotics, advanced image and video retrieval techniques, robot manipulation and learning, and explainable artificial intelligence (XAI).

The primary field of study for this researcher is computer science, with a total of 118 publications attributed to this area. Within computer science, Mottaghi's notable subfields include computer vision and pattern recognition, artificial intelligence, control and systems engineering, aerospace engineering, and computer science applications.

Frequent co-authors in their research include Aniruddha Kembhavi, Ali Farhadi, Dhruv Batra, Devendra Singh Chaplot, and Kiana Ehsani. Collaboration with these co-authors spans multiple projects and publications, reflecting sustained research partnerships.

Mottaghi has contributed extensively to several publication venues. The most frequent outlet for their work is arXiv (Cornell University), with 40 publications. Other notable venues include the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Proceedings of the AAAI Conference on Artificial Intelligence, and Lecture Notes in Computer Science.

Some recent papers that highlight their research areas are:

  • Simple but Effective: CLIP Embeddings for Embodied AI, 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects, 2020, arXiv (Cornell University)
  • Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks, 2022, arXiv (Cornell University)
  • Rearrangement: A Challenge for Embodied AI, 2020, arXiv (Cornell University)
  • Multi-Modal Answer Validation for Knowledge-Based VQA, 2022, Proceedings of the AAAI Conference on Artificial Intelligence

The research topics covered in these papers reflect Mottaghi's diverse interests, particularly in embodied AI, multimodal learning, and vision-language integration.

Best Publications

  • Target-driven visual navigation in indoor scenes using deep reinforcement learning

    Yuke Zhu;Roozbeh Mottaghi;Eric Kolve;Joseph J. Lim

  • The Role of Context for Object Detection and Semantic Segmentation in the Wild

    Roozbeh Mottaghi;Xianjie Chen;Xiaobai Liu;Nam-Gyu Cho

  • Beyond PASCAL: A benchmark for 3D object detection in the wild

    Yu Xiang;Roozbeh Mottaghi;Silvio Savarese

  • On Evaluation of Embodied Navigation Agents

    Peter Anderson;Angel X. Chang;Devendra Singh Chaplot;Alexey Dosovitskiy

  • Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts

    Xianjie Chen;Roozbeh Mottaghi;Xiaobai Liu;Sanja Fidler

  • AI2-THOR: An Interactive 3D Environment for Visual AI

    Eric Kolve;Roozbeh Mottaghi;Daniel Gordon;Yuke Zhu

  • OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge

    Kenneth Marino;Mohammad Rastegari;Ali Farhadi;Roozbeh Mottaghi

  • ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks

    Mohit Shridhar;Jesse Thomason;Daniel Gordon;Yonatan Bisk

  • ObjectNet3D: A Large Scale Database for 3D Object Recognition

    Yu Xiang;Wonhui Kim;Wei Chen;Jingwei Ji

  • Visual Semantic Navigation using Scene Priors

    Wei Yang;Xiaolong Wang;Ali Farhadi;Abhinav Gupta

  • Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning

    Mitchell Wortsman;Kiana Ehsani;Mohammad Rastegari;Ali Farhadi

  • Bottom-Up Segmentation for Top-Down Detection

    Sanja Fidler;Roozbeh Mottaghi;Alan Yuille;Raquel Urtasun

  • A-OKVQA: A Benchmark for Visual Question Answering Using World Knowledge

    Unknown

  • SeGAN: Segmenting and Generating the Invisible

    Kiana Ehsani;Roozbeh Mottaghi;Ali Farhadi

  • ProcTHOR: Large-Scale Embodied AI Using Procedural Generation

    Unknown

  • Visual Semantic Planning Using Deep Successor Representations

    Yuke Zhu;Daniel Gordon;Eric Kolve;Dieter Fox

  • ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects.

    Dhruv Batra;Aaron Gokaslan;Aniruddha Kembhavi;Oleksandr Maksymets

  • RoboTHOR: An Open Simulation-to-Real Embodied AI Platform

    Matt Deitke;Winson Han;Alvaro Herrasti;Aniruddha Kembhavi

  • Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images

    Roozbeh Mottaghi;Hessam Bagherinezhad;Mohammad Rastegari;Ali Farhadi

  • Simple but Effective: CLIP Embeddings for Embodied AI.

    Apoorv Khandelwal;Luca Weihs;Roozbeh Mottaghi;Aniruddha Kembhavi

  • Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning

    Yuke Zhu;Roozbeh Mottaghi;Eric Kolve;Joseph J. Lim

  • Rearrangement: A Challenge for Embodied AI.

    Dhruv Batra;Angel X. Chang;Sonia Chernova;Andrew J. Davison

  • Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks

    Unknown

  • “What Happens If...” Learning to Predict the Effect of Forces in Images

    Roozbeh Mottaghi;Mohammad Rastegari;Abhinav Gupta;Abhinav Gupta;Ali Farhadi;Ali Farhadi

  • Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts

    Xianjie Chen;Roozbeh Mottaghi;Xiaobai Liu;Sanja Fidler

  • Visual Room Rearrangement

    Luca Weihs;Matt Deitke;Aniruddha Kembhavi;Roozbeh Mottaghi

Frequent Co-Authors

Ali Farhadi
Ali Farhadi University of Washington
Abhinav Gupta
Abhinav Gupta Carnegie Mellon University
Alan L. Yuille
Alan L. Yuille Johns Hopkins University
Sanja Fidler
Sanja Fidler University of Toronto
Raquel Urtasun
Raquel Urtasun University of Toronto
Yuke Zhu
Yuke Zhu The University of Texas at Austin
Silvio Savarese
Silvio Savarese Stanford University
Yejin Choi
Yejin Choi Stanford University
Dieter Fox
Dieter Fox University of Washington
Li Fei-Fei
Li Fei-Fei Stanford University

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

Expanding your educational journey in computer science can take many forms, with flexible online programs now widely available. For students who may not have a strong academic background, exploring online colleges that accept 2.0 gpa offers an accessible way to start or continue your studies. These institutions help more learners pursue tech-driven careers regardless of their previous grades.

Interested in combining technology with the environment? Branching out with an environmental science degree opens doors beyond strictly IT roles. Discover what can i do with an environmental science degree—from sustainable energy to public policy—blending computing skills with pressing global needs.

For those eager to enter the workforce quickly, consider an accelerated computer science degree online. These programs help motivated students earn credentials faster, preparing them for in-demand tech positions.

If affordability is a priority, you may also want to explore related fields. Some of the cheapest online environmental science degree options combine technical education and cost-effectiveness, supporting diverse career pathways in engineering, analysis, and research.

Best Scientists Citing Roozbeh Mottaghi

Trending Scientists

Recently Published Articles