World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
31
Citations
15374
World Ranking
13325
National Ranking
5330

Overview

Amir Roshan Zamir is affiliated with Stanford University in the United States and has contributed extensively to the field of computer science, with a strong focus on computer vision and artificial intelligence. Their research spans a variety of specialized areas including advanced neural network applications, domain adaptation and few-shot learning, multimodal machine learning applications, advanced vision and imaging, robotics and sensor-based localization, adversarial robustness in machine learning, and anomaly detection techniques and applications.

Their publication record includes significant papers such as "UCF-101: A dataset of 101 human actions classes from videos in the wild" (2024, arXiv, Cornell University), "Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans" (2021, 2021 IEEE/CVF International Conference on Computer Vision), "CLIPasso" (2022, ACM Transactions on Graphics), "3D Common Corruptions and Data Augmentation" (2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition), and "Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation" (2020, arXiv, Cornell University).

Amir Roshan Zamir collaborates frequently with numerous colleagues, including Roman Bachmann, Andrei Atanov, Oğuzhan Fatih Kar, Teresa Yeo, and Alexander F. Sax. These collaborations reflect a network of joint research efforts across multiple projects and publications.

Their research contributions have been published primarily in notable venues with regular appearances in arXiv (Cornell University), which accounts for 22 publications. Other venues include the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), ACM Transactions on Graphics, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), and Lecture Notes in Computer Science.

Their work focuses on several intersecting subfields of study within computer science: computer vision and pattern recognition, artificial intelligence, aerospace engineering, computer graphics and computer-aided design, and computational mechanics. These subfields correspond to the range of topics addressed in their body of work.

Best Publications

  • UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

    Khurram Soomro;Amir Roshan Zamir;Mubarak Shah

  • 3D Semantic Parsing of Large-Scale Indoor Spaces

    Iro Armeni;Ozan Sener;Amir R. Zamir;Helen Jiang

  • Structural-RNN: Deep Learning on Spatio-Temporal Graphs

    Ashesh Jain;Amir R. Zamir;Silvio Savarese;Ashutosh Saxena

  • Taskonomy: Disentangling Task Transfer Learning

    Amir R. Zamir;Alexander Sax;William Shen;Leonidas Guibas

  • Joint 2D-3D-Semantic Data for Indoor Scene Understanding

    Iro Armeni;Sasha Sax;Amir Roshan Zamir;Silvio Savarese

  • Gibson Env: Real-World Perception for Embodied Agents

    Fei Xia;Amir R. Zamir;Zhiyang He;Alexander Sax

  • On Evaluation of Embodied Navigation Agents

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

  • The THUMOS challenge on action recognition for videos “in the wild”

    Haroon Idrees;Amir Roshan Zamir;Yu-Gang Jiang;Alex Gorban

  • GMCP-Tracker: global multi-object tracking using generalized minimum clique graphs

    Amir Roshan Zamir;Afshin Dehghan;Mubarak Shah

  • Accurate image localization based on google maps street view

    Amir Roshan Zamir;Mubarak Shah

  • Action Recognition in Realistic Sports Videos

    Khurram Soomro;Amir R. Zamir

  • Image Geo-Localization Based on MultipleNearest Neighbor Feature Matching UsingGeneralized Graphs

    Amir Roshan Zamir;Mubarak Shah

  • Which Tasks Should Be Learned Together in Multi-task Learning?

    Trevor Standley;Amir Zamir;Dawn Chen;Leonidas Guibas

  • 3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera

    Iro Armeni;Zhi-Yang He;Amir Zamir;Junyoung Gwak

  • CLIPasso

    Unknown

  • Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets From 3D Scans

    Ainaz Eftekhar;Alexander Sax;Jitendra Malik;Amir Zamir

  • MultiMAE: Multi-modal Multi-task Masked Autoencoders

    Unknown

  • Taskonomy: Disentangling Task Transfer Learning.

    Amir Roshan Zamir;Amir Roshan Zamir;Alexander Sax;William B. Shen;Leonidas J. Guibas

  • Feedback Networks

    Amir R. Zamir;Te-Lin Wu;Lin Sun;William B. Shen

  • Feedback Networks

    Unknown

  • Taskonomy: Disentangling Task Transfer Learning

    Amir Zamir;Amir Zamir;Alexander Sax;William Shen;Leonidas Guibas

  • Unsupervised Semantic Parsing of Video Collections

    Ozan Sener;Amir R. Zamir;Silvio Savarese;Ashutosh Saxena

  • Generic 3D Representation via Pose Estimation and Matching

    Amir Roshan Zamir;Tilman Wekel;Pulkit Agrawal;Colin Wei

  • Semantic Cross-View Matching

    Francesco Castaldo;Amir Zamir;Roland Angst;Francesco Palmieri

  • An Information-Theoretic Approach to Transferability in Task Transfer Learning

    Yajie Bao;Yang Li;Shao-Lun Huang;Lin Zhang

  • Robust Learning Through Cross-Task Consistency

    Amir Zamir;Alexander Sax;Teresa Yeo;Oğuzhan Kar

  • 3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera

    Iro Armeni;Zhi-Yang He;JunYoung Gwak;Amir R. Zamir

Frequent Co-Authors

Silvio Savarese
Silvio Savarese Stanford University
Jitendra Malik
Jitendra Malik University of California, Berkeley
Leonidas J. Guibas
Leonidas J. Guibas Stanford University
Mubarak Shah
Mubarak Shah University of Central Florida
Ashutosh Saxena
Ashutosh Saxena Cornell University
Martin Fischer
Martin Fischer Stanford University
Luc Van Gool
Luc Van Gool Institute for Computer Science, Artificial Intelligence and Technology (INSAIT)
Richard Szeliski
Richard Szeliski University of Washington
Rahul Sukthankar
Rahul Sukthankar Google (United States)
Yuke Zhu
Yuke Zhu The University of Texas at Austin

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 related online degrees can open up diverse opportunities in computer science and technology. For those looking to advance quickly, quick masters degrees online make it possible to earn an advanced credential in a shorter time frame. These programs can be ideal if you’re eager to accelerate your career or pivot into new tech-focused roles.

When choosing the right program, consider what the job market demands. If you want a solid return on your educational investment, find out which master's degree is most in demand in USA. Highly sought-after computer science fields often include data science, cybersecurity, and artificial intelligence.

Not everyone is ready to commit to a master’s program. Some students start with 1 year associate degree programs online as a faster and more affordable pathway into tech. This option can provide valuable skills and help you enter the workforce quickly.

Cost is also a key consideration. If budget is a concern, look for cheap online college classes to complete prerequisites, skill upgrades, or certifications without breaking the bank. These flexible options ensure you can move forward in computer science no matter where you start.

Best Scientists Citing Amir Roshan Zamir

Trending Scientists

Recently Published Articles