Mohammad Rastegari

Research Scientist
Allen Institute for Artificial Intelligence (AI2)

2157 N Northlake Way Suite 110, Seattle, WA 98103
(206) 548-5600
mohammadr [at] allenai [dot] org

I am currently a researcher at the Allen Institute for Artificial Intelligence (AI2). My research goes around Computer Vision and Machine Learning. I recieved my PhD in Computer Science at the University of Maryland under the supervision of Prof. Larry Davis. I am a recipient of the 2014-2015 Facebook Fellowship Award.

C.V. or Google Scholar page or DBLP or LinkedIn page.

News

  • [2016.10.4] 4 papers have been submitted to ECCV 2016
  • [2014.11.15] Newtonian Image Understanding will appeare at CVPR 2016
  • [Past News]

    Research Interest

  • Computer Vision: Convolutional Neural Networks, Large Scale Visual Recognition, Binary Descriptors
  • Machine Learning: Deep Learning, Large Scale Discriminative Learning, Metric/Feature Learning
  • Computational Lingustic: Semantic Understanding, Visual Understanding from Textual Data
  • Education

  • PhD: Computer Science at University of Maryland(UMD) 2016
  • Visiting Scholar: Department of Computer Science at University of California at Berkeley(UCB)
  • Visiting Scholar: Department of Computer Science at University of Illinois at Urbana Champaign(UIUC)
  • PhD Student: Computer Science at Dartmouth College
  • Graduate Research: Computer Vision and Active Perception Laboratory (CVAP), Royal Institute of Technology(KTH), Stockhom, Sweden.
  • Graduate Research: Computer Vision Group Institute for Research in Fundamental Science (IPM). Tehran, Iran.
  • Master of Computer Engineering : Islamic Azad University Branch of Science and Research, Tehran, Iran.
  • Bachelor of Computer Engineering: Shomal University of Amol (SUA), Amol, Iran.
  • Research Internships

  • Research Intern: Disney Research Lab at Carnegie Mellon University(CMU) 2012
  • Research Intern: Adobe Research Lab at Seattle, WA 2013
  • Research Intern: Microsoft Research Lab at Cambridge, UK 2014
  • Research Intern: Microsoft Research Lab at Redmond, WA 2014
  • Research Intern: Facebook AI Research Lab at Menlo Park, CA 2015
  • Publications

    XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
    Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, Ali Farhadi
    arXive 2016
    [PDF]
    What happens if..." Learning to Predict the Effect of Forces in Image
    Roozbeh Mottaghi, Mohammad Rastegari, Abhinav Gupta, Ali Farhadi
    arXive 2016
    [PDF]
    G-CNN: an Iterative Grid Based Object Detector
    Mahyar Najibi, Mohammad Rastegari, Larry Davis
    International Conf. on Computer Vision and Pattern Recognition (CVPR) 2016
    [PDF] [VIDEO]
    Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images
    Roozbeh Mottaghi, Hessam Bagherinezhad, Mohammad Rastegari, Ali Farhadi
    IEEE International Conf. on Computer Vision and Pattern Recognition(CVPR) 2016
    [PDF]
    Class Consistent Multi-Modal Fusion with Binary Features
    Ashish Shrivastava, Mohammad Rastegari, Sumith Shekhar, Rama Chellappa, Larry Davis
    International Conf. on Computer Vision and Pattern Recognition (CVPR) 2015
    [PDF]
    Discriminative and Consistent Similarities in Instance-Level Multiple Instance Learning
    Mohammad Rastegari, Hannaneh Hajishirzi Ali Farhadi
    IEEE International Conf. on Computer Vision and Pattern Recognition(CVPR) 2015
    [PDF]
    Computationally Bounded Retrieval
    Mohammad Rastegari, Cem Keskin, Pushmeet Kohli, Shahram Izadi
    International Conf. on Computer Vision and Pattern Recognition (CVPR) 2015
    [PDF]
    Domain Adaptive Classification
    Fatemeh Mirrashed*, Mohammad Rastegari* (*:equal contribution)
    IEEE International Conference on Computer Vision (ICCV) 2013
    [PDF] [NOTE: We recently found the results reported for Berkeley dataset in this paper are not correct please do not use these results.]
    Predictable Dual-View Hashing
    Mohammad Rastegari, Jonghyun Choi, Shobeir Fakhraei, Hal Daume III and Larry S. Davis
    International Conf. on Machine Learning (ICML) 2013
    [PDF] [CODE]
    Adding Unlabeled Samples to Categories by Learned Attributes
    Jonghyun Choi, Mohammad Rastegari, Ali Farhadi and Larry S. Davis
    IEEE Conf. on Computer Vision Pattern Recognition (CVPR) 2013 (To appear)
    [PDF] [BiBTex]
    Multi-Attribute Queries: To Merge or Not To Merge?
    Mohammad Rastegari, Ali Diba, Devi Parikh and Ali Farhadi
    IEEE Conf. on Computer Vision Pattern Recognition (CVPR) 2013
    [PDF] [BiBTex]
    Attribute Discovery via Predictable Discriminative Binary Codes
    Mohammad Rastegari, Ali Farhadi and David Forsyth
    European Conference on Computer Vision (ECCV) 2012
    [PDF] [Supplementary] [CODE]
    Semantic Understanding of Professional Soccer Commentaries
    Hannaneh Hajishirzi, Mohammad Rastegari, Ali Farhadi and Jessica Hodgins
    Uncertainty in Artificial Intelligence (UAI) 2012
    [PDF] [Project Page]
    Scalable Object-Class Retrieval with Approximate and Top-k Ranking
    Mohammad Rastegari*, Chen Fang* and Lorenzo Torresani
    *:equal contribution International Conference on Computer Vision (ICCV) 2011
    [PDF] [Project Page]
    Max-Margin Content Based Image Search
    Mohammad Rastegari
    Course Project for Computer Vision at Dartmouth College, Fall 2010
    [PDF] [PPT]
    Object Detection using Pictorial Structure from Active Basis
    Babak Saleh, Mohammad Rastegari
    International Conference on Computer Vision Theory and Applications (VISAPP) 2010 (Oral)
    [PDF]
    Action Recognition in Large Scale Domain
    Mohammad Rastegari, Josephine Sullivan and Stefan Carlsson
    Technical Report (CVAP-KTH) 2009
    Cartoon Motion Capturing and Retargeting by Rigid Shape Manipulation
    Mohammad Rastegari, Mohammad Rouhani, Niloofar Gheissari, Mir Mohsen Pedram
    IEEE proceeding, Digital Image Computing Technique and Application (DICTA) 2009 (Oral)
    [PDF] [CODE]
    Multi-scale Cartoon Motion Capture and Retargeting without Shape Matching
    Mohammad Rastegari, Niloofar Gheissari
    IEEE proceeding, Digital Image Computing Technique and Application (DICTA) 2008
    [PDF] [CODE]
    System of linear differential equations and collocation method
    Masoud Saravi, Esmail Babolian, Mohammad Rastegari
    Mathematic Scientific Journal (MSJ), Volume 5, NO.2 , Autumn-Winter 2009-2010, Page: 79-87.
    [PDF]
    Solution of linear ODEs by a pseudo-spectral method with coefficient singularity
    Mohammad Rastegari, Masoud Saravi, Ronald England, M. T. Bromilow
    22nd Biennial Conference on Numerical Analysis University of Dundee 2007, Dundee, Scotland.
    An experimental method for modifying pseudo-spectral method for solving ODEs with singularity point
    Masoud Saravi, Esmail Babolian, Mohammad Rastegari
    36th Annual International Mathematics Conference of Iran sept, 2005, Yazd, Iran.
    Solving Critical Section Problem in Distributed System by Entangled Quantum Bits
    Mohammad Rastegari, Amir Masoud Rahmani
    Technical Report, Science and Research Branch of Islamic Azad University, Tehran (2007)
    [PDF] [PPT]
    Quantum Approach To Image Processing
    Mohammad Rastegari
    Bachelor Thesis, Shomal University, Amol (2007)
    [PDF]

    Invited Talk

  • University of Washington, Seattle, WA.
    Fast Object Detection and Newtonian Image Understanding
  • Oxford University at Oxford, UK.
    Rich and Efficient Visual Data Representation
  • University of Illinois at Urbana Champaign, IL.
    On Attribute Discovery and its Applications
  • University of Texas at Austin.
    On Attribute Discovery and its Applications
  •