Lorenzo Torresani


Associate Professor of Computer Science

Visual Learning Group
Dartmouth College

6211 Sudikoff Lab, Hanover, NH 03755
Email:
lt@dartmouth.edu
Tel:  (603) 646.3048
Fax: (603) 646.
1672

 


recent news



  1. Bullet Winner of a Google Faculty Research Award.


  1. Bullet Recipient of the Susan and Gib Myers 1964 Dartmouth Faculty Fellowship for the
       2014-2015 academic year.

      

  2. Bullet New article to appear in IEEE TPAMI:
      
    Classemes and Other Classifier-based Features for Efficient Object Categorization,
       with A. Bergamo.


  1. Bullet New article to appear at WACV 2014:
      
    AutoCaption: Automatic Caption Generation for Personal Photos,
       with K. Ramnath, S. Baker, L. Vanderwende, M. El-Saban, S.N. Sinha, A. Kannan,

   N. Hassan, M. Galley, Y. Yang, D. Ramanan, A. Bergamo.


  1. Bullet New article accepted at ICLR 2014:
      
    EXMOVES: Classifier-based Features for Scalable Action Recognition,
       with D. Tran.


  1. Bullet Winner of a Neukom 2014 CompX grant.


  1. Bullet Thanks to Nvidia Corporation for supporting our research with a hardware donation.


  1. Bullet New article published in Pattern Recognition (March 2014):
      
    Learning Discriminative Localization from Weakly Labeled Data,
       with M.H. Nguyen, F. de la Torre, and Carsten Rother.


  1. Bullet New paper published in the Machine Learning Journal (February 2014):
      
    Learning what is where from unlabeled images: joint localization and clustering of
       foreground objects
    ,
       with A. Chandrashekar, and R. Granger.


  1. Bullet In Spring 2014 I will be teaching COSC 89/189, a seminar on “Deep Learning”.
       The prerequisite for this course is COSC 74/174 (Machine Learning). No exceptions.


  1. Bullet Invited speaker at the ICCV 2013 Workshop on “Large Scale Visual Commerce”.


  1. Bullet Our research on image-assisted Web search was featured in the Irish Times:

   ‘Secret sauce’ for web image searches.


  1. Bullet The Dartmouth ran a story about our SIGIR13 work:
      
    Torresani enhances search engine with image analysis.


  1. Bullet Software for extraction of classemes, PiCoDes & meta-classes.


  1. Bullet I received an Outstanding Reviewer award at CVPR 2013. Credit must also go to my
       students Alessandro Bergamo and Du Tran who helped me in the reviewing process.


  2. Bullet New paper at SIGIR 2013:
      
    What Can Pictures Tell Us About Web Pages? Improving Document Search using
       Images
    ,
       with S. Rodriguez-Vaamonde, and A. Fitzgibbon.


  1. Bullet New paper at CVPR 2013:
      
    Leveraging Structure from Motion to Learn Discriminative Codebooks for Scalable
       Landmark Classification
    ,
       with A. Bergamo, and S. Sinha.


  1. Bullet New paper at MobiSys 2013:
      
    CarSafe App: Alerting Drowsy and Distracted Drivers using Dual Cameras on
       Smartphones
    ,
       with C.W. You, N. Lane, F. Chen, R. Wang, Z. Chen, T. Bao, Y. Cheng, M. Lin,
       and A. Campbell.


  1. Bullet New paper published in IEEE TPAMI (February 2013):
      
    A Dual Decomposition Approach to Feature Correspondence,
       with V. Kolmogorov, and C. Rother.


  1. Bullet Invited speaker at the NIPS 2012 Workshop “Big Data Meets Computer Vision”.


  1. Bullet New paper at ECCV 2012.

   Measuring Image Distances via Embedding in a Semantic Manifold,

   with C. Fang.


  1. Bullet New paper at CVPR 2012:
      
    Meta-Class Features for Large-Scale Object Categorization on a Budget,
       with A. Bergamo.


  1. Bullet New paper at HotMobile 2012:
      
    WalkSafe: A Pedestrian Safety App for Mobile Phone Users Who Walk and Talk While Crossing Roads,
       with T. Wang, G. Cardone, A. Corradi, and A.T. Campbell.



research overview


My research interests are in computer vision, machine learning, and computer animation.
My current work is aimed at designing machine learning algorithms for scalable object recognition and image retrieval. I am also interested in the problem of learning models of human motion using video or motion capture data. You can read more about the research of my group here.


previous affiliations


Microsoft Research Cambridge, Machine Learning and Perception
Riya/Like.com
New York University, Computer Science
Stanford University, Computer Science
DigitalPersona
IRST
University of Milan, Computer Science