Search For:

Displaying 1-13 out of 13 total
Scalable object-class retrieval with approximate and top-k ranking
Found in: Computer Vision, IEEE International Conference on
By Mohammad Rastegari,Chen Fang,Lorenzo Torresani
Issue Date:November 2011
pp. 2659-2666
In this paper we address the problem of object-class retrieval in large image data sets: given a small set of training examples defining a visual category, the objective is to efficiently retrieve images of the same class from a large database. We propose ...
 
Simultaneous point matching and 3D deformable surface reconstruction
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Appu Shaji, Aydin Varol, Lorenzo Torresani, Pascal Fua
Issue Date:June 2010
pp. 1221-1228
It has been shown that the 3D shape of a deformable surface in an image can be recovered by establishing correspondences between that image and a reference one in which the shape is known. These matches can then be used to set-up a convex optimization prob...
 
Nonrigid Structure-from-Motion: Estimating Shape and Motion with Hierarchical Priors
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Lorenzo Torresani, Aaron Hertzmann, Chris Bregler
Issue Date:May 2008
pp. 878-892
This paper describes methods for recovering time-varying shape and motion of non-rigid 3D objects from uncalibrated 2D point tracks. For example, given a video recording of a talking person, we would like to estimate the 3D shape of the face at each instan...
 
Tracking and Modeling Non-Rigid Objects with Rank Constraints
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Lorenzo Torresani, Danny B. Yang, Eugene J. Alexander, Christoph Bregler
Issue Date:December 2001
pp. 493
This paper presents a novel solution for flow-based tracking and 3D reconstruction of deforming objects in monocular image sequences. A non-rigid 3D object undergoing rotation and deformation can be effectively approximated using a linear combination of 3D...
 
What Can Pictures Tell Us About Web Pages? Improving Document Search using Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Sergio Rodriguez-Vaamonde,Lorenzo Torresani,Andrew Fitzgibbon
Issue Date:February 2015
pp. 1
Traditional Web search engines do not use the images in the HTML pages to find relevant documents for a given query. Instead, they typically operate by computing a measure of agreement between the keywords provided by the user and only the text portion of ...
 
Classemes and Other Classifier-based Features for Efficient Object Categorization
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Alessandro Bergamo,Lorenzo Torresani
Issue Date:May 2014
pp. 1
This paper describes compact image descriptors enabling accurate object categorization with linear classification models, which offer the advantage of being efficient to both train and test. The shared property of our descriptors is the use of classifiers ...
 
AutoCaption: Automatic caption generation for personal photos
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Krishnan Ramnath,Simon Baker,Lucy Vanderwende,Motaz El-Saban,Sudipta N. Sinha,Anitha Kannan,Noran Hassan,Michel Galley,Yi Yang,Deva Ramanan,Alessandro Bergamo,Lorenzo Torresani
Issue Date:March 2014
pp. 1050-1057
AutoCaption is a system that helps a smartphone user generate a caption for their photos. It operates by uploading the photo to a cloud service where a number of parallel modules are applied to recognize a variety of entities and relations. The outputs of ...
   
Leveraging Structure from Motion to Learn Discriminative Codebooks for Scalable Landmark Classification
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Alessandro Bergamo,Sudipta N. Sinha,Lorenzo Torresani
Issue Date:June 2013
pp. 763-770
In this paper we propose a new technique for learning a discriminative codebook for local feature descriptors, specifically designed for scalable landmark classification. The key contribution lies in exploiting the knowledge of correspondences within sets ...
 
What can pictures tell us about web pages?: improving document search using images
Found in: Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval (SIGIR '13)
By Andrew Fitzgibbon, Lorenzo Torresani, Sergio Rodriguez-Vaamonde
Issue Date:July 2013
pp. 849-852
Traditional Web search engines do not use the images in the HTML pages to find relevant documents for a given query. Instead, they typically operate by computing a measure of agreement between the keywords provided by the user and only the text portion of ...
     
CarSafe: a driver safety app that detects dangerous driving behavior using dual-cameras on smartphones
Found in: Proceedings of the 2012 ACM Conference on Ubiquitous Computing (UbiComp '12)
By Andrew T. Campbell, Chuang-Wen You, Giuseppe Cardone, Hong Lu, Lorenzo Torresani, Martha Montes-de-Oca, Nicholas D. Lane, Thomas J. Bao
Issue Date:September 2012
pp. 671-672
Driving while being tired or distracted is dangerous. We are developing the CafeSafe app for Android phones, which fuses information from both front and back cameras and others embedded sensors on the phone to detect and alert drivers to dangerous driving ...
     
CarSafe demo: supporting driver safety using dual-cameras on smartphones
Found in: Proceedings of the 2012 ACM Conference on Ubiquitous Computing (UbiComp '12)
By Andrew T. Campbell, Chuang-Wen You, Giuseppe Cardone, Hong Lu, Lorenzo Torresani, Martha Montes-de-Oca, Nicholas D. Lane, Thomas J. Bao
Issue Date:September 2012
pp. 547-547
We demonstrate CarSafe, a driver safety application for Android phones that fuses information from both front and back cameras and others embedded sensors on the phone to detect and alert drivers to dangerous driving conditions in and outside of the car. I...
     
WalkSafe: a pedestrian safety app for mobile phone users who walk and talk while crossing roads
Found in: Proceedings of the Twelfth Workshop on Mobile Computing Systems & Applications (HotMobile '12)
By Antonio Corradi, Lorenzo Torresani, Andrew T. Campbell, Giuseppe Cardone, Tianyu Wang
Issue Date:February 2012
pp. 1-6
Research in social science has shown that mobile phone conversations distract users, presenting a significant impact to pedestrian safety; for example, a mobile phone user deep in conversation while crossing a street is generally more at risk than other pe...
     
Unsupervised hierarchical modeling of locomotion styles
Found in: Proceedings of the 26th Annual International Conference on Machine Learning (ICML '09)
By Lorenzo Torresani, Wei Pan
Issue Date:June 2009
pp. 1-8
This paper describes an unsupervised learning technique for modeling human locomotion styles, such as distinct related activities (e.g. running and striding) or variations of the same motion performed by different subjects. Modeling motion styles requires ...
     
 1