Search For:

Displaying 1-23 out of 23 total
Tracking People by Learning Their Appearance
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Deva Ramanan, David A. Forsyth, Andrew Zisserman
Issue Date:January 2007
pp. 65-81
An open vision problem is to automatically track the articulations of people from a video sequence. This problem is difficult because one needs to determine both the number of people in each frame and estimate their configurations. But, finding people and ...
 
Articulated Human Detection with Flexible Mixtures of Parts
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yi Yang,Deva Ramanan
Issue Date:December 2013
pp. 2878-2890
We describe a method for articulated human detection and human pose estimation in static images based on a new representation of deformable part models. Rather than modeling articulation using a family of warped (rotated and foreshortened) templates, we us...
 
N-best maximal decoders for part models
Found in: Computer Vision, IEEE International Conference on
By Dennis Park,Deva Ramanan
Issue Date:November 2011
pp. 2627-2634
We describe a method for generating N-best configurations from part-based models, ensuring that they do not overlap according to some user-provided definition of overlap. We extend previous N-best algorithms from the speech community to incorporate non-max...
 
AVSS 2011 demo session: A large-scale benchmark dataset for event recognition in surveillance video
Found in: 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2011)
By Sangmin Oh,Anthony Hoogs,Amitha Perera,Naresh Cuntoor,Chia-Chih Chen,Jong Taek Lee,Saurajit Mukherjee,J. K. Aggarwal,Hyungtae Lee,Larry Davis,Eran Swears,Xiaoyang Wang,Qiang Ji,Kishore Reddy,Mubarak Shah,Carl Vondrick,Hamed Pirsiavash,Deva Ramanan,Jenny Yuen,Antonio Torralba,Bi Song,Anesco Fong,Amit Roy-Chowdhury,Mita Desai
Issue Date:August 2011
pp. 527-528
Summary form only given. We present a concept for automatic construction site monitoring by taking into account 4D information (3D over time), that is acquired from highly-overlapping digital aerial images. On the one hand today's maturity of flying micro ...
   
Local Distance Functions: A Taxonomy, New Algorithms, and an Evaluation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Deva Ramanan, Simon Baker
Issue Date:April 2011
pp. 794-806
We present a taxonomy for local distance functions where most existing algorithms can be regarded as approximations of the geodesic distance defined by a metric tensor. We categorize existing algorithms by how, where, and when they estimate the metric tens...
 
Layered object detection for multi-class segmentation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yi Yang, Sam Hallman, Deva Ramanan, Charless Fowlkes
Issue Date:June 2010
pp. 3113-3120
We formulate a layered model for object detection and multi-class segmentation. Our system uses the output of a bank of object detectors in order to define shape priors for support masks and then estimates appearance, depth ordering and labeling of pixels ...
 
Object Detection with Discriminatively Trained Part-Based Models
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Pedro F. Felzenszwalb, Ross B. Girshick, David McAllester, Deva Ramanan
Issue Date:September 2010
pp. 1627-1645
We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object detection challenges. While deformable ...
 
A discriminatively trained, multiscale, deformable part model
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Pedro Felzenszwalb, David McAllester, Deva Ramanan
Issue Date:June 2008
pp. 1-8
This paper describes a discriminatively trained, multiscale, deformable part model for object detection. Our system achieves a two-fold improvement in average precision over the best performance in the 2006 PASCAL person detection challenge. It also outper...
 
Increasing the density of Active Appearance Models
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Krishnan Ramnath, Simon Baker, Iain Matthews, Deva Ramanan
Issue Date:June 2008
pp. 1-8
Active Appearance Models (AAMs) typically only use 50–100 mesh vertices because they are usually constructed from a set of training images with the vertices hand-labeled on them. In this paper, we propose an algorithm to increase the density of an AAM. Our...
 
Leveraging archival video for building face datasets
Found in: Computer Vision, IEEE International Conference on
By Deva Ramanan, Simon Baker, Sham Kakade
Issue Date:October 2007
pp. 1-8
We introduce a semi-supervised method for building large, labeled datasets of faces by leveraging archival video. Specifically, we have implemented a system for labeling 11 years worth of archival footage from a television show. We have compiled a dataset ...
 
Using Segmentation to Verify Object Hypotheses
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Deva Ramanan
Issue Date:June 2007
pp. 1-8
We present an approach for object recognition that combines detection and segmentation within a efficient hypothesize/test framework. Scanning-window template classifiers are the current state-of-the-art for many object classes such as faces, cars, and ped...
 
Training Deformable Models for Localization
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Deva Ramanan, Cristian Sminchisescu
Issue Date:June 2006
pp. 206-213
We present a new method for training deformable models. Assume that we have training images where part locations have been labeled. Typically, one fits a model by maximizing the likelihood of the part labels. Alternatively, one could fit a model such that,...
 
Detecting, Localizing and Recovering Kinematics of Textured Animals
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Deva Ramanan, D. A. Forsyth, Kobus Barnard
Issue Date:June 2005
pp. 635-642
We develop and demonstrate an object recognition system capable of accurately detecting, localizing, and recovering the kinematic configuration of textured animals in real images. We build a deformation model of shape automatically from videos of animals a...
 
Strike a Pose: Tracking People by Finding Stylized Poses
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Deva Ramanan, D. A. Forsyth, Andrew Zisserman
Issue Date:June 2005
pp. 271-278
We develop an algorithm for finding and kinematically tracking multiple people in long sequences. Our basic assumption is that people tend to take on certain canonical poses, even when performing unusual activities like throwing a baseball or figure skatin...
 
Tracking People and Recognizing Their Activities
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Deva Ramanan, David Forsyth, Andrew Zisserman
Issue Date:June 2005
pp. 1194
No summary available.
   
Using Temporal Coherence to Build Models of Animals
Found in: Computer Vision, IEEE International Conference on
By Deva Ramanan, D. A. Forsyth
Issue Date:October 2003
pp. 338
This paper describes a system that can build appearance models of animals automatically from a video sequence of the relevant animal with no explicit supervisory information. The video sequence need not have any form of special background. Animals are mode...
 
Finding and Tracking People from the Bottom Up
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Deva Ramanan, D. A. Forsyth
Issue Date:June 2003
pp. 467
We describe a tracker that can track moving people in long sequences without manual initialization. Moving people are modeled with the assumption that, while configuration can vary quite substantially from frame to frame, appearance does not. This leads to...
 
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 ...
   
Histograms of Sparse Codes for Object Detection
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Xiaofeng Ren,Deva Ramanan
Issue Date:June 2013
pp. 3246-3253
Object detection has seen huge progress in recent years, much thanks to the heavily-engineered Histograms of Oriented Gradients (HOG) features. Can we go beyond gradients and do better than HOG? We provide an affirmative answer by proposing and investigati...
 
Exploring Weak Stabilization for Motion Feature Extraction
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Dennis Park,C. Lawrence Zitnick,Deva Ramanan,Piotr Dollar
Issue Date:June 2013
pp. 2882-2889
We describe novel but simple motion features for the problem of detecting objects in video sequences. Previous approaches either compute optical flow or temporal differences on video frame pairs with various assumptions about stabilization. We describe a c...
 
Self-Paced Learning for Long-Term Tracking
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By James Steven Supancic III,Deva Ramanan
Issue Date:June 2013
pp. 2379-2386
We address the problem of long-term object tracking, where the object may become occluded or leave-the-view. In this setting, we show that an accurate appearance model is considerably more effective than a strong motion model. We develop simple but effecti...
 
Scheduling sensors for monitoring sentient spaces using an approximate POMDP policy
Found in: 2013 IEEE International Conference on Pervasive Computing and Communications (PerCom)
By Ronen Vaisenberg,Alessio Della Motta,Sharad Mehrotra,Deva Ramanan
Issue Date:March 2013
pp. 141-150
We present a framework for sensor actuation and control in sentient spaces, in which sensors are used to observe a physical phenomena. We focus on sentient spaces that enable pervasive computing applications, such as smart video surveillance and situationa...
   
Visual object detection with deformable part models
Found in: Communications of the ACM
By David McAllester, Deva Ramanan, Pedro Felzenszwalb, Ross Girshick
Issue Date:September 2013
pp. 97-105
We describe a state-of-the-art system for finding objects in cluttered images. Our system is based on deformable models that represent objects using local part templates and geometric constraints on the locations of parts. We reduce object detection to cla...
     
 1