Overview:
icon

A large precentage of the images and video that exists today - from personal photo collections to webcams to online images - contain people. We are working on automated methods for analyzing people from such data. Such methods have a variety of applications from pedestrian detection for autonomous vehicles to surveillance-based security to motion capture for computer graphics & interaction. We are also interested in higher-level activity models that can capture human actions and behavior.

Publications:
icon
Understanding Everyday Hands in Action from RGB-D Images
Grégory Rogez, James Supančič, Deva Ramanan
IEEE International Conference on Computer Vision, 2015.
[pdf]
icon
First-Person Pose Recognition using Egocentric Workspaces
Grégory Rogez, James Supančič, Deva Ramanan
CVPR, 2015.
[pdf]
icon
Occlusion Coherence: Detecting and Localizing Occluded Faces
Golnaz Ghiasi, Charless Fowlkes
arXiv:, 2015, abs/1506.08347.
[pdf]
icon
Using segmentation to predict the absence of occluded parts
Golnaz Ghiasi, Charless Fowlkes
British Machine Vision Conference (BMVC), 2015.
[pdf]
icon
Parsing Occluded People
Golnaz Ghiasi, Yi Yang, Deva Ramanan, Charless Fowlkes
CVPR, 2014.
[pdf]
icon
Occlusion Coherence: Localizing Occluded Faces with a Hierarchical Deformable Part Model
Golnaz Ghiasi, Charless Fowlkes
CVPR, 2014.
[pdf]
icon
3D Hand Pose Detection in Egocentric {RGB-D} Images
Grégory Rogez, James Supančič, Maryam Khademi, J.M.M. Montiel, Deva Ramanan
CoRR, 2014, abs/1412.0065.
[pdf]
icon
Monocular 3-D Gait Tracking in Surveillance Scenes
Grégory Rogez, Jonathan Rihan, J.J. Guerrero, Carlos Orrite
Cybernetics, IEEE Transactions on, 2013, PP, 99.
[pdf]
icon
Egovision4Health - Assessing Activities of Daily Living from a Wearable RGB-D Camera for In-Home Health Care Applications
Grégory Rogez, Deva Ramanan, J.M.M. Montiel
ERCIM News, 2013, 2013, 95, 18-19.
[pdf]
icon
Fast Human Pose Detection Using Randomized Hierarchical Cascades of Rejectors
Grégory Rogez, Jonathan Rihan, Carlos Orrite, Philip Torr
International Journal of Computer Vision, 2012, 99, 1, 25-52.
[pdf]
icon
A Large-scale Benchmark Dataset for Event Recognition in Surveillance Video
Sangmin Oh, Anthony Hoogs, Amitha Perera, Naresh Cuntoor, C.-C. Chen, Jong Lee, Saurajit Mukherjee, J. Aggarwal, Hyungtae Lee, Larry Davis, Eran Swears, Xioyang 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
CVPR, 2011.
[pdf]
icon
Where's Waldo: Matching People in Images of Crowds
Rahul Garg, Deva Ramanan, Steve Seitz, Noah Snavely
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.
[pdf]
icon
Shape-based Pedestrian Parsing
Yihang Bo, Charless Fowlkes
CVPR, 2011.
[pdf]
icon
Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects
Hamed Pirsiavash, Deva Ramanan, Charless Fowlkes
IEEE conference on Computer Vision and Pattern Recognition (CVPR), 2011.
[pdf]
icon
Efficiently Scaling Up Video Annotation with Crowdsourced Marketplaces
Carl Vondrick, Deva Ramanan, Donald Patterson
Proc. of the European Conference on Computer Vision, 2010.
[pdf]
icon
SEMARTCam Scheduler - Semantics Driven Real-Time Data Collection from Indoor Camera Networks to Maximize Event Detection
Ronen Vaisenberg, Sharad Mehrotra, Deva Ramanan
Journal of Real-Time Image Processing (JRTIP), 2010.
[pdf]
icon
Robust Tracking of the Upper Limb for Functional Stroke Assessment
Sonya Allin, Nancy Baker, Emily Eckel, Deva Ramanan
IEEE Transactions on Neural Systems and Rehabilitation Engineering (NSRE), 2010.
[pdf]
icon
Discriminative models for static human-object interactions
Chaitanya Desai, Deva Ramanan, Charless Fowlkes
IEEE Conference on Computer Vision and Pattern Recognition, Workshop on Structured Prediction, 2010.
[pdf]
icon
Exploiting Semantics for Scheduling Data Collection From Sensors in Real-Time to Maximimize Event Detection
Ronen Vaisenberg, Sharad Mehrotra, Deva Ramanan
Multimedia and Computer Networks (MMCN), 2009.
[pdf]
icon
Leveraging Archival Video for Building Face Datasets
Deva Ramanan, Simon Baker, Sham Kakade
ICCV, 2007, 141.
[pdf]
icon
Learning to parse images of articulated bodies
Deva Ramanan
Advances in Neural Information Processing Systems 19, 2007, 1129--1136.
[pdf]
icon
Assessment of Post Stroke Functioning Using Machine Vision
Sonya Allin, Deva Ramanan
IAPR Conference on Machine Vision Applications (MVA), 2007.
[pdf]
icon
Using Segmentation to Verify Object Hypotheses
Deva Ramanan
CVPR, 2007, 1-8.
[pdf]
icon
Tracking People by Learning Their Appearance
Deva Ramanan, D.A. Forsyth, Andrew Zisserman
PAMI, 2007, 29, 1, 65-81.
[pdf]
icon
Training Deformable Models for Localization
Deva Ramanan, Cristian Sminchisescu
CVPR, 2006, I: 206-213.
[pdf]
icon
Computational studies of human motion: part 1, tracking and motion synthesis
David Forsyth, Okan Arikan, Leslie Ikemoto, James O'Brien, Deva Ramanan
Found. Trends. Comput. Graph. Vis., 2005, 1, 2-3, 77--254.
[pdf]
icon
Tracking People and Recognizing Their Activities
Deva Ramanan, D.A. Forsyth, Andrew Zisserman
CVPR, 2005, II: 1194.
[pdf]
icon
Automatic Annotation of Everyday Movements
Deva Ramanan, David Forsyth
Advances in Neural Information Processing Systems 16, 2004.
[pdf]
icon
Finding and tracking people from the bottom up
Deva Ramanan, D.A. Forsyth
CVPR, 2003, II: 467-474.
[pdf]