Like Egocentric Vision on Facebook
|
|
Alireza Fathi
College of Computing Email: afathi3@gatech.edu
|
I am currently a Ph.D. candidate at GeorgiaTech working with Jim Rehg. I worked with Greg Mori during my Masters. I have also closely worked with Jessica Hodgins, Frank Dellaert and John Krumm.
| News |
| Publications |
|
Modeling Actions through State Changes Alireza Fathi, James M. Rehg CVPR, 2013 (PDF) |
|
|
Learning to Recognize Daily Actions using Gaze Alireza Fathi, Yin Li, James M. Rehg ECCV, 2012 (PDF, Project Page) |
|
|
Detecting Eye Contact using Wearable Eye-Tracking Glasses Zhefan Ye, Yin Li, Alireza Fathi, Yi Han, Agata Rozga, Gergory D. Abowd, James M. Rehg 2nd Workshop on Pervasive Eye Tracking and Mobile Eye-based Interaction (in conjunction with UbiComp), 2012 (PDF) |
|
|
Social Interactions: A First-Person Perspective Alireza Fathi, Jessica K. Hodgins, James M. Rehg |
|
|
Understanding Egocentric Activities Alireza Fathi, Ali Farhadi, James M. Rehg |
|
|
Learning to Recognize Objects in Egocentric Activities Alireza Fathi, Xiaofeng Ren, James M. Rehg |
|
|
Combining Self Training and Active Learning for Video Segmentation Alireza Fathi, Maria Florina Balcan, Xiaofeng Ren, James M. Rehg |
|
|
Detecting Road Intersections from GPS Traces Alireza Fathi, John Krumm GIScience, 2010 (PDF) |
|
|
Action Recognition by Learning Mid-Level Motion Features Alireza Fathi, Greg Mori |
|
|
Human Pose Estimation using Motion Exemplars Alireza Fathi, Greg Mori ICCV, 2007 (PDF, Bibtex, More Information, Slides, Course Project that led to this paper) |
|
|
Voice Synthesis using the Generalized Pressure-Controlled Valve Tamara Smyth, Alireza Fathi International Computer Music Conference (ICMC), 2008 (PDF) |
|
|
A Standard Workflow for Illumination-Invariant Image Extraction Mark S. Drew, Muntaseer Salahuddin, Alireza Fathi 15th Color and Imaging Conference, 2007 (PDF) |
|
|
EasySLAM Alireza Fathi, Alex Cunninghum, Balmanohar Paluri, Kai Ni and Frank Dellaert GVU Technical Report (GIT-GVU-10-03), 2010. (Link) |
|
|
Local Exponential Maps: Towards Massively Distributed Multi-Robot Mapping Frank Dellaert, Alireza Fathi, Alex Cunninghum, Balmanohar Paluri, Kai Ni GVU Technical Report(GIT-GVU-10-04), 2010. (Link) |
|
|
Poseidon Team Description Paper Nasrin Mostafazadeh, Saba Ardeshiri, Sepideh Movaghati, Shadi Hariri, Zeinab Jahanzad, Alireza Fathi, Majid Valipour
Ranked 2nd in Rescue Simulation League, Robocup 2006, Bremen, Germany (PDF) |
|
|
Impossibles Sony Aibo 4-Legged RoboCup Technical report Saman Aliari Zonouz, Hamid Reza Vaezi Joze, Siavash Rahbar, Majid Valipour, Alireza Fathi RoboCup 2006, Bremen, Germany. (PDF) |
|
|
Impossibles Sony Aibo 4-Legged RoboCup Team Description Paper Hamid Reza Vaezi Joze, Saman Aliari Zonouz, Siavash Rahbar, Majid Valipour, Alireza Fathi RoboCup 2006, Bremen, Germany. (PDF) |
|
|
Impossibles Team Description Paper Jafar Habibi, Alireza Fathi, Saeed Hassanpour, Mohammad Reza Ghodsi, Behzad Sadjadi, Hamid Reza Vaezi, Majid Valipour Ranked 1st in Rescue Similation League, RoboCup 2005, Osaka, Japan (PDF) |
| Invited Talks |
An Egocentric Paradigm for Learning to Understand Daily Activities
| Datasets/Software |
| Interactive Image Segmentation Toolbox |
| My Computer Vision Toolbox |
![]() |
GTEA Gaze(+) |
![]() |
Social Interactions at Disney parks |
![]() |
Georgia Tech Egocentric Activities (GTEA) |
| Projects |
Egocentric (First-Person) Vision: An egocentric vision system, is a framework consisting of a wearable camera that continuoulsy captures the scene in front of the first-person. In particular, I define an egocentric vision system as a framework that leverages different levels of first-person attention to identify important objects and faces in the scene that contribute to subject's activities. First-person's attitude, including where she looks (gaze) and what she does (hands manipulating objects) provide an invaluable context for determining the objects that grab her attention at any given time. Our goal is to use these structured sources of information coming from first-person in order to enable weakly supervised recognition of objects and activities.
Video and Image Segmentation: I believe that segmentation is probably the most fundamental problem in computer vision. If segmentation is solved, many of the big challenges in the field become trivial.
Action Recognition (ICCV07, CVPR08, ICCV11, CVPR12, MSc Thesis): I aim at developing action recognition techniques that rely on semantically meaningful features which capture interaction of objects with each other. This is in contrast to state of the art techniques that are based on space-time interest points or point trajectories.
Human Pose Estimation:
Localization and Mapping:
Color Constancy and Illumination Invariance:
RoboCup:
Other:
| Courses |
| Services |
| Co-Chair of 2nd IEEE Workshop on Egocentric (First-Person) Vision in Conjunction with CVPR 2012. |
| Program Committee member of IEEE International Conference on Automatic Face and Gesture Recognition (FG) 2013. |
| Program Committee member of AAAI 2012. |
| Reviewer of IEEE Transaction on Pattern Analysis and Machine Intelligence (PAMI). |
| Reviewer of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). |
| Reviewer of International Conference on Computer Vision (ICCV). |
| Reviewer of British Machine Vision Conference (BMVC). |
| Reviewer of ACM Conference on Ubiquitous Computing (UbiComp). |
| Reviewer of IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). |
| Useful Links |
| Experience |
Teaching Experience:
Research Experience:
Work Experience:
Languages:
| Fun |
This video is seen by 20,000 people by now (Nov 2010)