Xiaofeng Ren

Intel Research Seattle
1100 NE 45th St., 6th Floor
Seattle, WA 98105

Phone:
Fax:
Email:		 (206) 545-2523
(206) 633-6504
xiaofeng.ren at intel.com

I am co-organizing the First Workshop on Egocentric Vision in conjunction with CVPR '09. Please check out the workshop website and the program. Our egocentric object recognition dataset will soon be available here.

I have recently joined Intel Research Seattle. I had been a research assistant professor at the Toyota Technological Institute at Chicago (TTI-C) for 2006-2008. I received my Ph.D. from UC Berkeley, under the supervision of Jitendra Malik.

My research is in the areas of computer vision and artificial intelligence. My current interests are mainly in Mid-level Vision and its integration with both low-level image signal and high-level object knowledge. I have worked on contour grouping, image segmentation, figure/ground labeling, finding people in images as well as tracking and segmenting people in video.


Research

Multi-Scale Improves Boundary Detection
Local Grouping for Optical Flow
Finding and Tracking People in Archive Films
Tracking as Repeated Figure/Ground Segmentation
Line-based Aspect Learning and Matching
Figure-ground organization in natural images
Cue Integration in Figure/Ground Labeling
Scale-Invariant Contour Completion using Conditional Random Fields
Using Shapemes for Mid-level Vision
A Scale-Invariant Image Representation: the CDT Graph
Pairwise Constraints between Human Body Parts
Learning Discriminative Models for Image Segmentation
Human Body Configuration from Bottom-Up: a Segmentation-based Approach
Contours in Natural Images and Scale Invariance
Superpixel: Empirical Studies and Applications

Publications