Xiaofeng Ren

Amazon - Otter (SEA55)
2301 5th Ave., Seattle, WA 98109

xiaofenr at amazon dot com

We are hiring!! We are looking for motivated computer vision researchers and engineers at all levels to join our world-class team working on the shiny new business initiative at Amazon. If you love vision and want to change the world with it, this is the perfect opportunity. Please contact me and others for more information and/or apply through these links.

As of March 2013, I joined Amazon as a principal research scientist for the "Shiny New Project" that centers around computer vision. It's about time that computer vision makes a real impact in the real world on real people's lives :-) And we will try our best to make it happen at Amazon. I still have an affiliate position at University of Washington. (Current CV,Google Scholar).

I am interested in all aspects of computer vision, as I believe all are needed to solve it. Most recently I worked on using RGB-D (color+depth, a.k.a. Kinect style) cameras, ranging from 3D mapping and modeling to everyday object recognition. I worked on many other vision problems, including image descriptors, boundary detection, image segmentation, figure-ground grouping, object and pose recognition, human body detection and pose estimation, object segmentation and tracking, and optical flow. I had opportunities to work on vision-related problems in robotics and human-computer interaction.

I was a research scientist at Intel Labs during 2008-2013, working closely with faculty and students at University of Washington. Prior to sunny Seattle, I was a research assistant professor at the Toyota Technological Institute at Chicago (TTI-C). I received my Ph.D. from U.C. Berkeley in 2006, under the supervision of Jitendra Malik.

Recent Updates


(Old) Research Projects

Discriminative Viewpoint Classification
RGB-D Mapping
Egocentric Object Recognition
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