Yu Xiang's homepage

Biography

I am a Phd student in the Electrical Engineering and Computer Science Department at the University of Michigan. I joined the computer vision lab at the University of Michigan in 2010. My advisor is Prof. Silvio Savarese. My research focuses on understanding objects and scenes from images and videos, with emphasis on recognizing both semantic and 3D geometric properties of objects and scenes. My current work attempts to develop 3D object representation and recognition methods which can be useful for real world applications. I received my B.S. degree in computer science from Fudan University in 2007 and my M.S. degree in computer science from Fudan University in 2010. I did research on automatic image annotation under the supervision of Prof. Xiangdong Zhou for my master thesis. (CV)

News

  • 6/15/2014 Our work on multiview object tracking is accepted to ECCV 2014!
  • 5/18/2014 PASCAL3D+ version 1.1 is available now! Check it out to see how it can benefit your research!
  • 5/5/2014 I started a 3-month internship at NEC Labs America in Cupertino.
  • 2/15/2014 Our PASCAL3D+ benchmark (version 1.0) is released!
  • 1/30/2014 Our work on building a large scale dataset for 3D object detection and pose estimation is accepted to WACV 2014!
  • 10/5/2013 Our paper is accepted to the 3dRR workshop in conjunction with ICCV 2013.
  • 9/1/2013 I moved to Stanford as a visiting student.
  • Our paper has been accepted to the ECCV 2012 conference.
  • I received the Outstanding Master's Thesis Award of Shanghai.
  • Our CVPR 2012 paper and code are available!

Publications

Since 2010 (Image and the 3D World)

Monocular Multiview Object Tracking with 3D Aspect Parts
Yu Xiang*, Changkyu Song*, Roozbeh Mottaghi and Silvio Savarese (*equal contribution)
In European Conference on Computer Vision (ECCV), 2014.
PDF, BibTex,
 Technical_Report, Project


Beyond PASCAL: A Benchmark for 3D Object Detection in the Wild
Yu Xiang, Roozbeh Mottaghi and Silvio Savarese
In IEEE Winter Conference on Applications of Computer Vision (WACV), 2014.
PDF, BibTex
Poster, SlidesPASCAL3D+

Object Detection by 3D Aspectlets and Occlusion Reasoning
Yu Xiang and Silvio Savarese
In the 4th International IEEE Workshop on 3D Representation and Recognition (3dRR), 2013.
PDFBibTex
Technical_Report, SlidesDataset(~24MB)

Object Co-detection
Sid Yingze Bao, Yu Xiang and Silvio Savarese
In European Conference on Computer Vision (ECCV), vol. 7572, pp. 86-101, 2012.
PDFBibTexPosterProject

Estimating the Aspect Layout of Object Categories
Yu Xiang and Silvio Savarese
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3410-3417, 2012.
PDFBibTexTechnical ReportPoster, SlidesCodeProject
Before 2010 (Image and Text)


Semantic Context Modeling with Maximal Margin Conditional Random Fields for Automatic Image Annotation
Yu Xiang, Xiangdong Zhou, Zuotao Liu, Tat-Seng Chua and Chong-Wah Ngo
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3368-3375, 2010.
PDFBibTexTechnical_Report

Learning Contextual Metrics for Automatic Image Annotation
Zuotao Liu, Xiangdong Zhou, Yu Xiang and Yan-Tao Zheng
In Advances in Multimedia Information Processing - PCM, vol. 6297, pp. 124-135, 2010.
PDFBibTex


A Revisit of Generative Model for Automatic Image Annotation using Markov Random Fields
Yu Xiang, Xiangdong Zhou, Tat-Seng Chua and Chong-Wah Ngo
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1153-1160, 2009.
PDFBibTex

Adaptive Model for Web Image Semantic Automatic Image Annotation
Hongtao Xu, Xiangdong Zhou, Yu Xiang and Baile Shi
In Journal of Software (in Chinese), vol. 21, no. 9, pp. 2183-2195, 2009.
PDFBibTex


Exploiting Flickr's Related Tags for Semantic Annotation of Web Images
Hongtao Xu, Xiangdong Zhou, Mei Wang, Yu Xiang and Baile Shi
In Proceedings of the ACM International Conference on Image and Video Retrieval (CIVR), no. 46, 2009.
PDFBibTex


Automatic Web Image Annotation via Web-Scale Image Semantic Space Learning
Hongtao Xu, Xiangdong Zhou, Lan Lin, Yu Xiang and Baile Shi
In Advances in Data and Web Management, vol. 5446, pp. 211-222, 2009.
PDFBibTex

Thesis

  • Graphical Models for Semantic Context Modeling in Automatic Image Annotation (PDF)
Fudan University, Master thesis (in Chinese), Outstanding Master's Thesis Award of Shanghai, 2010.

Presentations

  • Beyond PASCAL: A Benchmark for 3D Object Detection in the Wild (PDF)
In IEEE Winter Conference on Applications of Computer Vision, Steamboat Springs, Colorado, 03/24/2014.
  • Object Detection by 3D Aspectlets and Occlusion Reasoning (PDF)
In the 4th International IEEE Workshop on 3D Representation and Recognition in conjunction with ICCV, Sydney, Australia, 12/08/2013.
  • Estimating the Aspect Layout of Object Categories (PDF)
In Midwest Vision Workshop, University of Illinois at Urbana-Champaign, 09/21/2012.