Home  •   News  •   Highlights  •   Publications  •   Teaching  •   Awards  •   Service  •   Resources  •   Family
Jianxiong Xiao

Email: xj [at] princeton [dot] edu

            

Overview:

My research is in the field of Computer Vision. I focus on leveraging big data to build computer systems to understand visual scenes, both inferring the semantics and extracting 3D structure for a large variety of environments. These two related tasks ‒ scene recognition and reconstruction ‒ are generally studied separately. To look for the right representations of visual scenes that realistically describe the world, I believe that it is critical to unify both tasks and learn the joint representations from huge amounts of rich data (e.g. rich annotation, panoramic field of view, depth, multiple viewpoints).

My work has won the ECCV best student paper award, Google US/Canada PhD Fellowship in Computer Vision, and MIT CSW best research award. It has also appeared in the popular press, e.g. Science Daily, Slashdot, Videolectures and MIT News.

News:

Highlights:

SUN Database SUN Classification Benchmark SUN360 Panorama SUN Primitive SUN Memorability 3D Indoor Museum Maps 3D Building Reconstruction Semantic Streetview Segmentation  Unified Tracking Benchmark

Publications:    Google Scholar   Bibtex

I work on scene and object recognition, data-driven approach and dataset issue, RGB-D and ambulatory vision, image matching and visual feature, semantic segmentation and co-segmentation, 3D reconstruction and image-based modeling, visual perception and human in the loop, vision for graphics.

S. Song and J. Xiao
Tracking Revisited using RGBD Camera: Unified Benchmark and Baselines
arXiv:1212.2823 [cs.CV].
Paper ·  Project Webpage

Y. Zhang, J. Xiao, J. Hays and P. Tan
FrameBreak: Dramatic Image Extrapolation by Guided Shift-Maps
Proceedings of 26th IEEE Conference on Computer Vision and Pattern Recognition (CVPR2013)
Paper ·  Project Webpage ·  Supplementary Material ·  Poster

H. Jiang and J. Xiao
A Linear Approach to Matching Cuboids in RGBD Images
Proceedings of 26th IEEE Conference on Computer Vision and Pattern Recognition (CVPR2013)
Paper

J. Xiao, B. C. Russell, and A. Torralba
Localizing 3D Cuboids in Single-view Images
Advances in Neural Information Processing Systems 25 (NIPS2012)
Paper · Source Code, Dataset and Project Webpage

A. Khosla, J. Xiao, A. Torralba and A. Oliva
Memorability of Image Regions
Advances in Neural Information Processing Systems 25 (NIPS2012)
Paper ·  Source Code and Project Webpage

J. Xiao and Y. Furukawa
Reconstructing the World's Museums
Proceedings of the 12th European Conference on Computer Vision (ECCV2012)
Best Student Paper Award ·  Oral Presentation ·  Paper ·  Project Website

J. Xiao, B. C. Russell, J. Hays, K. A. Ehinger, A. Oliva and A. Torralba
Basic Level Scene Understanding: From Labels to Structure and Beyond
ACM SIGGRAPH Asia 2012
Invited Paper of Technical Briefs

J. Xiao*, A. Khosla*, P. Isola, A. Torralba and A. Oliva (* - indicates equal contribution)
Image Memorability and Visual Inception
ACM SIGGRAPH Asia 2012
Invited Paper of Technical Briefs

J. Xiao
3D Reconstruction is Not Just a Low-level Task: Retrospect and Survey
Shimon Ullman and Tomaso Poggio's MIT9.S912: What is Intelligence?
Technical Report

J. Xiao, K. A. Ehinger, A. Oliva and A. Torralba
Recognizing Scene Viewpoint using Panoramic Place Representation
Proceedings of 25th IEEE Conference on Computer Vision and Pattern Recognition (CVPR2012)
Paper ·  Project Webpage (Dataset and Source Code)

K. A. Ehinger, J. Xiao, A. Torralba and A. Oliva
Estimating scene typicality from human ratings and image features
Proceedings of 33rd Annual Meeting of the Cognitive Science Society (CogSci2011)
Oral Presentation ·  Paper  ·  Slides

P. Isola, J. Xiao, A. Torralba and A. Oliva
What makes an image memorable?
Proceedings of 24th IEEE Conference on Computer Vision and Pattern Recognition (CVPR2011)
Paper ·  Project Webpage (Dataset and Source Code)
Press Coverage: MIT Homepage, MIT News, Slashdot, Science Daily, Armenian Medical, e!Science, etc.

H. Zhang, J. Xiao, and L. Quan
Supervised Label Transfer for Semantic Segmentation of Street Scenes
Proceedings of the 11th European Conference on Computer Vision (ECCV2010)

J. Xiao, J. Hays, K. A. Ehinger, A. Oliva, and A. Torralba
SUN Database: Large-scale Scene Recognition from Abbey to Zoo
Proceedings of 23rd IEEE Conference on Computer Vision and Pattern Recognition (CVPR2010)
Paper ·  Project Webpage with Dataset and Source Code ·  Poster ·  DrawMe

P. Zhao, T. Fang, J. Xiao, H. Zhang, Q. Zhao, and L. Quan
Rectilinear Parsing of Architecture in Urban Environment
Proceedings of 23rd IEEE Conference on Computer Vision and Pattern Recognition (CVPR2010)
Oral presentation

J. Xiao, T. Fang, P. Zhao, M. Lhuillier, and L. Quan
Image-based Street-side City Modeling
ACM Transaction on Graphics (TOG), Volume 28, Number 5. Proceedings of ACM SIGGRAPH Asia 2009.
Project Webpage ·  High Resolution Paper ·  Video of System Explanation ·  Video of Results

J. Xiao and L. Quan
Multiple View Semantic Segmentation for Street View Images
Proceedings of 12th IEEE International Conference on Computer Vision (ICCV2009)
Project Webpage ·  High Resolution Paper ·  High Resolution Poster (126M) ·  Low Resolution Poster ·  Video in YouTube

J. Xiao
Image-based Building Modeling
Thesis for Master of Philosophy in Computer Science and Engineering, The Hong Kong University of Science and Technology.
M.Phil. Thesis (27MB)  ·  HKUST Institutional Repository

J. Xiao, T. Fang, P. Tan, P. Zhao, E. Ofek, and L. Quan
Image-based Facade Modeling
ACM Transaction on Graphics (TOG), Volume 27, Number 5. Proceedings of ACM SIGGRAPH Asia 2008.
[Image is selected for Back Cover of ToG. Video is selected for Papers Preview.]
Low Resolution Paper  ·  High Resolution Paper ·  Video in YouTube  ·  Slides ·  Image 1 ·  Image 2

P. Tan, T. Fang, J. Xiao, P. Zhao, and L. Quan
Single Image Tree Modeling
ACM Transaction on Graphics (TOG), Volume 27, Number 5. Proceedings of ACM SIGGRAPH Asia 2008.
Video is selected for Papers Preview  ·  Low Resolution Paper  ·  High Resolution Paper  ·  Video in YouTube

J. Xiao, J. Chen, D.-Y. Yeung, and L. Quan
Learning Two-view Stereo Matching
Proceedings of the 10th European Conference on Computer Vision (ECCV2008)
Oral Presentation Low Resolution Paper  ·  High Resolution Paper  ·  Slides

J. Xiao, J. Chen, D.-Y. Yeung, and L. Quan
Structuring Visual Words in 3D for Arbitrary-view Object Localization
Proceedings of the 10th European Conference on Computer Vision (ECCV2008)
Low Resolution Paper  ·  High Resolution Paper  ·  Slides ·  Data Set (742MB)

J. Xiao, J. Wang, P. Tan, and L. Quan
Joint Affinity Propagation for Multiple View Segmentation
Proceedings of 11th IEEE International Conference on Computer Vision (ICCV2007)
Oral presentation  ·  Low Resolution Paper  ·  High Resolution Paper  ·  Slides

Teaching:

  • Guest Lecturer and TA, MIT 6.869: Advances in Computer Vision
    • NEW:  I designed and taught a new lecture on 3D reconstruction.
    Student Rating: presentations 6.5/7, overall 6.1/7 (7=Excellent).
    Quotes from students:
    • "Super TA. He helped me a lot"
    • "Jianxiong was very helpful during the presentations and hilarious in his talk."
    • "The presentation he gave once on 3D modeling was very interesting. He gave very useful advice regarding the final projects."
    • "Jianxiong is enthusiastic in answering the questions in the office hours."
    • "It's a privilege to count on a TA that have deep knowledge about the class."
    • "Excellent presentations and always willing to help with psets."
    • "Quick response and broad availability. Great class!"
  • TA, HKUST COMP102 Computer and Programming Fundamental I
  • TA, HKUST COMP109 Special Summer Programming Course
  • TA, HKUST COMP272 Theory of Computation

Awards:

  • Google Research Best Paper Award (2013)
  • ECCV 2012 Best Student Paper Award (2012)
  • Google Ph.D. Fellowship in Computer Vision (2012)
  • ACCV 2012 Best Reviewer Award (2012)
  • MIT CSW Best Presentation Run-up (2012)
  • Qualcomm Innovation Fellowship Finalist (2012)
  • MIT CSW Best Research Award (2011)
  • HKUST Academic Achievement Medal (2007)

Service:

As chair:

As program committee / reviewer:

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)
  • International Journal of Computer Vision (IJCV)
  • IEEE Computer Vision and Pattern Recognition (CVPR) 2009‒2013
  • IEEE International Conference on Computer Vision (ICCV) 2007‒2013
  • European Conference on Computer Vision (ECCV) 2010‒2012
  • Neural Information Processing Systems (NIPS) 2010, 2012, 2013
  • ACM SIGGRAPH 2010, 2012, 2013
  • ACM SIGGRAPH Asia 2009, 2010, 2012, 2013
  • ACM Multimedia (ACMMM) 2010
  • Asian Conference on Computer Vision (ACCV) 2007, 2012
    (Best Reviewer Award)
  • IAPR International Conference on Pattern Recognition (ICPR) 2008
  • European Association for Computer Graphics (Eurographics) 2012, 2013
  • International Conference on Digital Information Management 2011
  • ACM Transactions on Graphics (ToG)
  • Pattern Recognition Letters (PR)
  • The Imaging Science Journal
  • IEEE Transactions on Systems, Man, and Cybernetics (SMC)
  • IEEE Transactions on Visualization and Computer Graphics (TVCG)
  • Computer Graphics Forum (CFG)
  • Elsevier Journal on Computers & Graphics (CAG)
  • KSII Transactions on Internet and Information Systems
  • Machine Vision and Applications Journal (MVA)
  • Image and Vision Computing Journal (IVC)
  • Journal of Computer Science and Technology

Resources:

Family:

  • I am a proud father of two sons, Jesse and Jack.