Serge Belongie

Serge Belongie

Copenhagen, Capital Region of Denmark, Denmark
5K followers 500+ connections

Join to view profile

About

Specialties: Computer Vision and Machine Learning

Articles by Serge

Activity

Join now to see all activity

Experience

  • Pioneer Centre for AI Graphic

    Pioneer Centre for AI

    Denmark

  • -

    Denmark

  • -

    Europe

  • -

    Copenhagen, Capital Region, Denmark

  • -

    New York, New York

  • -

  • -

    Copenhagen Area, Denmark

  • -

  • -

    Greater New York City Area

  • -

    New York, New York

  • -

    Ithaca, New York Area

  • -

    Greater New York City Area

  • -

  • -

    Portland, Oregon

  • -

  • -

    San Francisco Bay Area

  • -

    Redwood City, CA

  • -

  • -

    Greater New York City Area

  • -

  • -

  • -

  • -

  • -

  • -

  • -

Education

Publications

  • Learning to Match Aerial Images with Deep Attentive Architectures

    2016 IEEE Conference on Computer Vision and Pattern Recognition

  • Wet fingerprint recognition: Challenges and opportunities

    IEEE Computer Society Washington, DC, USA

    See publication

  • Generalized Non-metric Multidimensional Scaling

    AISTATS

    See publication

  • Soylent Grid: Its Made of People

    Workshop on Interactive Computer Vision (ICV)

    See publication

  • Approximate Thin Plate Spline Mappings

    European Conference on Computer Vision - ECCV

    The thin plate spline (TPS) is an effective tool for modeling coordinate transformations that has been applied successfully in several computer vision applications. Unfortunately the solution requires the inversion of a p × p matrix, where p is the number of points in the data set, thus making it impractical for large scale applications. As it turns out, a surprisingly good approximate solution is often possible using only a small subset of corresponding points. We begin by discussing the…

    The thin plate spline (TPS) is an effective tool for modeling coordinate transformations that has been applied successfully in several computer vision applications. Unfortunately the solution requires the inversion of a p × p matrix, where p is the number of points in the data set, thus making it impractical for large scale applications. As it turns out, a surprisingly good approximate solution is often possible using only a small subset of corresponding points. We begin by discussing the obvious approach of using the subsampled set to estimate a transformation that is then applied to all the points, and we show the drawbacks of this method. We then proceed to borrow a technique from the machine learning community for function approximation using radial basis functions (RBFs) and adapt it to the task at hand. Using this method, we demonstrate a significant improvement over the naive method. One drawback of this method, however, is that is does not allow for principal warp analysis, a technique for studying shape deformations introduced by Bookstein based on the eigenvectors of the p × p bending energy matrix .T o address this, we describe a third approximation method based on a classic matrix completion technique that allows for principal warp analysis as a by-product. By means of experiments on real and synthetic data, we demonstrate the pros and cons of these different approximations so as to allow the reader to make an informed decision suited to his or her application.

    See publication

Honors & Awards

  • Medlem

    Videnskabernes Selskabs

    Member, The Royal Danish Academy Of Sciences And Letters

More activity by Serge

View Serge’s full profile

  • See who you know in common
  • Get introduced
  • Contact Serge directly
Join to view full profile

Other similar profiles

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Add new skills with these courses

See all courses