Skip to content

Svebor Karaman

  • PhD
  • Postdoctoral Researcher
  • Columbia University
  • 0ReadersNumber of instances of Svebor's publications in Mendeley libraries. Updated daily.
  • 5PublicationsNumber of items in this person’s My Publications folder on Mendeley.

Research interests

Machine learningPattern recognitionVideo indexingComputer vision

About

I am a French Computer Vision and Machine Learning researcher currently a Postdoctoral researcher in the DVMM Lab at Columbia University. Previously, I have spent three great years at the MICC (Media Integration and Communication Center) of the University of Florence in Italy. My research themes are image and video analysis. I am particularly interested in semantic concepts recognition in images and videos. I have made my PhD at the LaBRI – University of Bordeaux, under the supervision of Jenny Benois-Pineau and Rémi Mégret. During my PhD thesis, I have worked on human activities recognition by Hidden Markov Models (HMM) in videos recorded from a wearable device within the IMMED project. I have also developed an object recognition approach in the Bag-of-Visual-Words framework which integrates spatial information within semi-local features: the Graph-Words. I defended my PhD entitled “Indexing of Activities in Wearable Videos : Application to Epidemiological Studies of Aged Dementia” in 2011. Since joining the MICC in 2012, I have been highly involved in the MNEMOSYNE project. In this project multiple aspects of computer vision such as person detection, person tracking and re-identification are used to passively profile the interests of visitors in a museum to provide personalized multimedia content delivery. I am also still working on more general image and video classification problems.

Followers (3)

Following (6)

Publications

From Re-identification to Identity Inference: Labeling Consistency by Local Similarity Constraints

  • Karaman S
  • Lisanti G
  • Bagdanov A
Person Re-Identification (2014)
  • n/a

    Readers

  • n/a

    Citations

Full text

Leveraging local neighborhood topology for large scale person re-identification

  • Karaman S
  • Lisanti G
  • Bagdanov A
Pattern Recognition (2014)
  • n/a

    Readers

  • n/a

    Citations

Personalized multimedia content delivery on an interactive table by passive observation of museum visitors

  • Karaman S
  • Bagdanov A
  • Landucci L
Multimedia Tools and Applications (2014)
  • n/a

    Readers

  • n/a

    Citations

Full text

Hierarchical Hidden Markov Model in detecting activities of daily living in wearable videos for studies of dementia

  • Karaman S
  • Benois-Pineau J
  • Dovgalecs V
Multimedia Tools and Applications (2012)
  • n/a

    Readers

  • n/a

    Citations

Full text

Identity Inference: Generalizing Person Re-identification Scenarios

  • Karaman S
  • Bagdanov A
Computer Vision – ECCV 2012. Workshops and Demonstrations (2012)
  • n/a

    Readers

  • n/a

    Citations

Full text

Professional experience

Postdoctoral Researcher

Columbia University

April 2015 - Present

Postdoctoral research fellow

Universita degli Studi di Firenze

February 2012 - January 2015(3 years)

PhD student

Laboratoire Bordelais d'Informatique (LABRI)

October 2008 - December 2011(3 years)

Education history

PhD in Computer Science

Université Bordeaux 1

October 2008 - December 2011(3 years)

Master's Degree

Université Bordeaux 1

September 2007 - June 2008(9 months)

Engineer's Degree

ENSEIRB-MATMECA

September 2005 - June 2008(3 years)