Hi! I'm Sven. I am a newly appointed postdoctoral researcher at Indiana University, having just (August 2016) completed a joint Ph.D. degree in Computer Science and in Cognitive Science here at IU. I started my academic career in Germany with a B.Eng. from Cologne University of Applied Sciences (2010) that focused on Media and Imaging Technology. I also have a M.S. in Computer Science from Indiana University (2013).

My main research interest is computer vision, i.e. the intersection of computer science, machine learning and artificial intelligence that investigates methods of analyzing and understanding the visual world in the form of images and videos. I am advised by David Crandall.

Originating from a collaboration with Chen Yu and his Computational Cognition and Learning Laboratory comes a specialization in first-person (egocentric) video that approximates a person's view. I am interested in why, how and when we look at things (and also how infants learn to do so) and how computer vision algorithms could predict or emulate human behavior. To that end, I have developed robust methods to locate and distinguish hands during complex interactions between the observer and the world. More generally, I am interested in a broad range of vision applications and have worked on tracking, recognition, detection, and scene classification problems using state-of-the-art techniques such as deep learning with convolutional neural networks.

Peer-reviewed conference papers from my research as a Ph.D. student at Indiana University:

    2016:
  • Active Viewing in Toddlers Facilitates Visual Object Learning: An Egocentric Vision Approach, in 38th Annual Conference of the Cognitive Science Society, 2016 (with D. Crandall, L.B. Smith, C. Yu) (Oral, 34% acceptance rate) [PDF]
  • Objects in the Center: How the Infant’s Body Constrains Infant Scenes, in IEEE 6th Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL), 2016 (with L.B. Smith, D. Crandall, C. Yu) (Oral) [PDF] Distinguished Oral Presentation Award
  • 2015:
  • Lending A Hand: Detecting Hands and Recognizing Activities in Complex Egocentric Interactions, in IEEE International Conference on Computer Vision (ICCV), 2015 (with S. Lee, D. Crandall, C. Yu) (Poster, 31% acceptance rate) [PDF] [Dataset WWW] [Paper WWW]
  • Viewpoint Integration for Hand-Based Recognition of Social Interactions from a First-Person View, in 17th ACM International Conference on Multimodal Interaction (ICMI), 2015 (with D. Crandall, C. Yu) * (Poster, 41% acceptance rate) [PDF]

    This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in the Proceedings of the 17th ACM International Conference on Multimodal Interaction.

  • 2014:
  • This Hand Is My Hand: A Probabilistic Approach to Hand Disambiguation in Egocentric Video, in 3rd Workshop on Egocentric (First-person) Vision, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014 (with S. Lee, D. Crandall, J. Franchak, C. Yu) [PDF] Intel Best Paper Award
  • Detecting Hands in Children's Egocentric Views to Understand Embodied Attention during Social Interaction, in 36th Annual Conference of the Cognitive Science Society, 2014 (with J. Franchak, D. Crandall, C. Yu) (Oral, 41% acceptance rate) [PDF]
  • 2013:
  • Understanding Embodied Visual Attention in Child-Parent Interaction, in IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL), 2013. (with D. Crandall, C. Yu) (Oral, 33% acceptance rate) [PDF]

Abstracts, challenges, and other things:

  • Active Vision: Learning Visual Objects through Egocentric Views of Children and Parents, 1st Workshop on Action and Anticipation for Visual Learning, European Conference on Computer Vision (ECCV), 2016. [Abstract]
  • Analyzing Hands to Recognize Social Interactions with a Large-scale Egocentric Hands Dataset, Workshop on Observing and Understanding Hands in Action, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. [Abstract]
  • Detecting and Classifying Hands in Social and Driving Contexts, Vision for Intelligent Vehicles and Applications (VIVA) Challenge and Workshop, IEEE Intelligent Vehicles Symposium, 2015. [Poster]
  • Tracking Hands of Interacting People in Egocentric Video, Workshop on Observing and Understanding Hands in Action, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. [Abstract][Poster]

My Ph.D. dissertation, for those interested in a coherent summary of my work on analyzing hands from first-person cameras:

  • Sven Bambach, Analyzing Hands with First-Person Computer Vision, 2016. [PDF]

Survey papers from my Ph.D. qualifying exam that might be of interest for some:

  • Sven Bambach, A Survey on Recent Advances of Computer Vision Algorithms for Egocentric Video, 2013. [PDF] [ArXiv PDF]
  • Sven Bambach, A Survey on the Cognitive Basis of Visual Attention in Real-World Behavior" 2013. [PDF]

From my time as an undergraduate student at Cologne University of Applied Sciences:

  • Sven Bambach, "Design and Realization of an Experimental Optical Stop-Motion Capture System", Cologne University of Applied Sciences ePublications, 2010. (Bachelor Thesis, Reviewers: Dietmar Kunz, Stefan Grünvogel) [PDF] [Video]

Since September 2016 I have been a Postdoctoral Research Fellow at the School of Informatics and Computing at Indiana University, working with David Crandall, Chen Yu, and Linda B. Smith.

As a graduate student at IU, I was employed as a teaching assistant (officially called associate instructor) at IU (see Teaching) from Fall 2011 to Spring 2013, and worked as a research assistant from Summer 2013 to Summer 2016.

In the time between graduating with my bachelor's degree in Germany and coming to the US (01/2011 - 06/2011), I worked as a self-employed media engineer. My main client was almö GmbH.

Finally, here are some internships that I did during my time as an undergraduate engineering student at Cologne University of Applied Sciences:

  • meta-fusion GmbH, 05/2009 - 08/2009, internship: meta-fusion is a service provider for multi-media and internet applications and specializes in internet video streaming of major conferences. I worked both with the technical staff on location (United Nations Climate Change Conference 2009 in Bonn, Germany) as well as with the research/development department.
  • nexum AG, 01/2007 - 06/2007 (internship), 06/2008 - 11/2011 (student assistant): nexum is a big consultancy and agency for digital media. I worked in the developement department and was responsible for the planning and implementation of large scale internet solutions (front end and back end web development).

For the current Fall 2016 semester I am the instructor of record for CSCI B551 - Elements of Artificial Intelligence together Prof. David Crandall, with whom I split the responsibility between the residential section and the online section of the course.

During my first two years at Indiana University, I helped teaching the following courses as an associate instructor:

  • Fall 2011: CSCI P573 - Scientific Computing with Prof. Bramley
  • Spring 2012: CSCI A321 - Computing Tools for Scientific Research with Prof. Bramley
  • Fall 2012: CSCI C211 - Introduction to Computer Science with Prof. Menzel and Prof. Sabry (included preparing and teaching labs)
  • Spring 2013: CSCI C211 - Introduction to Computer Science with Prof. Lara-Dammer (included preparing and teaching labs)

I have also been asked to give various guest lectures in computer vision related courses both at the graduate and undergraduate level (e.g. CSCI B490 - Introduction to Computer Vision or CSCI B657 - Computer Vision.

Fun

I recently started biking as I discovered that it's by far the most fun "basic" outdoor activity to me and Bloomington actually has some really nice bike trails. The "normal" tour that I try to do daily (at least during summer) is about 18.5km. Not too bad I guess.

Inspired by playing foosball inbetween classes, my friend and I developed a software capable of tracking all key components of a foosball game in real time (30+ FPS). It was a project for a computer vision class that we took in the spring 2012 semester and a lot of fun to realize. A video of our results can be seen here.

Lastly, I don't only like to analyze photos, I also love taking them. Although I took some photography classes as an undergraduate, I am far from being a professional. However, I am a proud owner of a Canon SLR camera and you can check out a very sparse selection of my photos below. Feel free to also check out my Flickr account for more.

Andes behind Santiago de Chile

Santiago Santiago Santiago

The People of Osaka, Japan

Osaka Osaka Osaka Osaka Osaka Osaka Osaka

Rhine Falls in Schaffhausen, Switzerland

Rhine Falls Rhine Falls Rhine Falls

Zoo Impressions from Gelsenkirchen, Germany

Zoo Zoo Zoo Zoo Zoo Zoo