I am a researcher in the computer vision group of the Friedrich Schiller University of Jena (Germany). I finished my PhD in 2011 supervised by Joachim Denzler and I am heading the visual recognition part of the group now. In 2012/13, I worked as a PostDoc in the computer vision group of ICSI/EECS (UC Berkeley, California).

My research interests are mainly machine learning aspects of computer vision applications, such as transfer learning for object recognition and fast inference for semantic segmentation. If you have any questions concerning my research or a specific detail in my publications, do not hesitate to write an e-mail. 

Dagstuhl workshop on non-iid learning

posted Sep 12, 2014, 2:35 AM by Erik Rodner   [ updated Sep 12, 2014, 2:36 AM ]

I am organizing a Dagstuhl workshop on "Machine Learning with Interdependent and Non-identically Distributed Data" together with Marius Kloft (HU Berlin), Trevor Darrell (UC Berkeley), Gunnar Rätsch (Memorial Sloan-Kettering Cancer Center) and Massimiliano Pontil (University College London).

The workshop will take place in April next year and will be a meeting of several international experts in the area of machine learning and computer vision.

ECCV papers

posted Sep 12, 2014, 2:33 AM by Erik Rodner

Together with my students Alex and Marcel, I present three papers at ECCV and the Parts and Attributes workshop about active learning, exemplar-specific feature representations, and patch discovery with CNNs.

RSS Presentation

posted Aug 17, 2014, 11:58 PM by Erik Rodner

Sergio gave a short talk about our open vocabulary paper at RSS and the video is now online.

PhD position in a joint project with the MPI

posted Jul 18, 2014, 7:37 AM by Erik Rodner

We have a PhD position open in a joint project with the International Max Planck Research School for Global Biogeochemical Cycles about anomaly and novelty detection. More information about the position is available at this page.


posted Jul 11, 2014, 4:54 AM by Erik Rodner

We have a new open source project available called ARTOS developed by a student of mine, Björn Barz. If we want to quickly build object detectors for arbitrary ImageNet categories, this is the tool you need. It comes with a clean UI and offers C++ and python interfaces: http://cvjena.github.io/artos/

Heidelberger BV-Forum

posted Jul 10, 2014, 1:25 PM by Erik Rodner

I gave a talk at the Heidelberger BV-Forum about adaptive and active learning. Before the talk we had an open house event in our group with several live demonstrations in the area of visual recognition.

CVPR 2014 Spotlight videos

posted Jun 11, 2014, 1:55 AM by Erik Rodner

I uploaded the spotlight videos for both of my CVPR 2014 papers, just click on the Videos page above.

ICRA paper webpage

posted May 28, 2014, 12:26 PM by Erik Rodner   [ updated May 28, 2014, 12:26 PM ]

The webpage for my current ICRA paper is online and it also includes bounding box annotations for the Office dataset of Kate Saenko: http://raptor.berkeleyvision.org/

CVPR 2014 papers

posted Mar 31, 2014, 7:09 AM by Erik Rodner

The group in Jena got two papers accepted for CVPR 2014 and I am a co-author on both of them:

Christoph Göring and Erik Rodner and Alexander Freytag and Joachim Denzler. 
Nonparametric Part Transfer for Fine-grained Recognition
Short Summary: Detection of parts with part transfer and feature extraction at part locations. The approach is super simple but works great!

Daniel Haase and Erik Rodner and Joachim Denzler. 
Instance-weighted Transfer Learning of Active Appearance Models
Short Summary: Domain adaptation techniques for Active Appearance Models, simple approach motivated from importance sampling

TASK-CV Workshop

posted Mar 31, 2014, 7:00 AM by Erik Rodner

Kate Saenko and several other people are organizing a workshop at ECCV 2014 this year about transfer learning and adaptation: http://www.cvc.uab.es/adas/task-cv2014/. I will help with reviewing and the deadline is the 14th of July, so keep this in mind when thinking about a venue for submitting a domain adaptation paper.

1-10 of 34