Presented results of COCO Stuff Challenge

Recently I attended the International Conference on Computer Vision (ICCV) 2017 in Venice, Italy. Besides presenting a paper on Weakly Supervised Object Localization Using Things and Stuff Transfer, I was also one of the organizers of the Joint Workshop of the COCO and Places Challenges at ICCV 2017. I presented the COCO Stuff Segmentation Challenge …

More

Overview of my Github projects

In this article I would like to give a brief overview of my activities on GitHub. I try to make as much as possible of my research publicly available using open-source licenses. Statistics Project Visitors* Stars Forks Really awesome GAN 918 510 103 Really awesome semantic segmentation 363 141 41 COCO-Stuff 431 101 25 Matconvnet-Calvin …

More

Paper accepted at ECCV 2016

My latest paper entitled Region-based semantic segmentation with end-to-end training has been accepted the the European Conference on Computer Vision (ECCV) 2016. Semantic segmentation is the task of labeling each pixel in an image. Our work combines the advantages of the two main paradigms in semantic segmentation: Fully Convolutional Neural Networks can be trained end-to-end and region-based …

More

List of contemporary semantic segmentation datasets

I have compiled a list with all semantic segmentation papers that I have come across during my PhD and the datasets they use for their experiments. These include fully / semi / weakly supervised works. It comprises 139 papers and 39 datasets and nicely shows the growth of the field and the move from small-scale datasets …

More

Paper accepted at BMVC 2015 in Swansea

In June 2015 our paper was accepted to the British Machine Vision Conference (BMVC) 2015 in Swansea. The paper entitled “Joint Calibration for Semantic Segmentation” is a collaboration with Jasper Uijlings and Vittorio Ferrari. We tackle the problem of semantic segmentation – assigning a class label to each pixel in an image – by jointly calibrating the …

More

PhD at the University of Edinburgh

In May 2014 I started my PhD at the University of Edinburgh, Scotland. I am a member of the CALVIN research group under the lead of Vittorio Ferrari. We focus on Computer Vision and Machine Learning techniques (weakly supervised learning of object classes, semantic segmentation and large-scale auto-annotation). My PhD thesis topic is centered around the creation …

More

Java EE developer

In October 2012 I joined “Exxeta AG – Consulting and Technologies”. As a part-time Java EE developer I have been working on an open-source project called “B2B By Practice“. This application enables small to medium sized energy suppliers to fulfill the legal requirements for Business-to-Business communication, while keeping down the costs for in-house development and maintenance. Until the …

More

Internship at Credit Suisse

I just received confirmation for an internship with Credit Suisse in Zurich, Switzerland. My task will be to evaluate how well the recently published Advanced Message Queuing Protocol (AMQP) integrates with the company’s middleware messaging infrastructure.

Bachelor-Thesis at the IDIAP Research Institute

In summer 2012 I wrote my Bachelor thesis IDIAP research institute in Martigny, Switzerland. The work entitled “Integrating Language Identification to improve Multilingual Speech Recognition” was supervised by Dr. David Imseng and Prof. Hervé Bourlard. In this work I developed an Automatic Speech Recognition (ASR) system that converts spoken language into written words. Since the data was …

More

Visitor statistics

For the last two years I have been using Google Analytics to receive detailled statistics about the origin and behavior of the visitors of this website. I would like to present some of the numbers in an anonymized form. By that I hope to raise awareness for the massive amount of data collected on each of us …

More

SDQ Best Paper Award

As part of the University course “Inside Eclipse” at the chair for “Software Design and Quality” (SDQ) of Prof. Reussner, I received the best paper award for my work entitled “Mylyn – Increasing Productivity by Analyzing Task Context”.