Place: Large Lecture Room   Low-level Vision Statistical Color Constancy and Prior Color Naming for Application-Independent Automated Near Real-Time Detection and Quality Assessment of Superpixels / Texels in Any Color Image: (i) Uncalibrated / Calibrated, (ii) RGB True- or False-Color …

Low-Level Vision Color Constancy and Prior Color Naming for Application-independent Automated Linear-Time Detection and Quality Assessment of Superpixels in Multi-Source Color Images Read More »

Place: Large lecture room. Tomorrow’s healthcare lies in early diagnosis and individually tailored treatments, i.e. delivering the right treatment to the right patient at the right time. This patient-centred approach to medicine, the so-called personalized medicine, has been embraced as …

From Medical Image Analysis to Computer-based Personalized Medicine. Read More »

Place: Large lecture room. Affiliation:  INRIA Rhône-Alpes, France.   Object tracking and activity recognition underly many applications in computer science. Because they allow a principle integration of uncertainties, probabilistic models have been deepl investigated to solve object tracking and activity …

Dynamic Probabilistic Models for Person Tracking and Activity Recognition Read More »

Place: Large lecture room. Affiliation: Department of Computer Science, TU Dortmund. Germany.   Machine learning methods are capable of achieving impressive performances on a variety of pattern recognition tasks today. This is mostly due to two factors. First, large annotated data …

Semi-Supervised Learning in Large Image Collections Read More »

Place: Large lecture room. Affiliation: Daimler Group. Germany.   Daimler introduced an advanced set of driver assistance functions in its latest Mercedes-Benz 2013-2014 S-, E-, and C-Class models, termed “Intelligent Drive”, using stereo vision. It includes a pedestrian safety component which …

Active Pedestrian Safety 2.0 Read More »

Place: Large lecture room. Affiliation: ETHZ vision group. Zurich, Switzerland.     Object proposals have become a key component in most of the recent state-of-the-art object detectors, as they provide a reduced set of candidate locations for objects in the image. They …

Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation. Read More »

Place: Large lecture room. Affiliation: Image Analysis Lab. Stony Brook University,  N.Y. , U.S.A.     The objective of this work is to detect shadows in images. We pose this as the problem of labeling image regions, where each region …

Leave-One-Out Kernel Optimization for Shadow Detection Read More »

Place: Large lecture room. Affiliation: Philips Research North America. Cambridge, MA, USA.     With the recent advancement in intracardiac therapies, navigation and steering of medical devices in moving environments have become an important research topic. In this talk, I will present …

Image guided robotics for cardiac surgery Read More »

Place: Large lecture room. Affiliation:  Queen Mary University of London. U.K.     Recent years have witnessed an unprecedented interest in the recognition of human behaviour, from analysis of facial expressions, body gestures or neurophysiological signals such as EEG and …

Looking at / Sensing People Read More »

Place: Large lecture room. Affiliation:  University of Edinburgh.     Modern object class detectors typically apply a window classifier to all the windows in a large set, either in a sliding window manner or using object proposals. In this work, …

An Active Search Strategy for Efficient Object Class Detection Read More »