Category: Seminars

Mapping the World with Street View

  Affiliation: Senior Staff Software Engineer Google Inc. USA Place: Large Lecture Room   Google extracts information from Street View images to build maps. It started with street address numbers, and is now growing to more and more types of

Posted in Seminars

Computational mechanisms of rapid visual recognition

  Place: Large Lecture Room   Perception involves a complex interaction between feedforward sensory-driven information and feedback attentional, memory, and executive processes that modulate such feedforward processing. A mechanistic understanding of feedforward processing, and its limitations, is a necessary first

Posted in Seminars

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

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

Posted in Seminars

From Medical Image Analysis to Computer-based Personalized Medicine.

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

Posted in Seminars

Dynamic Probabilistic Models for Person Tracking and Activity Recognition

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

Posted in Seminars

Semi-Supervised Learning in Large Image Collections

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

Posted in Seminars

Active Pedestrian Safety 2.0

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

Posted in Seminars

Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation.

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

Posted in Seminars

Leave-One-Out Kernel Optimization for Shadow Detection

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

Posted in Seminars

Image guided robotics for cardiac surgery

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

Posted in Seminars