Month: November 2011

Introduction to Android Programming and OpenCV for Android

Place: Large Lecture Room – CVC Affiliation: Computer Vision Center   Description: In this two-hour technical forum we will cover the basic concepts of Android development. After a short introduction to the development environment and key concepts such as intents, services and

Approximate Ensemble Methods for Physical Activity Recognition Applications

Place: Large Lecture Room – CVC Affiliation: Universitat de Barcelona and Computer Vision Centre   The main interest of this thesis focuses on computational methodologies able to reduce the degree of complexity of learning algorithms and its application to physical activity recognition. Random

Change Detection in Streaming Multivariate Data Using Likelihood Detectors

Place: Large Lecture Room – CVC Affiliation: School of Computer Science, Bangor University,Wales, UK   Change detection in streaming data relies on a fast estimation of the probability that the data in two consecutive windows come from different distributions. Choosing the criterion

Enhanced Visual Analysis for Cluster Tendency Assessment and Data Partitioning

Place: Large Lecture Room – CVC Affiliation: National Laboratory of Pattern Recognition (NLPR) Institute of Automation, Chinese Academy of Sciences. Beijing. China   Before my talk, I would like to briefly introduce our lab, and review my main research topics as well,

Monocular 3D Pose Estimation

Place: Large Lecture Room – CVC Affiliation: Research School of Information Sciences and Engineering. College of Engineering and Computer Science. Australian National University   The problem of identifying the 3D pose of a known object from a given 2D image has important applications

Saliency, visual attention and image quality

Place: Large Lecture Room – CVC Affiliation: CiSRA, Canon Information Systems Research Australia   Measuring image quality is a complex process that often requires elements of subjective analysis in order to be reliable when the final judge is a human observer. Preference

Space, Design, and Interactive Vision: Creating a Spatial Operating Environment

Place: Large Lecture Room – CVC Affiliation: Oblong Industries   Oblong Industries is a technology start-up focused on changing the way people work, create, and collaborate. We are building a Spatial Operating Environment (SOE) that supports collaboration between multiple users and multiple

Perturb-and-MAP Random Fields: Using Discrete Optimization to Learn and Sample from Energy Models

Place: Large Lecture Room – CVC Affiliation: University of California, Los Angeles. CA, USA   We propose a novel way to induce a random field from an energy function on discrete labels. It amounts to locally injecting noise to the energy potentials,

Multi ­scale Stacked Sequential Learning

Place: Large Lecture Room – CVC Affiliation: Computer Vision Centre and Universitat de Barcelona   The classification and or segmentation of sequential data (such as text, audio, images and videos) can be improved by moving from i.i.d. classifiers to contextual‐aware methods. One

Learning Components for Human Sensing

Place: Large Lecture Room – CVC Affiliation: Component Analysis Laboratory, and the Human Sensing Laboratory. Carnegie Mellon University, Pittsburg. USA   Enabling computers to understand human behavior has the potential to revolutionize many areas that benefit society such as clinical diagnosis, human