https://iis.uibk.ac.at/ 2026-04-06T04:26:33+0200 https://iis.uibk.ac.at/ https://iis.uibk.ac.at/lib/tpl/iis/images/favicon.ico text/html 2018-09-03T19:35:59+0200 Anonymous (anonymous@undisclosed.example.com) https://iis.uibk.ac.at/research/appearance-models?rev=1535996159&do=diff Probabilistic Models of Appearance for Object Recognition and Pose Estimation We developed probabilistic models to encode the appearance of objects, and inference methods to perform detection (localization) and pose estimation of those object in 2D images text/html 2018-09-03T19:35:59+0200 Anonymous (anonymous@undisclosed.example.com) https://iis.uibk.ac.at/research/grasp-densities?rev=1535996159&do=diff Interactive, Visuomotor Learning of Grasp Models We are interested in probabilistic representations and learning methods that allow a robotic agent to infer useful behaviors from perceptual observations. We develop probabilistic models of 3D visual and haptic object properties, along with means of learning the model autonomously from exploration: A robotic agent physically experiences the correlation between successful grasps and local visual appearance by “playing” with an object. With time, i… text/html 2018-09-03T19:35:59+0200 Anonymous (anonymous@undisclosed.example.com) https://iis.uibk.ac.at/research/mrf-object-models?rev=1535996159&do=diff Probabilistic Models for 3D Pose Estimation and Recognition Motivated by automnomous robots that need to acquire object models and manipulation skills on the fly, we develop learnable object models that represent objects as Markov networks, where nodes represent feature types, and arcs represent spatial relations. These models can handle deformations, occlusion and clutter. Object detection, recognition and pose estimation are solved using classical methods of probabilistic inference. text/html 2018-09-03T19:35:59+0200 Anonymous (anonymous@undisclosed.example.com) https://iis.uibk.ac.at/research/object-tracking?rev=1535996159&do=diff Object Tracking in Video A summary of results is given in a video from our TRICTRAC project. Point Distribution Models To track articulated objects through complex occlusions, we developed methods based on point distribution models. The idea is to abandon the idea of segmenting the tracked object, and rather focus on identifiable points. Point distribution models track a large number of points on the same target while exploiting the spatial configuration between them. This redundancy results … text/html 2026-03-16T21:10:52+0200 Anonymous (anonymous@undisclosed.example.com) https://iis.uibk.ac.at/research/projects?rev=1773691852&do=diff Externally-Funded, Collaborative Projects Current Projects CEIS - Comparative Ecological Innovation Styles (FWF Emerging Field 2026-2031, FWF and UIBK news items): Where does inventiveness come from? It is not limited to humans but can also be found across different animals. The project “Comparative Ecological Innovation Styles” investigates how different body structures, ecological niches, and cognitive abilities shape the emergence of novel behaviors. Rather than comparing only successful pr… text/html 2018-09-03T19:35:59+0200 Anonymous (anonymous@undisclosed.example.com) https://iis.uibk.ac.at/research/trictrac-video?rev=1535996159&do=diff