Showing results 21 to 40 of 89
 Active Learning using Mean Shift Optimization for Robot Grasping; Detry, Renaud  ; Piater, Justus et alin IEEE/RSJ International Conference on Intelligent Robots and Systems (2009) Detailed reference viewed: 22 (2 ULg)Learning Objects and Grasp Affordances through Autonomous Exploration; Detry, Renaud ; et alin International Conference on Computer Vision Systems (2009) Detailed reference viewed: 10 (3 ULg)Learning Object-specific Grasp Affordance DensitiesDetry, Renaud ; ; et alin International Conference on Development and Learning (2009) Detailed reference viewed: 13 (1 ULg) A Probabilistic Framework for 3D Visual Object RepresentationDetry, Renaud ; ; Piater, Justus in IEEE Transactions on Pattern Analysis & Machine Intelligence (2009) Detailed reference viewed: 32 (12 ULg)Learning Visual Representations for Interactive SystemsPiater, Justus ; Jodogne, Sébastien ; Detry, Renaud et alin 14th International Symposium on Robotics Research (2009) Detailed reference viewed: 7 (2 ULg)Using Multi-Modal 3D Contours and Their Relations for Object Encoding and Grasping; ; et al in 24th International Symposium on Computer and Information Sciences (2009) Detailed reference viewed: 7 (1 ULg)Ground-Target Tracking in Multiple Cameras Using Collaborative Particle Filters and Principal Axis-Based IntegrationDu, Wei ; ; Verly, Jacques et alin IPSJ Transactions on Computer Vision and Applications (2009), 1 Detailed reference viewed: 40 (2 ULg)Computer Vision Systems: Seventh International Conference; ; Piater, Justus Book published by Springer (2009) Detailed reference viewed: 5 (0 ULg) Planning Readings: a Comparative Exploration of Basic AlgorithmsPiater, Justus in Computer Science Education (2009), 19(3), 179--192 Detailed reference viewed: 2 (0 ULg)Programme SMA SémantiqueDemaret, Jean-Noël ; Piater, Justus ; et alSoftware (2008) Detailed reference viewed: 75 (24 ULg)3D Probabilistic Representations for Vision and ActionPiater, Justus ; Detry, Renaud in Robotics Challenges for Machine Learning II (2008) Detailed reference viewed: 19 (3 ULg)Exploration and Planning in a Three-Level Cognitive Architecture; ; et al in International Conference on Cognitive Systems (CogSys) (2008) Detailed reference viewed: 24 (1 ULg)Probabilistic Pose Recovery Using Learned Hierarchical Object ModelsDetry, Renaud ; ; Piater, Justus in International Cognitive Vision Workshop (Workshop at the 6th International Conference on Vision Systems) (2008) Detailed reference viewed: 16 (3 ULg)Online Learning of Gaussian Mixture Models - a Two-Level ApproachDeclercq, Arnaud ; Piater, Justus in VISAPP 2008: Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1 (2008) Online learning, Gaussian mixture model, Uncertain model. We present a method for incrementally learning mixture models that avoids the necessity to keep all data points around. It contains a single user ... [more ▼] Online learning, Gaussian mixture model, Uncertain model. We present a method for incrementally learning mixture models that avoids the necessity to keep all data points around. It contains a single user-settable parameter that controls via a novel statistical criterion the trade-off between the number of mixture components and the accuracy of representing the data. A key idea is that each component of the (non-overfitting) mixture is in turn represented by an underlying mixture that represents the data very precisely (without regards to overfitting); this allows the model to be refined without sacrificing accuracy. [less ▲] Detailed reference viewed: 45 (0 ULg)A Probabilistic Approach to Integrating Multiple Cues in Visual TrackingDu, Wei ; Piater, Justus in 10th European Conference on Computer Vision (2008) Detailed reference viewed: 17 (0 ULg)Vision as Inference in a Hierarchical Markov NetworkPiater, Justus ; ; Detry, Renaud Conference (2008) Detailed reference viewed: 15 (1 ULg)Hierarchical Integration of Local 3D Features for Probabilistic Pose RecoveryDetry, Renaud ; Piater, Justus in Robot Manipulation: Sensing and Adapting to the Real World (Workshop at Robotics, Science and Systems) (2007) Detailed reference viewed: 15 (3 ULg)Closed-Loop Learning of Visual Control PoliciesJodogne, Sébastien ; Piater, Justus in Journal of Artificial Intelligence Research (2007), 28 Detailed reference viewed: 8 (5 ULg)On-line Simultaneous Learning and Tracking of Visual Feature GraphsDeclercq, Arnaud ; Piater, Justus in 2007 IEEE Conference on Computer Vision and Pattern Recognition (CVPR07) (2007) Model learning and tracking are two important topics in computer vision. While there are many applications where one of them is used to support the other, there are currently only few where both aid each ... [more ▼] Model learning and tracking are two important topics in computer vision. While there are many applications where one of them is used to support the other, there are currently only few where both aid each other simultaneously. In this work, we seek to incrementally learn a graphical model from tracking and to simultaneously use whatever has been learned to improve the tracking in the next frames. The main problem encountered in this situation is that the current intermediate model may be inconsistent with future observations, creating a bias in the tracking results. We propose an uncertain model that explicitly accounts for such uncertainties by representing relations by an appropriately weighted sum of informative (parametric) and uninformative (uniform) components. The method is completely unsupervised and operates in real time. [less ▲] Detailed reference viewed: 11 (0 ULg)On-Line Rectification of Sport Sequences with Moving Cameras; Piater, Justus in Mexican International Conference on Artificial Intelligence (2007) Detailed reference viewed: 4 (0 ULg) |
||
