References of "Piater, Justus"
     in
Bookmark and Share    
Peer Reviewed
See detailAdaptive Patch Features for Object Class Recognition with Learned Hierarchical Models
Scalzo, Fabien; Piater, Justus ULg

in 2nd Beyond Patches Workshop (2007)

Detailed reference viewed: 8 (0 ULg)
Peer Reviewed
See detailSequential Variational Inference for Distributed Multi-Sensor Tracking and Fusion
Du, Wei ULg; Piater, Justus ULg

in The 10th International Conference on Information Fusion (2007)

Detailed reference viewed: 8 (1 ULg)
Peer Reviewed
See detailMulti-Camera People Tracking by Collaborative Particle Filters and Principal Axis-Based Integration
Du, Wei ULg; Piater, Justus ULg

in Asian Conference on Computer Vision (2007)

Detailed reference viewed: 19 (0 ULg)
Full Text
Peer Reviewed
See detailApproximate Policy Iteration for Closed-Loop Learning of Visual Tasks
Jodogne, Sébastien ULg; Briquet, Cyril ULg; Piater, Justus ULg

in Lecture Notes in Computer Science (2006, September), 4212

Approximate Policy Iteration (API) is a reinforcement learning paradigm that is able to solve high- dimensional, continuous control problems. We propose to exploit API for the closed-loop learning of ... [more ▼]

Approximate Policy Iteration (API) is a reinforcement learning paradigm that is able to solve high- dimensional, continuous control problems. We propose to exploit API for the closed-loop learning of mappings from images to actions. This approach requires a family of function approximators that maps visual percepts to a real-valued function. For this purpose, we use Regression Extra-Trees, a fast, yet accurate and versatile machine learning algorithm. The inputs of the Extra-Trees consist of a set of visual features that digest the informative patterns in the visual signal. We also show how to parallelize the Extra-Tree learning process to further reduce the computational expense, which is often essential in visual tasks. Experimental results on real-world images are given that indicate that the combination of API with Extra-Trees is a promising framework for the interactive learning of visual tasks. [less ▲]

Detailed reference viewed: 35 (14 ULg)
Full Text
Peer Reviewed
See detailTask-Driven Discretization of the Joint Space of Visual Percepts and Continuous Actions
Jodogne, Sébastien ULg; Piater, Justus ULg

in Lecture Notes in Computer Science (2006), 4212

Detailed reference viewed: 7 (4 ULg)
See detailResearch Unit in Signal and Image Exploitation (INTELSIG)
Verly, Jacques ULg; Piater, Justus ULg; Van Droogenbroeck, Marc ULg et al

Scientific conference (2006)

Detailed reference viewed: 7 (1 ULg)
Peer Reviewed
See detailCollaborative Multi-Camera Tracking of Athletes in Team Sports
Du, Wei ULg; Hayet, Jean-Bernard; Piater, Justus ULg et al

in Workshop on Computer Vision Based Analysis in Sport Environments (CVBASE) (2006)

Detailed reference viewed: 28 (3 ULg)
Full Text
Peer Reviewed
See detailMulti-view object tracking using sequential belief propagation
Du, Wei ULg; Piater, Justus ULg

in Computer Vision – ACCV 2006 (2006)

Multiple cameras and collaboration between them make possible the integration of information available from multiple views and reduce the uncertainty due to occlusions. This paper presents a novel method ... [more ▼]

Multiple cameras and collaboration between them make possible the integration of information available from multiple views and reduce the uncertainty due to occlusions. This paper presents a novel method for integrating and tracking multi-view observations using bidirectional belief propagation. The method is based on a fully connected graphical model where target states at different views are represented as different but correlated random variables, and image observations at a given view are only associated with the target states at the same view. The tracking processes at different views collaborate with each other by exchanging information using a message passing scheme, which largely avoids propagating wrong information. An efficient sequential belief propagation algorithm is adopted to perform the collaboration and to infer the multi-view target states. We demonstrate the effectiveness of our method on video-surveillance sequences. [less ▲]

Detailed reference viewed: 142 (4 ULg)
Peer Reviewed
See detailTRICTRAC Video Dataset: Public HDTV Synthetic Soccer Video Sequences With Ground Truth
Desurmont, Xavier; Hayet, Jean*-Bernard; Delaigle, Jean*-Fran et al

in Workshop on Computer Vision Based Analysis in Sport Environments (CVBASE) (2006)

Detailed reference viewed: 39 (0 ULg)
Peer Reviewed
See detailData Fusion by Belief Propagation for Multi-Camera Tracking
Du, Wei ULg; Piater, Justus ULg

in The 9th International Conference on Information Fusion (2006)

Detailed reference viewed: 14 (0 ULg)
Peer Reviewed
See detailUnsupervised Learning of Dense Hierarchical Appearance Representations
Scalzo, Fabien; Piater, Justus ULg

in International Conference on Pattern Recognition (2006)

Detailed reference viewed: 8 (0 ULg)
Peer Reviewed
See detailRobust Non-Rigid Object Tracking Using Point Distribution Manifolds
Mathes, Tom; Piater, Justus ULg

in 28th Annual Symposium of the German Association for Pattern Recognition (DAGM) (2006)

Detailed reference viewed: 19 (1 ULg)
Full Text
Peer Reviewed
See detailUnsupervised learning of visual feature hierarchies
Scalzo, Fabien; Piater, Justus ULg

in Machine Learning and Data Mining in Pattern Recognition (2005)

We propose an unsupervised, probabilistic method for learning visual feature hierarchies. Starting from local, low-level features computed at interest point locations, the method combines these primitives ... [more ▼]

We propose an unsupervised, probabilistic method for learning visual feature hierarchies. Starting from local, low-level features computed at interest point locations, the method combines these primitives into high-level abstractions. Our appearance-based learning method uses local statistical analysis between features and Expectation-Maximization to identify and code spatial correlations. Spatial correlation is asserted when two features tend to occur at the same relative position of each other. This learning scheme results in a graphical model that constitutes a probabilistic representation of a flexible visual feature hierarchy. For feature detection, evidence is propagated using Belief Propagation. Each message is represented by a Gaussian mixture where each component represents a possible location of the feature. In experiments, the proposed approach demonstrates efficient learning and robust detection of object models in the presence of clutter and occlusion and under view point changes. [less ▲]

Detailed reference viewed: 41 (5 ULg)
Full Text
Peer Reviewed
See detailControlling an Agent by Focusing its Attention on Interactively Selected Patterns
JODOGNE, Sébastien ULg; Piater, Justus ULg

in HF Journal -- Belgian Journal of Electronics Communications (2005), (1), 14--16

Detailed reference viewed: 17 (2 ULg)
Peer Reviewed
See detailObject Tracking Using Color Interest Points
Gabriel, Pierre F.; Hayet, Jean-Bernard; Piater, Justus ULg et al

Conference (2005)

Detailed reference viewed: 13 (0 ULg)
Peer Reviewed
See detailFast 2D model-to-image registration using vanishing points for sports video analysis
Hayet, Jean-Bernard; Piater, Justus ULg; Verly, Jacques ULg

Conference (2005)

Detailed reference viewed: 14 (1 ULg)
Peer Reviewed
See detailLearning, then Compacting Visual Policies
Jodogne, Sébastien ULg; Piater, Justus ULg

in 7th European Workshop on Reinforcement Learning (2005)

Detailed reference viewed: 5 (3 ULg)
Peer Reviewed
See detailInteractive Learning of Mappings from Visual Percepts to Actions
Jodogne, Sébastien ULg; Piater, Justus ULg

in 22nd International Conference on Machine Learning (2005)

Detailed reference viewed: 8 (4 ULg)
Peer Reviewed
See detailTask-Driven Learning of Spatial Combinations of Visual Features
Jodogne, Sébastien ULg; Scalzo, Fabien; Piater, Justus ULg

in Proc. of the IEEE Workshop on Learning in Computer Vision and Pattern Recognition (2005)

Detailed reference viewed: 12 (3 ULg)