Previous | 
Home
Section: New Software and Platforms
DPMS
Functional Description
Dpms implements branch-and-bound object detection, cutting down the complexity of detection from linear in the number of pixels to logarithmic.
Overall Objectives
Research Program
Application Domains
New Results
- Optimizing Average Precision
- Region-based Semantic Segmentation
- Parsimonious Labeling
- Structured Learning and Inference
- Novel graph kernels
- Structured Sparsity Regularization & Statistical Hypothesis Testing
- High-Order MRF models
- Graph-based registration and segmentation
- Object Detection from RGB-Depth images
- Deep CNN for Modelling Deformations and Semantic Segmentation
- Learning Low-level Image Representations with Deep CNN
- Human-Limb Segmentation for Intelligent Mobility Assistance Robots
Partnerships and Cooperations
Bibliography
Overall Objectives
Research Program
Application Domains
New Results
- Optimizing Average Precision
- Region-based Semantic Segmentation
- Parsimonious Labeling
- Structured Learning and Inference
- Novel graph kernels
- Structured Sparsity Regularization & Statistical Hypothesis Testing
- High-Order MRF models
- Graph-based registration and segmentation
- Object Detection from RGB-Depth images
- Deep CNN for Modelling Deformations and Semantic Segmentation
- Learning Low-level Image Representations with Deep CNN
- Human-Limb Segmentation for Intelligent Mobility Assistance Robots
Partnerships and Cooperations
Bibliography