A Discriminative Learning Framework with Pairwise Constraints for Video Object Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence
Parsing Images into Regions, Curves, and Curve Groups
International Journal of Computer Vision
Segmentation and description of natural outdoor scenes
Image and Vision Computing
Robust Object Detection with Interleaved Categorization and Segmentation
International Journal of Computer Vision
Precise Eye Localization with AdaBoost and Fast Radial Symmetry
Computational Intelligence and Security
Learning to Combine Bottom-Up and Top-Down Segmentation
International Journal of Computer Vision
International Journal of Computer Vision
Coupled grouping and matching for sign and gesture recognition
Computer Vision and Image Understanding
Cooperative Object Segmentation and Behavior Inference in Image Sequences
International Journal of Computer Vision
A logic framework for active contours on multi-channel images
Journal of Visual Communication and Image Representation
SSVM'07 Proceedings of the 1st international conference on Scale space and variational methods in computer vision
Recovering human body configurations: combining segmentation and recognition
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Tracking multiple humans in crowded environment
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Learning to segment images using region-based perceptual features
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Towards recognition of degraded words by probabilistic parsing
Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing
Robust precise eye location under probabilistic framework
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Recursive Compositional Models for Vision: Description and Review of Recent Work
Journal of Mathematical Imaging and Vision
Object recognition and tracking in video sequences: a new integrated methodology
CIARP'06 Proceedings of the 11th Iberoamerican conference on Progress in Pattern Recognition, Image Analysis and Applications
Segmenting highly articulated video objects with weak-prior random forests
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
Learning to combine bottom-up and top-down segmentation
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
Toward a unified probabilistic framework for object recognition and segmentation
ISVC'05 Proceedings of the First international conference on Advances in Visual Computing
A probabilistic integrated object recognition and tracking framework
Expert Systems with Applications: An International Journal
A framework for unsupervised segmentation of multi-modal medical images
CVAMIA'06 Proceedings of the Second ECCV international conference on Computer Vision Approaches to Medical Image Analysis
Parsing architecture within plan drawings with application to medieval castles and fortresses
VAST'09 Proceedings of the 10th International conference on Virtual Reality, Archaeology and Cultural Heritage
A generic model to compose vision modules for holistic scene understanding
ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part I
Fusion of 3D-LIDAR and camera data for scene parsing
Journal of Visual Communication and Image Representation
Probabilistic Joint Image Segmentation and Labeling by Figure-Ground Composition
International Journal of Computer Vision
| Hi-index | 0.00 |
We propose a general framework for parsing images into regions andobjects. In this framework, the detection and recognition ofobjects proceed simultaneously with image segmentation in acompetitive and cooperative manner. We illustrate our approach onnatural images of complex city scenes where the objects of primaryinterest are faces and text. This method makes use of bottom-upproposals combined with top-down generative models using the DataDriven Markov Chain Monte Carlo (DDMCMC) algorithm which isguaranteed to converge to the optimal estimate asymptotically. Moreprecisely, we define generative models for faces, text, and genericregions- e.g. shading, texture, and clutter. These models areactivated by bottom-up proposals. The proposals for faces and textare learnt using a probabilistic version of AdaBoost. The DDMCMCcombines reversible jump and diffusion dynamics to enable thegenerative models to explain the input images in a competitive andcooperative manner. Our experiments illustrate the advantages andimportance of combining bottom-up and top-down models and ofperforming segmentation and object detection/recognitionsimultaneously.