Shape Matching and Object Recognition Using Shape Contexts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Class-Specific, Top-Down Segmentation
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part II
Normalized Cuts and Image Segmentation
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
A Metric for Distributions with Applications to Image Databases
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Pictorial Structures for Object Recognition
International Journal of Computer Vision
Pedestrian Detection in Crowded Scenes
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Histograms of Oriented Gradients for Human Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Efficient Shape Matching Using Shape Contexts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Closely Coupled Object Detection and Segmentation
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Recovering Human Body Configurations Using Pairwise Constraints between Parts
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Bottom-Up & Top-down Object Detection using Primal Sketch Features and Graphical Models
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Recovering human body configurations: combining segmentation and recognition
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Shape context and chamfer matching in cluttered scenes
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Learning to combine bottom-up and top-down segmentation
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
Object detection by contour segment networks
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
Semi-supervised Edge Learning for Building Detection in Aerial Images
ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing, Part II
Contour Grouping Based on Contour-Skeleton Duality
International Journal of Computer Vision
Shape Based Detection and Top-Down Delineation Using Image Segments
International Journal of Computer Vision
Using visual context and region semantics for high-level concept detection
IEEE Transactions on Multimedia - Special issue on integration of context and content
Contour based object detection using part bundles
Computer Vision and Image Understanding
Improving shape retrieval by spectral matching and meta similarity
IEEE Transactions on Image Processing
Shape matching using a binary search tree structure of weak classifiers
Pattern Recognition
Novel and efficient pedestrian detection using bidirectional PCA
Pattern Recognition
A boosting approach for the simultaneous detection and segmentation of generic objects
Pattern Recognition Letters
Hi-index | 0.00 |
We develop an object detection method combining top-down recognition with bottom-up image segmentation. There are two main steps in this method: a hypothesis generation step and a verification step. In the top-down hypothesis generation step, we design an improved Shape Context feature, which is more robust to object deformation and background clutter. The improved Shape Context is used to generate a set of hypotheses of object locations and figure-ground masks, which have high recall and low precision rate. In the verification step, we first compute a set of feasible segmentations that are consistent with top-down object hypotheses, then we propose a False Positive Pruning (FPP) procedure to prune out false positives. We exploit the fact that false positive regions typically do not align with any feasible image segmentation. Experiments show that this simple framework is capable of achieving both high recall and high precision with only a few positive training examples and that this method can be generalized to many object classes.