The Data-Correcting Algorithm for the Minimization of Supermodular Functions
Management Science
Maximizing the spread of influence through a social network
Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining
Robust Real-Time Face Detection
International Journal of Computer Vision
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
Near-optimal sensor placements in Gaussian processes
ICML '05 Proceedings of the 22nd international conference on Machine learning
Near-optimal sensor placements: maximizing information while minimizing communication cost
Proceedings of the 5th international conference on Information processing in sensor networks
Comparative study of metrics for evaluation of object localisation by bounding boxes.
ICIG '07 Proceedings of the Fourth International Conference on Image and Graphics
Learning to Localize Objects with Structured Output Regression
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Cutting-plane training of structural SVMs
Machine Learning
Efficient Subwindow Search: A Branch and Bound Framework for Object Localization
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Pascal Visual Object Classes (VOC) Challenge
International Journal of Computer Vision
SFO: A Toolbox for Submodular Function Optimization
The Journal of Machine Learning Research
Fast PRISM: Branch and Bound Hough Transform for Object Class Detection
International Journal of Computer Vision
Diverse M-best solutions in markov random fields
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Branch&Rank for Efficient Object Detection
International Journal of Computer Vision
Hi-index | 0.00 |
In this work, we are concerned with the detection of multiple objects in an image. We demonstrate that typically applied objectives have the structure of a random field model, but that the energies resulting from non-maximal suppression terms lead to the maximization of a submodular function. This is in general a difficult problem to solve, which is made worse by the very large size of the output space. We make use of an optimal approximation result for this form of problem by employing a greedy algorithm that finds one detection at a time. We show that we can adopt a branch-and-bound strategy that efficiently explores the space of all subwindows to optimally detect single objects while incorporating pairwise energies resulting from previous detections. This leads to a series of inter-related branch-and-bound optimizations, which we characterize by several new theoretical results. We then show empirically that optimal branch-and-bound efficiency gains can be achieved by a simple strategy of reusing priority queues from previous detections, resulting in speedups of up to a factor of three on the PASCAL VOC data set as compared with serial application of branch-and-bound.