• Publications
  • Influence
Improving Object Localization with Fitness NMS and Bounded IoU Loss
A simple and fast modification to the existing methods called Fitness NMS is proposed and obtains a significantly improved MAP at greater localization accuracies without a loss in evaluation rate, and can be used in conjunction with Soft NMS for additional improvements. Expand
Encouraging LSTMs to Anticipate Actions Very Early
A new action anticipation method that achieves high prediction accuracy even in the presence of a very small percentage of a video sequence, and develops a multi-stage LSTM architecture that leverages context-aware and action-aware features, and introduces a novel loss function that encourages the model to predict the correct class as early as possible. Expand
Statistical Threat Assessment for General Road Scenes Using Monte Carlo Sampling
  • A. Eidehall, L. Petersson
  • Engineering, Computer Science
  • IEEE Transactions on Intelligent Transportation…
  • 1 March 2008
The algorithm is intended both for online safety applications in a vehicle and for offline data analysis, and several techniques are presented to increase performance without increasing computational load. Expand
GOGMA: Globally-Optimal Gaussian Mixture Alignment
The algorithm, named GOGMA, employs a branch-and-bound approach to search the space of 3D rigid motions SE(3), guaranteeing global optimality regardless of the initialisation, and demonstrates that the method performed much more robustly on two challenging datasets than an existing globally-optimal registration solution. Expand
A new pedestrian dataset for supervised learning
This paper presents a comparative analysis of different pedestrian dataset characteristics. The main goal of the research is to determine what characteristics are desirable for improved training andExpand
Large scale sign detection using HOG feature variants
The aim of this research is to find features capable of driving further improvements atop a preexisting detection framework used commercially to detect traffic signs on the scale of entire national road networks (1000's of kilometres of video). Expand
Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation
This work proposes a novel method to extract markedly more accurate masks from the pre-trained network itself, forgoing external objectness modules, and introduces a new form of inexpensive weak supervision yielding an additional accuracy boost. Expand
An Adaptive Data Representation for Robust Point-Set Registration and Merging
A framework for rigid point-set registration and merging using a robust continuous data representation and a novel algorithm, GMMerge, that parsimoniously and equitably merges aligned mixture models, allowing the framework to be used for reconstruction and mapping. Expand
Globally-Optimal Inlier Set Maximisation for Camera Pose and Correspondence Estimation
This work proposes a robust and globally-optimal inlier set maximisation approach that jointly estimates the optimal camera pose and correspondences, and outperforms existing approaches on challenging synthetic and real datasets, reliably finding the global optimum. Expand
Effective Use of Synthetic Data for Urban Scene Semantic Segmentation
A drastically different way to handle synthetic images that does not require seeing any real images at training time is introduced, which builds on the observation that foreground and background classes are not affected in the same manner by the domain shift, and thus should be treated differently. Expand