Topic
Bounding overwatch
About: Bounding overwatch is a research topic. Over the lifetime, 966 publications have been published within this topic receiving 15156 citations.
Papers published on a yearly basis
Papers
More filters
TL;DR: A novel technique for bounded analysis of asynchronous message-passing programs with ordered message queues that avoids explicitly representing message queues and gives rise to a simple and efficient program analysis by reduction to sequential programs.
Abstract: We describe a novel technique for bounded analysis of asynchronous message-passing programs with ordered message queues. Our bounding parameter does not limit the number of pending messages, nor the number of "context-switches" between processes. Instead, we limit the number of process communication cycles, in which an unbounded number of messages are sent to an unbounded number of processes across an unbounded number of contexts. We show that remarkably, despite the potential for such vast exploration, our bounding scheme gives rise to a simple and efficient program analysis by reduction to sequential programs. As our reduction avoids explicitly representing message queues, our analysis scales irrespectively of queue content and variation.
37 citations
TL;DR: A novel functional is formulated that governs an optimization process to obtain a partition with multiple components to computing a union of tight bounding volumes based on an affine invariant measure of e‐tightness, the resemblance to ellipsoid.
Abstract: We propose a variational approach to computing an optimal segmentation of a 3D shape for computing a union of tight bounding volumes. Based on an affine invariant measure of e-tightness, the resemblance to ellipsoid, a novel functional is formulated that governs an optimization process to obtain a partition with multiple components. Refinement of segmentation is driven by application-specific error measures, so that the final bounding volume meets pre-specified user requirement. We present examples to demonstrate the effectiveness of our method and show that it works well for computing ellipsoidal bounding volumes as well as oriented bounding boxes.
37 citations
TL;DR: SiamCorners as mentioned in this paper proposes a modified corner pooling layer to convert the bounding box estimate of the target into a pair of corner predictions (the bottom-right and the top-left corners).
Abstract: The current Siamese network based on region proposal network (RPN) has attracted great attention in visual tracking due to its excellent accuracy and high efficiency. However, the design of the RPN involves the selection of the number, scale, and aspect ratios of anchor boxes, which will affect the applicability and convenience of the model. Furthermore, these anchor boxes require complicated calculations, such as calculating their intersection-over-union (IoU) with ground truth bounding boxes. Due to the problems related to anchor boxes, we propose a simple yet effective anchor-free tracker (named Siamese corner networks, SiamCorners), which is end-to-end trained offline on large-scale image pairs. Specifically, we introduce a modified corner pooling layer to convert the bounding box estimate of the target into a pair of corner predictions (the bottom-right and the top-left corners). By tracking a target as a pair of corners, we avoid the need to design the anchor boxes. This will make the entire tracking algorithm more flexible and simple than anchor-based trackers. In our network design, we further introduce a layer-wise feature aggregation strategy that enables the corner pooling module to predict multiple corners for a tracking target in deep networks. We then introduce a new penalty term that is used to select an optimal tracking box in these candidate corners. Finally, SiamCorners achieves experimental results that are comparable to the state-of-art tracker while maintaining a high running speed. In particular, SiamCorners achieves a 53.7% AUC on NFS30 and a 61.4% AUC on UAV123, while still running at 42 frames per second (FPS).
37 citations
TL;DR: Weakly-Supervised Object Detection (WSOD) and Localization (WSOL) are long-standing and challenging tasks in object detection as discussed by the authors , and numerous techniques have been proposed in the deep learning era.
37 citations
TL;DR: Lower bounds on the approximation factor of PCA bounding boxes of convex sets in arbitrary dimension, and upper bounds in R^2 and R^3 are contributed.
Abstract: Principal component analysis (PCA) is commonly used to compute a bounding box of a point set in R^d. The popularity of this heuristic lies in its speed, easy implementation and in the fact that usually, PCA bounding boxes quite well approximate the minimum-volume bounding boxes. We present examples of discrete points sets in the plane, showing that the worst case ratio of the volume of the PCA bounding box and the volume of the minimum-volume bounding box tends to infinity. Thus, we concentrate our attention on PCA bounding boxes for continuous sets, especially for the convex hull of a point set. Here, we contribute lower bounds on the approximation factor of PCA bounding boxes of convex sets in arbitrary dimension, and upper bounds in R^2 and R^3.
37 citations