Bounding overwatch

About: Bounding overwatch is a research topic. Over the lifetime, 966 publications have been published within this topic receiving 15156 citations.

Bounding 3d CFT correlators

Abstract: We consider the problem of bounding CFT correlators on the Euclidean section. By reformulating the question as an optimization problem, we construct functionals numerically which determine upper and lower bounds on correlators under several circumstances. A useful outcome of our analysis is that the gap maximization bootstrap problem can be reproduced by a numerically easier optimization problem. We find that the 3d Ising spin correlator takes the minimal possible allowed values on the Euclidean section. Turning to the maximization problem we find that for d > 2 there are gap-independent maximal bounds on CFT correlators. Under certain conditions we show that the maximizing correlator is given by the generalized free boson for general Euclidean kinematics. In our explorations we also uncover an intriguing 3d CFT which saturates gap, OPE maximization and correlator value bounds. Finally we comment on the relation between our functionals and the Polyakov bootstrap.

Deep Multivariate Mixture of Gaussians for Object Detection under Occlusion

Abstract: In this paper, we consider the problem of detecting object under occlusion. Most object detectors formulate bounding box regression as a unimodal task (i.e., regressing a single set of bounding box coordinates independently). However, we observe that the bounding box borders of an occluded object can have multiple plausible configurations. Also, the occluded bounding box borders have correlations with visible ones. Motivated by these two observations, we propose a deep multivariate mixture of Gaussians model for bounding box regression under occlusion. The mixture components potentially learn different configurations of an occluded part, and the covariances between variates help to learn the relationship between the occluded parts and the visible ones. Quantitatively, our model improves the AP of the baselines by 3.9% and 1.2% on CrowdHuman and MS-COCO respectively with almost no computational or memory overhead. Qualitatively, our model enjoys explainability since we can interpret the resulting bounding boxes via the covariance matrices and the mixture components.

Point RCNN: An Angle-Free Framework for Rotated Object Detection

Abstract: Rotated object detection in aerial images is still challenging due to arbitrary orientations, large scale and aspect ratio variations, and extreme density of objects. Existing state-of-the-art rotated object detection methods mainly rely on angle-based detectors. However, angle-based detectors can easily suffer from a long-standing boundary problem. To tackle this problem, we propose a purely angle-free framework for rotated object detection, called Point RCNN. Point RCNN is a two-stage detector including both PointRPN and PointReg which are angle-free. Given an input aerial image, first, the backbone-FPN extracts hierarchical features, then, the PointRPN module generates an accurate rotated region of interests (RRoIs) by converting the learned representative points of each rotated object using the MinAreaRect function of OpenCV. Motivated by RepPoints, we designed a coarse-to-fine process to regress and refine the representative points for more accurate RRoIs. Next, based on the learned RRoIs of PointRPN, the PointReg module learns to regress and refine the corner points of each RRoI to perform more accurate rotated object detection. Finally, the final rotated bounding box of each rotated object can be attained based on the learned four corner points. In addition, aerial images are often severely unbalanced in categories, and existing rotated object detection methods almost ignore this problem. To tackle the severely unbalanced dataset problem, we propose a balanced dataset strategy. We experimentally verified that re-sampling the images of the rare categories can stabilize the training procedure and further improve the detection performance. Specifically, the performance was improved from 80.37 mAP to 80.71 mAP in DOTA-v1.0. Without unnecessary elaboration, our Point RCNN method achieved new state-of-the-art detection performance on multiple large-scale aerial image datasets, including DOTA-v1.0, DOTA-v1.5, HRSC2016, and UCAS-AOD. Specifically, in DOTA-v1.0, our Point RCNN achieved better detection performance of 80.71 mAP. In DOTA-v1.5, Point RCNN achieved 79.31 mAP, which significantly improved the performance by 2.86 mAP (from ReDet’s 76.45 to our 79.31). In HRSC2016 and UCAS-AOD, our Point RCNN achieved higher performance of 90.53 mAP and 90.04 mAP, respectively.

Ray cone hierarchy renderer

Abstract: Some aspects of the disclosure include systems and methods for grouping rays into sets according to their directions. In some cases, the rays of the directional sets may then be organized into a hierarchy according to their origins and bounding cones are generated for the hierarchy nodes. The resulting bounding cone hierarchy may be intersected with a bounding volume hierarchy or other scene hierarchy.