scispace - formally typeset
Search or ask a question
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
More filters
Journal ArticleDOI
TL;DR: The authors proposed a high-resolution rectified gradient-based class activation mapping with bounding box annotations (bbox) to improve the initial seed for weakly supervised segmentation (WSS) tasks.

4 citations

Book ChapterDOI
21 Oct 2019
TL;DR: This paper presents an alternative bounding technique that, under specific conditions, treats dependent flows as if flows were independent, and shows that it provides often better delay bounds while simultaneously significantly improving the computation time.
Abstract: Computing probabilistic end-to-end delay bounds is an old, yet still challenging problem. Stochastic network calculus enables closed-form delay bounds for a large class of arrival processes. However, it encounters difficulties in dealing with dependent flows, as standard techniques require to apply Holder’s inequality. In this paper, we present an alternative bounding technique that, under specific conditions, treats them as if flows were independent. We show in two case studies that it often provides better delay bounds while simultaneously significantly improving the computation time.

4 citations

Journal ArticleDOI
TL;DR: A novel scene text detector using a deep convolutional network which efficiently detects arbitrary oriented and complex-shaped text segments from natural scenes and predicts quadrilateral bounding boxes around text segments.
Abstract: In spite of significant research efforts, the existing scene text detection methods fall short of the challenges and requirements posed in real-life applications. In natural scenes, text segments exhibit a wide range of shape complexities, scale, and font property variations, and they appear mostly incidental. Furthermore, the computational requirement of the detector is an important factor for real-time operation. To address the aforementioned issues, the paper presents a novel scene text detector using a deep convolutional network which efficiently detects arbitrary oriented and complex-shaped text segments from natural scenes and predicts quadrilateral bounding boxes around text segments. The proposed network is designed in a U-shape architecture with the careful incorporation of skip connections to capture complex text attributes at multiple scales. For addressing the computational requirement of the input processing, the proposed scene text detector uses the MobileNet model as the backbone that is designed on depthwise separable convolutions. The network design is integrated with text attention blocks to enhance the learning ability of our detector, where the attention blocks are based on efficient channel attention. The network is trained in a multi-objective formulation supported by a novel text-aware non-maximal procedure to generate final text bounding box predictions. On extensive evaluations on ICDAR2013, ICDAR2015, MSRA-TD500, and COCOText datasets, the paper reports detection F-scores of 0.910, 0.879, 0.830, and 0.617, respectively.

4 citations

Proceedings ArticleDOI
09 Dec 2003
TL;DR: A rigorous convergence analysis is performed and a number of algorithm's properties are highlighted such as the decrease of the normed estimation error, the shrinkage of the parameters outer-bounding set and the acceptability of the output error.
Abstract: This contribution proposes a recursive and easily implementable online algorithm for the parameters estimation of linear multi-output systems using ellipsoidal bounds on the unknown observation noises. A simple approach based on parameters bounding techniques is presented. A particular /spl omega/-parameterization of the algorithm is used, first to characterize, at each step, the set containing all possible values of the true parameters consistent with input/output data and the noises' bounds and also to guaranty the convergence of the estimated parameters to some neighborhood of their true values. A rigorous convergence analysis is performed and a number of algorithm's properties are highlighted such as the decrease of the normed estimation error, the shrinkage of the parameters outer-bounding set and the acceptability of the output error. Finally, the theoretical results are illustrated by a numerical simulation on a simple example.

4 citations

Journal ArticleDOI
TL;DR: Zhang et al. as discussed by the authors proposed an Object Class Head Detector (OCDT) model for fine-grained segmentation of cloth products in a single platform, which can improve the accuracy of cloth shape segmentation by preserving object contours.
Abstract: Visual analysis of fashion images gain much attention in the fashion industry due to its commercial and social importance. In recent years, deep learning techniques offer overwhelming progress in improving the accuracy of fine-grained apparel segmentation with accurate bounding box prediction. The baseline pixel-based masking techniques show excellent performance in object detection and segmentation but sometimes ignores the boundary of objects, resulting in uneven and complicated segmentation masks. Moreover, it is time taking to generate a multi-scale feature map against each anchor box. To remedy this problem, a more accurate, faster, and suitable deep learning architecture is proposed that accurately detects, classify, and performs fine-grained segmentation of cloth products in a single platform. In this paper, initially, an Object Class Head Detector model is proposed in which the baseline Mask-RCNN model is used as a reference model. Here, we replace the Region Proposal Network with the proposed modified YoloV2 model to locate apparel products with its class prediction. The modified YoloV2 model has more capability to detect tiny objects because of local and high-level feature fusion. The goal of this step is to accurately locate the objects in minimum time intervals. Furthermore, the predicted bounding box is converted to object shape offsets using deep snake architecture that tightly fits onto the apparel shape. It can improve the accuracy of cloth shape segmentation by preserving object contours. The proposed architecture is empirically validated on various existing fashion image datasets. The experimental results illustrate that the proposed architecture performs better on the Deepfashion2 dataset with mAP of 86.86%, as compared to other state-of-the-art deep learning models.

4 citations


Network Information
Related Topics (5)
Robustness (computer science)
94.7K papers, 1.6M citations
85% related
Optimization problem
96.4K papers, 2.1M citations
85% related
Matrix (mathematics)
105.5K papers, 1.9M citations
82% related
Nonlinear system
208.1K papers, 4M citations
81% related
Artificial neural network
207K papers, 4.5M citations
80% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023714
20221,629
2021155
202075
201973
201850