检索结果-内蒙古大学图书馆

Weak celestial source fringes detection based on channel attention shrinkage networks and cluster-based anchor boxes generation algorithm

引用

DIGITAL SIGNAL PROCESSING 2022年第0期129卷

作者： Yan, Ruiqing Ma, Rong Liu, Wei Yin, Zongyao Zhao, Zhengang Chen, Siying Chang, Sheng Zhu, Hui Hu, Dan Yu, Xianchuan Beijing Normal Univ Sch Artificial Intelligence 19 Waida Jie Xinjie Kou Beijing 100875 Peoples R China Chinese Acad Sci Inst Automati Natl Lab Pattern Recognition Beijing 100190 Peoples R China Univ North Carolina Chapel Hill Dept Radiol BRIC Chapel Hill NC 27599 USA Chinese Acad Sci Natl Astron Observat Beijing 100101 Peoples R China

Detecting weak celestial source signals from massive radio data is a very challenging task because the radiation received by radio telescope is very weak and prone to disturbances. In order to detect these weak signals, we propose a two-stage object detection method that performs more finely in computer vision tasks. The novelty of the proposed method is to combine traditional soft thresholding denoising methods with attention mechanisms in deep neural networks. We propose a channel attention shrinkage network as the backbone of the object detection model to extract the features of weak signals from celestial sources by removing noise-related information. Moreover, targeting the characteristics of celestial source fringes in phase images, we propose a cluster-based anchor boxes generation algorithm to improve the accuracy of fringes position detection. We also introduce the CIoU loss function to improve the performance of the model because of the large aspect ratio of the celestial source fringes in the phase image. We generate simulated celestial source fringes data based on the parameters of the observation system to train our model and conduct experiments to evaluate the performance of the proposed algorithm. Our model obtains satisfactory detection accuracy and accurate for the location of celestial source fringes. (C) 2022 Elsevier Inc. All rights reserved.

关键词： Deep learning Weak signal detection Celestial source fringe Soft thresholding Astronomical image processing

来源：评论

学校读者我要写书评

暂无评论

Enhanced Boundary Learning for Glass-like Object Segmentation

arXiv

引用

arXiv 2021年

作者： He, Hao Li, Xiangtai Cheng, Guangliang Shi, Jianping Tong, Yunhai Meng, Gaofeng Prinet, Véronique Weng, Lubin National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Peking University China SenseTime Group Research Centre for Artificial Intelligence and Robotics HK Institute of Science & Innovation CAS 6 Shanghai AI Lab China

Glass-like objects such as windows, bottles, and mirrors exist widely in the real world. Sensing these objects has many applications, including robot navigation and grasping. However, this task is very challenging due to the arbitrary scenes behind glass-like objects. This paper aims to solve the glass-like object segmentation problem via enhanced boundary learning. In particular, we first propose a novel refined differential module that outputs finer boundary cues. We then introduce an edge-aware point-based graph convolution network module to model the global shape along the boundary. We use these two modules to design a decoder that generates accurate and clean segmentation results, especially on the object contours. Both modules are lightweight and effective: they can be embedded into various segmentation models. In extensive experiments on three recent glass-like object segmentation datasets, including Trans10k, MSD, and GDD, our approach establishes new state-of-the-art results. We also illustrate the strong generalization properties of our method on three generic segmentation datasets, including Cityscapes, BDD, and COCO Stuff. Code and models is available at https://***/hehao13/EBLNet. Copyright © 2021, The Authors. All rights reserved.

关键词： Glass

来源：评论

学校读者我要写书评

暂无评论

PoCaP Corpus: A Multimodal Dataset for Smart Operating Room Speech Assistant using Interventional Radiology Workflow Analysis

arXiv

引用

arXiv 2022年

作者： Demir, Kubilay Can May, Matthias Schmid, Axel Uder, Michael Breininger, Katharina Weise, Tobias Maier, Andreas Yang, Seung Hee Speech & Language Processing Lab. Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Radiologisches Institut Universitätsklinikum Erlangen Erlangen Germany Artificial Intelligence in Medical Imaging Lab. Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany

This paper presents a new multimodal interventional radiology dataset, called PoCaP (Port Catheter Placement) Corpus. This corpus consists of speech and audio signals in German, X-ray images, and system commands collected from 31 PoCaP interventions by six surgeons with average duration of 81.4 ± 41.0 minutes. The corpus aims to provide a resource for developing a smart speech assistant in operating rooms. In particular, it may be used to develop a speech-controlled system that enables surgeons to control the operation parameters such as C-arm movements and table positions. In order to record the dataset, we acquired consent by the institutional review board and workers' council in the University Hospital Erlangen and by the patients for data privacy. We describe the recording set-up, data structure, workflow and preprocessing steps, and report the first PoCaP Corpus speech recognition analysis results with 11.52% word error rate using pretrained models. The findings suggest that the data has the potential to build a robust command recognition system and will allow the development of a novel intervention support systems using speech and image processing in the medical *** Codes 00b20 © 2022, CC0.

关键词： Radiation

来源：评论

学校读者我要写书评

暂无评论

Enhanced Boundary Learning for Glass-like Object Segmentation

Enhanced Boundary Learning for Glass-like Object Segmentatio...

引用

International Conference on Computer Vision (ICCV)

作者： Hao He Xiangtai Li Guangliang Cheng Jianping Shi Yunhai Tong Gaofeng Meng Véronique Prinet LuBin Weng National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Key Laboratory of Machine Perception (MOE) Peking University SenseTime Group Research Shanghai AI Lab Centre for Artificial Intelligence and Robotics HK Institute of Science & Innovation CAS

ISBN: (纸本)9781665428132

关键词： Shape Convolution Navigation Semantics Object segmentation Predictive models Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

VideoPipe 2022 Challenge: Real-World Video Understanding for Urban Pipe Inspection

arXiv

引用

arXiv 2022年

作者： Liu, Yi Zhang, Xuan Li, Ying Liang, Guixin Jiang, Yabing Qiu, Lixia Tang, Haiping Xie, Fei Yao, Wei Dai, Yi Qiao, Yu Wang, Yali ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China Shenzhen Bwell Technology Co. Ltd China Shenzhen Longhua Drainage Co. Ltd China Shanghai AI Laboratory Shanghai China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Video understanding is an important problem in computer vision. Currently, the well-studied task in this research is human action recognition, where the clips are manually trimmed from the long videos, and a single class of human action is assumed for each clip. However, we may face more complicated scenarios in the industrial applications. For example, in the real-world urban pipe system, anomaly defects are fine-grained, multi-labeled, domain-relevant. To recognize them correctly, we need to understand the detailed video content. For this reason, we propose to advance research areas of video understanding, with a shift from traditional action recognition to industrial anomaly analysis. In particular, we introduce two high-quality video benchmarks, namely QV-Pipe and CCTV-Pipe, for anomaly inspection in the real-world urban pipe systems. Based on these new datasets, we will host two competitions including (1) Video Defect Classification on QV-Pipe and (2) Temporal Defect Localization on CCTV-Pipe. In this report, we describe the details of these benchmarks, the problem definitions of competition tracks, the evaluation metric, and the result summary. We expect that, this competition would bring new opportunities and challenges for video understanding in smart city and beyond. The details of our VideoPipe challenge can be found in https://***. Copyright © 2022, The Authors. All rights reserved.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models

arXiv

引用

arXiv 2022年

作者： Li, Lei Lin, Yankai Ren, Xuancheng Zhao, Guangxiang Li, Peng Zhou, Jie Sun, Xu MOE Key Lab of Computational Linguistics School of Computer Science Peking University China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Tsinghua University China Pattern Recognition Center WeChat AI Tencent Inc. China

Investigating better ways to reuse the released pre-trained language models (PLMs) can significantly reduce the computational cost and the potential environmental side-effects. This paper explores a novel PLM reuse paradigm, Knowledge Integration (KI). Without human annotations available, KI aims to merge the knowledge from different teacher-PLMs, each of which specializes in a different classification problem, into a versatile student model. To achieve this, we first derive the correlation between virtual golden supervision and teacher predictions. We then design a Model Uncertainty–aware Knowledge Integration (MUKI) framework to recover the golden supervision for the student. Specifically, MUKI adopts Monte-Carlo Dropout to estimate model uncertainty for the supervision integration. An instance-wise re-weighting mechanism based on the margin of uncertainty scores is further incorporated, to deal with the potential conflicting supervision from teachers. Experimental results demonstrate that MUKI achieves substantial improvements over baselines on benchmark datasets. Further analysis shows that MUKI can generalize well for merging teacher models with heterogeneous architectures, and even teachers major in cross-lingual datasets.1 © 2022, CC BY.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Face Presentation Attack Detection

arXiv

引用

arXiv 2022年

作者： Yu, Zitong Zhao, Chenxu Lei, Zhen ROSE Lab Nanyang Technological University Singapore639798 Singapore SailYond Technology Beijing100083 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China Beijing100049 China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong

Face recognition technology has been widely used in daily interactive applications such as checking-in and mobile payment due to its convenience and high accuracy. However, its vulnerability to presentation attacks (PAs) limits its reliable use in ultra-secure applicational scenarios. A presentation attack is first defined in ISO standard as: a presentation to the biometric data capture subsystem with the goal of interfering with the operation of the biometric system. Specifically, PAs range from simple 2D print, replay and more sophisticated 3D masks and partial masks. To defend the face recognition systems against PAs, both academia and industry have paid extensive attention to developing face presentation attack detection (PAD) technology (or namely `face anti-spoofing (FAS)'). Copyright © 2022, The Authors. All rights reserved.

关键词： ISO Standards

来源：评论

学校读者我要写书评

暂无评论

BrainCog: A Spiking Neural Network Based Brain-Inspired Cognitive intelligence Engine for Brain-Inspired AI and Brain Simulation

SSRN

引用

SSRN 2022年

作者： Zeng, Yi Zhao, Dongcheng Zhao, Feifei Shen, Guobin Dong, Yiting Lu, Enmeng Zhang, Qian Sun, Yinqian Liang, Qian Zhao, Yuxuan Zhao, Zhuoya Fang, Hongjian Wang, Yuwei Li, Yang Liu, Xin Du, Chengcheng Kong, Qingqun Ruan, Zizhe Bi, Weida Brain-inspired Cognitive Intelligence Lab Institute of Automation Chinese Academy of Sciences Beijing100190 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China School of Future Technology University of Chinese Academy of Sciences Beijing100049 China

Spiking Neural Networks (SNNs) serve as an appropriate level of abstraction to bring inspirations from brain and cognition to artificial intelligence (AI). Existing software frameworks separately develop SNNs-based brain simulation and brain-inspired intelligence infrastructures. However, the community requires an open-source platform that can simultaneously support building and integrating computational models for brain-inspired AI and brain simulation at multiple scales. To enable the scientific quest to decode the nature of biological intelligence and create AI, we present the SNNs-based Brain-inspired Cognitive intelligence Engine (BrainCog) that provides necessary and essential building blocks, and infrastructural support to develop brain-inspired AI and brain simulation. BrainCog integrates different biological neurons, spike encoding strategies, learning rules, brain areas, etc., as essential components provided by our open-source platform. Based on these easy-to-use components, BrainCog incorporates various cognitive functions, including Perception and Learning, Decision Making, Knowledge Representation and Reasoning, Motor Control, and Social Cognition, as well as the brain structure and function simulations at multiple scales. An AI engine named BORN is developed based on BrainCog, and it demonstrates how the components and cognitive functions of BrainCog can be integrated to build AI models and *** Information: This work is supported by the National Key Research and Development Program (Grant No. 2020AAA0104305), the Strategic Priority Research Program of the Chinese Academy of Sciences (Grant No. XDB32070100).Declaration of Interests: The authors declare no competing interests. © 2022, The Authors. All rights reserved.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

Language Cognition and Language Computation Human and Machine Language Understanding

arXiv

引用

arXiv 2023年

作者： Wang, Shaonan Ding, Nai Lin, Nan Zhang, Jiajun Zong, Chengqing National Laboratory of Pattern Recognition Institute of Automation Cas Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Key Laboratory for Biomedical Engineering of Ministry of Education College of Biomedical Engineering and Instrument Sciences Zhejiang University Hangzhou China Zhejiang Lab Zhejiang University Hangzhou China Cas Key Laboratory of Behavioural Sciences Institute of Psychology Beijing China Department of Psychology University of Chinese Academy of Sciences Beijing China

Language understanding is a key scientific issue in the fields of cognitive and computer science. However, the two disciplines differ substantially in the specific research questions. Cognitive science focuses on analyzing the specific mechanism of the brain and investigating the brain's response to language;few studies have examined the brain's language system as a whole. By contrast, computer scientists focus on the efficiency of practical applications when choosing research questions but may ignore the most essential laws of language. Given these differences, can a combination of the disciplines offer new insights for building intelligent language models and studying language cognitive mechanisms? In the following text, we first review the research questions, history, and methods of language understanding in cognitive and computer science, focusing on the current progress and challenges. We then compare and contrast the research of language understanding in cognitive and computer sciences. Finally, we review existing work that combines insights from language cognition and language computation and offer prospects for future development trends. © 2023, CC BY.

关键词： Intelligent buildings

来源：评论

学校读者我要写书评

暂无评论

Efficient Image Super-Resolution Using Pixel Attention 16th

Efficient Image Super-Resolution Using Pixel Attention

引用

Workshops held at the 16th European Conference on Computer Vision, ECCV 2020

作者： Zhao, Hengyuan Kong, Xiangtao He, Jingwen Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Beijing China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783030670696

This work aims at designing a lightweight convolutional neural network for image super resolution (SR). With simplicity bare in mind, we construct a pretty concise and effective network with a newly proposed pixel attention scheme. Pixel attention (PA) is similar as channel attention and spatial attention in formulation. The difference is that PA produces 3D attention maps instead of a 1D attention vector or a 2D map. This attention scheme introduces fewer additional parameters but generates better SR results. On the basis of PA, we propose two building blocks for the main branch and the reconstruction branch, respectively. The first one—SC-PA block has the same structure as the Self-Calibrated convolution but with our PA layer. This block is much more efficient than conventional residual/dense blocks, for its two-branch architecture and attention scheme. While the second one—U-PA block combines the nearest-neighbor upsampling, convolution and PA layers. It improves the final reconstruction quality with little parameter cost. Our final model—PAN could achieve similar performance as the lightweight networks—SRResNet and CARN, but with only 272K parameters (17.92% of SRResNet and 17.09% of CARN). The effectiveness of each proposed component is also validated by ablation study. The code is available at https://***/zhaohengyuan1/PAN. © 2020, Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：