检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Liang, Rongqin Li, Yuanman Zhou, Jiantao Li, Xia Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen518060 China The State Key Laboratory of Internet of Things for Smart City The Department of Computer and Information Science University of Macau Macau China

Traffic anomaly detection (TAD) in driving videos is critical for ensuring the safety of autonomous driving and advanced driver assistance systems. Previous single-stage TAD methods primarily rely on frame prediction, making them vulnerable to interference from dynamic backgrounds induced by the rapid movement of the dashboard camera. While two-stage TAD methods appear to be a natural solution to mitigate such interference by pre-extracting background-independent features (such as bounding boxes and optical flow) using perceptual algorithms, they are susceptible to the performance of first-stage perceptual algorithms and may result in error propagation. In this paper, we introduce TTHF, a novel single-stage method aligning video clips with text prompts, offering a new perspective on traffic anomaly detection. Unlike previous approaches, the supervised signal of our method is derived from languages rather than orthogonal one-hot vectors, providing a more comprehensive representation. Further, concerning visual representation, we propose to model the high frequency of driving videos in the temporal domain. This modeling captures the dynamic changes of driving scenes, enhances the perception of driving behavior, and significantly improves the detection of traffic anomalies. In addition, to better perceive various types of traffic anomalies, we carefully design an attentive anomaly focusing mechanism that visually and linguistically guides the model to adaptively focus on the visual context of interest, thereby facilitating the detection of traffic anomalies. It is shown that our proposed TTHF achieves promising performance, outperforming state-of-the-art competitors by +5.4% AUC on the DoTA dataset and achieving high generalization on the DADA dataset. © 2024, CC BY.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Autonomous and Incentivized Wireless Connection for Robust Mobile Blockchain Network

引用

IEEE Transactions on Mobile Computing 2025年

作者： Wang, Weiyi Jiao, Yutao Chen, Jin Kang, Jiawen Xu, Yuhua Army Engineering University of Pla College of Communications Engineering Nanjing210007 China Guangdong University of Technology School of Automation Guangzhou510006 China Ministry of Education Key Laboratory of Intelligent Information Processing and System Integration of IoT Guangzhou510006 China

Blockchain has been widely implemented as a trusted platform. Previous works mainly focus on the computing capacity of devices while communication factors play a vital role in blockchain performance during dynamic wireless environments. High-speed movement causes frequent wireless connection interruptions and leads to severe performance degradation of blockchain. Besides, resource-constrained mobile devices are unwilling to selflessly contribute their energy and bandwidth for blockchain, hindering applications in dynamic mobile networks. This paper proposes a reverse auction mechanism to incentivize mobile devices to provide robust wireless connections. Devices submit their connection provision and expected rewards as bids. The mobile blockchain system uses smart contracts to autonomously execute the reverse auction to determine winners and allocate payments based on actual connections. We prove that the reverse auction mechanism is Individual Rationality (IR), Incentive Compatibility (IC), and Computational Efficiency (CE), and derive the approximation ratio 2σ of the mechanism. Extensive simulation results demonstrate that the proposed mechanism decreases up to half the energy and bandwidth consumption, but achieves a similar TPS and stale rate compared to the selfless scheme, where devices contribute all wireless connections for nothing in return. The proposed auction mechanism achieves more than 96% of the optimal social welfare. © 2002-2012 IEEE.

关键词： Dynamic mobile network incentive mechanism mobile blockchain reverse auction

来源：评论

学校读者我要写书评

暂无评论

Expression-Aware Masking and Progressive Decoupling for Cross-Database Facial Expression Recognition

Expression-Aware Masking and Progressive Decoupling for Cros...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Tao Zhong Xiaole Xian Zihan Wang Weicheng Xie Linlin Shen Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University

ISBN: (数字)9798350394948

ISBN: (纸本)9798350394955

Cross-database facial expression recognition (CD-FER) has been widely studied due to its promising applicability in real-life situations, while the generalization performance is the main concern in this task. For improving cross-database generalization, current works frequently resort to masked auto encoder (MAE) to learn the expression representation in an unsupervised manner, and disentanglement of expression and domain features. (i) For MAE, current algorithms mainly employ random masking, and leverage the reconstruction of these masked regions to enable networks to learn the expression representation. However, these masked regions are expression-irrelevant, can not well reflect the characteristics of expression, thus are not efficient enough in representation learning. To this end, we propose an expression-aware masking in MAE to improve the learning efficiency of expression representation, by guiding MAE to mask out expression-aware regions during training. (ii) For disentanglement of expression and domain features, current algorithms realize it mainly in the deep layers. However, the coupling of these features in the shallow layers are rarely concerned, which may largely affect the disentanglement performance in deep layers. Thus, we propose a progressive decoupler to disentangle these features block by block, to use the feature disentanglement in shallow layers to facilitate that in deep layers. Extensive quantitative and qualitative results on multiple expression datasets show that our method can largely outperform the state of the arts in terms of cross-database generalization performance.

关键词： Training Representation learning Couplings Face recognition Gesture recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

MTL-SRN: Multi-task Learning-based Signal Recognition Network

MTL-SRN: Multi-task Learning-based Signal Recognition Networ...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Pengxu Wang Xingjian Zhang Yuan Ma Hao Zhu Jian Jiao Qinyu Zhang Department of Electronics and Information Engineering Harbin Institute of Technology (Shenzhen) Shenzhen China Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Harbin Institute of Technology (Shenzhen) Shenzhen China Peng Cheng Laboratory Shenzhen China State Key Laboratory of Radio Frequency Heterogeneous Integration Guangdong Key Laboratory of Intelligent Information Processing and the College of Electronic and Information Engineering Shenzhen University Shenzhen China

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

Wideband signal recognition is a crucial task in the cognitive wireless communication, involving accurate classification of different signal types, modulation types, center frequencies, etc. However, most conventional approaches treat the recognition of different parameters as multiple independent tasks, and often face performance bottlenecks due to the complexity and diversity of wideband signals. To overcome these challenges, we propose a multi-task learning (MTL) network that integrates multiple tasks of signal recognition into an end-to-end model to accomplish spectrum sensing, modulation recognition, and signal classification simultaneously. By employing a shared feature extraction network and a multi-task classification header, the proposed framework effectively captures the correlations and shared information among different tasks, thereby enhancing overall recognition performance. To validate the effectiveness of the proposed scheme, we compare its performance with other state-of-the-art recognition and classification networks. Experimental results demonstrate the significant performance of the proposed MTL network in spectrum sensing, modulation recognition, and signal classification tasks.

关键词： Wireless communication Correlation Accuracy Frequency modulation Face recognition Pattern classification Multitasking Sensors Global communication Wideband

来源：评论

学校读者我要写书评

暂无评论

TGSIFT: Robust SIFT Descriptor Based on Tensor Gradient for Hyperspectral Images

引用

Chinese Journal of Electronics 2020年第5期29卷 916-925页

作者： LI Yanshan FAN Leidong XIE Weixin ATR National Key Lab.of Defense Technology Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing College of Information Engineering Shenzhen University

This paper proposes a robust sparse descriptor based on tensor theory by using the spatial and spectral information synthetically, namely the Tensor gradient SIFT(TGSIFT), for Hyperspectral image(HSI).TGSIFT integrates both spatial and spectral information and considers the natural vector feature of HSIs. Based on the HSI Gaussian scale space, a new tensor model for HSI is proposed which takes the vectorial nature of HSI into consideration and preserves all the necessary structural information distributed over all the *** TGSIFT descriptor is formed based on the model proposed. Experimental results of HSI matching show that the TGSIFT descriptor achieves better matching performance than other SIFT descriptors under different transformations, including illumination change, sensor noise, image rotation, viewpoint change, and scale change.

关键词： tensor theory geophysical image processing tensors Tensor gradient SIFT (TGSIFT) SIFT descriptors Scale-invariant feature transform (SIFT) feature extraction HSI Gaussian scale space Sparse descriptor tensor model vectors robust SIFT descriptor spatial information image matching necessary structural information Interest points Tensor gradient SIFT transforms image rotation Gaussian processes robust sparse descriptor spectral information vectorial nature hyperspectral images Hyperspectral image (HSI) TGSIFT descriptor Hyperspectral image image representation HSI matching show

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Decoder Model Based On Spiking Neural Networks For Address Event Representation Object Recognition

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Du, Sichun Zhu, Haodi Zhang, Yang Hong, Qinghui Hunan University College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN) provides an energy-saving solution for AER object recognition. However, SNN with spike timing dependent plasticity (STDP) learning rule has not achieved satisfying AER object recognition performance. This work proposes an SNN-based encoder-decoder model to improve the recognition performance of AER objects. An STDP-based locally connected spiking neural network (LC-SNN) is proposed as an encoder to extract rich spatiotemporal features from AER event flows more flexibly. After the encoder extracts and learns primary features, we propose a fully connected spiking neural network (FC-SNN) based on the reward-modulated spike-timing-dependent plasticity (R-STDP) learning rule as a decoder to learn higher-level features for classification. In addition, we improved the winner-take-all (WTA) mechanisms and R-STDP learning rule in the decoder based on the reward and punish decision, enabling the network to perform better. The experiments are performed on the N-MNIST, MNIST-DVS, and the DVS Gesture datasets, improving the accuracy of the best existing plasticity-based SNN by 0.19%, 0.27% and 1.35%, respectively. © 2016 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Implications of neuroimaging findings in addiction

引用

Psychoradiology 2023年第1期3卷 18-23页

作者： Xinwen Wen Lirong Yue Zhe Du Linling Li Yuanqiang Zhu Dahua Yu Kai Yuan School of Life Science and Technology Xidian UniversityXi’an 710126China School of Biomedical Engineering Medical SchoolShenzhen UniversityShenzhen 518060China Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging Shenzhen UniversityShenzhen 518060China Department of Radiology Xijing HospitalFourth Military Medical UniversityXi’an 710032China Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing School of Information EngineeringInner Mongolia University of Science and TechnologyBaotou 014010China Engineering Research Center of Molecular and Neuro Imaging Ministry of Education Xidian UniversityXi’an 710126China Xi’an Key Laboratory of Intelligent Sensing and Regulation of trans-Scale Life Information School of Life Science and TechnologyXidian UniversityXi’an 710126China

Addiction is a chronic and often relapsing brain disorder characterized by drug abuse and withdrawal symptoms and compulsive drug seeking(Koob and Volkow,2010)when access to the drug is *** leads to structural and fun... 详细信息

关键词： motivation finding seeking

来源：评论

学校读者我要写书评

暂无评论

Contour Artifact Removal for Expanded HDR Content

Contour Artifact Removal for Expanded HDR Content

引用

IEEE International Conference on Image processing

作者： Yi Liu Guozhan Sun Wenjing Shuai School of Electronic Engineering Xidian University Xi’an China Guangdong Key Laboratory of Intelligent Information Processing and Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China

High Dynamic Range (HDR) displays are being widely adopted in the consumer electronics market, pushing up the demand of HDR content. However, HDR contents converted from their Standard Dynamic Range (SDR) counterparts often suffer from the contour artifact phenomenon. To address this issue, we formulate a sensitive region aware weighted gradient minimization process to remove the contour artifact. In order to assign reasonable weights to the image gradients in the objective function, we use features composed of local smoothness and gradient directions to highlight the risk regions, and then propose an expansion ratio to precisely locate the artifact. Solving the objective function gives improved HDR images with the contour artifacts minimized and texture preserved. Experimental results demonstrate the effectiveness of our method by the measurement of the objective metrics and visual comparison.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Source Localization for Extremely Large-Scale Antenna Arrays with Spatial Non-Stationarity

Source Localization for Extremely Large-Scale Antenna Arrays...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Xiaohuan Wu Ji Sun Xiaoyuan Jia Shuxin Wang School of Telecommunication and Information Engineering Nanjing University of Posts and Telecommunications Nanjing China Guangdong Key Laboratory of Intelligent Information Processing and Shenzhen Key Laboratory of Media Security Shenzhen China

Extremely large-scale antenna array (ELAA) is a promising technique in 6G and autonomous driving thanks to its high spatial resolution. However, due to the extremely large array aperture, the sources may only "see" a portion of the array, called visibility region (VR). Since the information of VR is usually unknown a priori, traditional methods may encounter performance degradation. In this paper, we show that under the exact steering vector model of ELAA, the eigenvectors of the signal subspace and the steering vectors are approximately collinear in most scenarios. Thus, the angle and range can be easily estimated by using the eigenvectors of the signal subspace. Moreover, the VRs of each source can be also estimated from the eigenvectors of signal subspace. Numerical results show that the estimation performance of our method is comparable to MUSIC with known VR information.

关键词： Location awareness Degradation Estimation Multiple signal classification Numerical models Speech processing Spatial resolution

来源：评论

学校读者我要写书评

暂无评论

ADATS: Adaptive RoI-Align based Transformer for End-to-End Text Spotting

ADATS: Adaptive RoI-Align based Transformer for End-to-End T...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zepeng Huang Qi Wan Junliang Chen Xiaodong Zhao Kai Ye Linlin Shen Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

Scene text spotting has attracted great attention in recent years. Compared with two-stage approaches that locate scene texts in the first stage and recognize them in the second stage, the advantages of joint location and recognition training are not fully explored. In this paper, we present an ADaptive RoI-Align based transformer for end-to-end Text Spotting (ADATS), which simultaneously locates and recognizes text with a single forward pass. By employing an Adaptive RoI-Align, the text features are extracted from the feature extraction network with the original aspect ratio, such that less information is lost during the alignment of arbitrarily-shaped scene text. Attention-based segmentation and recognition heads allow us to simultaneously optimize detection and recognition. Experiments on ICDAR 2015, MSRA-TD500, Total-Text, and CTW1500 demonstrate the effectiveness of our method.

关键词：

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：