检索结果-内蒙古大学图书馆

Visual Object Tracking via Cascaded RPN Fusion and Coordinate Attention

Computer Modeling in Engineering & Sciences 2022年第9期132卷 909-927页

作者： Jianming Zhang Kai Wang Yaoqi He Lidan Kuang School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China

Recently,Siamese-based trackers have achieved excellent performance in object ***,the high speed and deformation of objects in the movement process make tracking ***,we have incorporated cascaded region-proposal-network(RPN)fusion and coordinate attention into Siamese *** proposed network framework consists of three parts:a feature-extraction sub-network,coordinate attention block,and cascaded RPN *** exploit the coordinate attention block,which can embed location information into channel attention,to establish long-term spatial location dependence while maintaining channel ***,the features of different layers are enhanced by the coordinate attention *** then send these features separately into the cascaded RPN for classification and *** to the two classification and regression results,the final position of the target is *** verify the effectiveness of the proposed method,we conducted comprehensive experiments on the OTB100,VOT2016,UAV123,and GOT-10k *** with other state-of-the-art trackers,the proposed tracker achieved good performance and can run at real-time speed.

关键词： Object tracking deep learning coordinate attention cascaded RPN

来源：评论

学校读者我要写书评

暂无评论

Towards interpreting deep neural networks via layer behavior understanding

引用

MACHINE LEARNING 2022年第3期111卷 1159-1179页

作者： Cao, Jiezhang Li, Jincheng Hu, Xiping Wu, Xiangmiao Tan, Mingkui South China Univ Technol Guangzhou Peoples R China Pazhou Lab Guangzhou Peoples R China Minist Educ Key Lab Big Data & Intelligent Robot Guangzhou Peoples R China Lanzhou Univ Lanzhou Peoples R China

Deep neural networks (DNNs) have achieved success in many machine learning tasks. However, how to interpret DNNs is still an open problem. In particular, how do hidden layers behave is not clearly understood. In this paper, relying on a teacher-student paradigm, we seek to understand the layer behaviors of DNNs by "monitoring" the distribution evolution for both across-layer and single-layer along the depth and training epochs, respectively. Relying on the optimal transport theory, we employ the Wasserstein distance (W-distance) to measure the divergence between the layer distribution and the target distribution. Theoretically, we prove that (i) the W-distance between the distribution of any layer and the target distribution tends to decrease along the depth;(ii) for a specific layer, the W-distance between the distribution in an iteration and the target distribution tends to decrease along training epochs;(iii) a deeper layer, however, is not always better than a shallower layer. Relying on these properties, we are able to propose an early-exit inference method to improve the performance of the multi-label classification. Moreover, our results help to analyze the stability of layer distributions and explain why auxiliary losses are helpful in training DNNs. Extensive experiments justify our theoretical findings.

关键词： Layer behavior Wasserstein distance Teacher-student paradigm

来源：评论

学校读者我要写书评

暂无评论

Continuous and generalized visual odometry based on FLANN_PSC-RANSAC_LSTM

引用

Journal of intelligent and Fuzzy Systems 2024年第1-2期47卷 15-28页

作者： Li, Dengao Feng, Ran Wu, Fanming Zhao, Jinhua Zhao, Jumin College of Computer Science and Technology College of Data Science Taiyuan University of Technology Shanxi Taiyuan China College of Electronic Information and Optical Engineering Taiyuan University of Technology Shanxi Taiyuan China Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province Taiyuan University of Technology Shanxi Taiyuan China Intelligent Perception Engineering Technology Center of Shanxi Taiyuan China

In the field of simultaneous localization and mapping (SLAM), visual odometry (VO) always has great application prospects. In recent years, with the progress in the field of machine learning, methods based on neural networks are constantly being updated and applied. In this paper, we propose a continuous and generalized monocular visual odometry method based on features and neural networks. First, the feature information of adjacent image sequences is extracted by matching and troubleshooting algorithm (FLANN_PSC-RANSAC), then it and the corresponding six-degree-of-freedom information are simultaneously input into the long short-term memory artificial neural network (LSTM) for model construction, which not only ensures the reliability of the mode but also eliminates the influence of illumination on the data. In the real environment test, it has been effectively proved in terms of trajectory recovery accuracy and generalization ability to different environments and different illuminations. © 2024 - IOS Press. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Remote Image Acquisition System Based on STM32 for Spodoptera frugiperda 5

Remote Image Acquisition System Based on STM32 for Spodopter...

引用

5th IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2022

作者： Chang, Jumei Xu, Quanyuan Lu, Ying Zhang, Hanrui College of Big Data and Intelligent Engineering Southwest Forestry University Kunming China Southwest Forestry University Key Laboratory of Forestry and Ecological Big Data State Forestry Administration China

ISBN: (纸本)9781665479677

To enable remote image acquisition and wireless transmission for field sex lure monitoring of Spodoptera frugiperda, the design consists of a CPU processor module, power supply module, image acquisition module, 4G wireless network transmission module, and external SRAM module. The system employs the STM32F407 control core, the OV2640 camera for image acquisition, the JPEG algorithm to compress and decode the image data collected by the camera, and automatically restore the image collected at the monitoring point, the EC20 as a 4G wireless communication network for image data transmission, and the transmission of real-time image data to the server side of the upper computer to achieve human-computer interaction and real-time interaction of system daemons. The experimental results show that the system achieves remote image acquisition of grassland moths and reliably transmits the collected image data to the server side of the upper computer via a 4G wireless network, allowing the monitor to view images of grassland moth monitoring points collected by the system in real-time and save the collected image data locally. This system accomplishes the automation and intelligence of the grassland moth monitoring system, prepares the data for subsequent grassland moth research, and has a broad application promise for grassland moth population monitoring. © 2022 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

CETO-Sim: A Simulation Platform for Cloud-Edge Task Offloading 25

CETO-Sim: A Simulation Platform for Cloud-Edge Task Offloadi...

引用

25th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2022

作者： Yao, Rui Xu, Xiaolong Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Jiangsu Nanjing China

ISBN: (纸本)9781665405270

In order to verify the effectiveness of task offloading algorithms in large-scale cloud and edge computing systems, scholars usually use simulation platforms to conduct extensive experiments. However, existing simulation platforms have unclear application scenarios and relatively homogeneous functions, which cannot fully exploit the respective advantages of cloud and edge computing. To address the above issues, this paper designs a new simulation platform, CETO-Sim (Cloud-Edge Task Offloading Simulation), for the cloud-edge aggregation computing scenario, which is convenient for users to verify the effectiveness of the task offloading algorithm. The platform adopts a modular design strategy, allowing users to invoke the various interfaces provided by the platform to simulate and build different physical entities, and to freely combine them to simulate different computing environments. The platform contains six components: task management component, network topology component, end-user component, scheduling policy component, server component and operation component. The platform simulates the task offloading process through the interaction between these components, while recording the changes of various parameters of tasks and simulated entities in real time, and finally printing out the experimental results in the form of logs. This paper presents an example of task offloading using the particle swarm algorithm in a cloud-side aggregated computing environment, demonstrating that the CETO-Sim platform has the advantages of clear architecture, simple operation, easy deployment, accurate experimental results and high simulation efficiency, and also verifying the feasibility of deploying the platform in other scenarios. © 2022 IEEE.

关键词： Simulation platform

来源：评论

学校读者我要写书评

暂无评论

Privacy protection oriented on data stream computing

Privacy protection oriented on data stream computing

引用

2022 International Conference on Computer Application and Information Security, ICCAIS 2022

作者： He, Renjie Zheng, Xianghan Wang, Gong School of Computer and Big Data Fuzhou University Fujian Fuzhou China The Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fujian Fuzhou China

ISBN: (纸本)9781510663459

data security has always been one of the public concerns, and homomorphic encryption technology, as one of the effective means to ensure data security, has always been a hot topic of academic research. Traditional machine learning is trained in a batch environment. In practice, data owners tend to outsource data and model training tasks to third-party clouds with huge computing resources, but data outsourcing carries the risk of privacy leakage. Therefore, in order to prevent this situation, an effective method is to encrypt the data before the outsourcing, and the third-party cloud trains the machine model of the ciphertext data. This method has special requirements for encryption algorithms which should support computation directly on the ciphertext data. This paper presents a novel data flow computing privacy protection framework based on the homomorphic encryption algorithm CKKS and the flow data processing engine Flink, called SDPPF (Streaming data Privacy Protection on Flink). The proposed framework supports the functions of data stream encryption, decryption and ciphertext computing, and expands the functions of vector point multiplication and array sum operation on the basic simultaneous operation supported by the original CKKS algorithm. This paper also selects a classical machine learning algorithm: KNN algorithm, combined with the homomorphic encryption algorithm CKKS to realize the privacy protection machine learning algorithm. © 2023 SPIE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Relation Classification based on Selective Entity-Aware Attention 25

Relation Classification based on Selective Entity-Aware Atte...

引用

25th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2022

作者： Ding, Haijie Xu, Xiaolong Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Jiangsu Nanjing China

ISBN: (纸本)9781665405270

Relation classification aims to classify the entity pairs into a certain relation, which is an important task of natural language processing. The latest end-to-end models based on attention mechanism still have shortcomings, i.e., the attention will be gradually weakened when processing long sequences, and they cannot make use of the hidden type information of the entities. To solve these problems, we propose a relation classification model based on the selective entity-aware attention mechanism, which consists of context encoder and entity-aware attention network. In the context encoder, contextual word semantics are learned through self-attention. Entity selection is applied to adapt the fact that different words can determine each other's importance. Latent types of entities are taken as auxiliary information to make full use of the entities' hidden features. Experiments on the SemEval-2010 Task 8 dataset and TACRED show that our model outperforms the baselines without implementing any external resources or NLP tools, and the entity-aware attention indeed improve the model's performance. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Superclass-aware visual feature disentangling for generalized zero-shot learning

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 258卷

作者： Niu, Chang Shang, Junyuan Zhou, Zhiheng Yang, Junmei South China Univ Technol Sch Elect & Informat Engn Guangzhou 510640 Peoples R China Foshan Univ Sch Comp Sci & Artificial Intelligence Foshan 528000 Peoples R China GRG Banking Equipment Co Ltd Guangzhou 510663 Peoples R China South China Univ Technol Key Lab Big Data & Intelligent Robot Minist Educ Guangzhou Peoples R China

Zero-shot learning (ZSL) aims to learn a model trained on seen samples with the ability to recognize samples from unseen classes, while generalized ZSL (GZSL) takes a step closer to realistic scenarios by recognizing both of seen and unseen samples. The existing methods rely on the semantic descriptions as the side-information and conduct tight alignment between the visual and semantic spaces. However, the tight modality alignment may result in incomplete representations, leading to the loss of originally detailed and discriminative information. In this paper, we propose a simple yet effective superclass-aware visual feature disentangling method termed as SupVFD for GZSL. We use the neighbor relations of the semantic descriptions to define superclass and with the guide of superclass, our method disentangles visual features into discriminative and transferable factors. To this end, the semantic descriptions are used as implicit supervision, which preserves the valuable detailed and discriminative information in the visual features. The extensive experiments in both ZSL and GZSL settings prove our method outperforms the state-of-the-art methods for image object classification as well as video action recognition. Code is available at our github: https://***/changniu54/SupVFD-Master.

关键词： Zero-shot learning Transfer learning Image classification Action recognition

来源：评论

学校读者我要写书评

暂无评论

A Polynomial-Time Algorithm for MCS Partial Search Order on Chordal Graphs 48

A Polynomial-Time Algorithm for MCS Partial Search Order on ...

引用

48th International Symposium on Mathematical Foundations of Computer Science, MFCS 2023

作者： Rong, Guozhen Yang, Yongjie Li, Wenjun Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and Technology China Chair of Economic Theory Saarland University Saarbrücken Germany

ISBN: (纸本)9783959772921

We study the partial search order problem (PSOP) proposed recently by Scheffler [WG 2022]. Given a graph G together with a partial order on the set of vertices of G, this problem determines if there is an S-ordering that is consistent with the given partial order, where S is a graph search paradigm like BFS, DFS, etc. This problem naturally generalizes the end-vertex problem which has received much attention over the past few years. It also generalizes the so-called F-tree recognition problem which has just been studied in the literature recently. Our main contribution is a polynomial-time dynamic programming algorithm for the PSOP of the maximum cardinality search (MCS) restricted to chordal graphs. This resolves one of the most intriguing open questions left in the work of Scheffler [WG 2022]. To obtain our result, we propose the notion of layer structure and study numerous related structural properties which might be of independent interest. © Guozhen Rong, Yongjie Yang, and Wenjun Li

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

VECSim: A Simulation Platform for Multi-bitrate Video Caching Collaboratively in Edge Computing Network 25

VECSim: A Simulation Platform for Multi-bitrate Video Cachin...

引用

25th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2022

作者： Chen, Peipei Xu, Xiaolong Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Jiangsu Nanjing China

ISBN: (纸本)9781665405270

The development of the mobile Internet has led to a shape increase in video traffic data. New Mobile Edge Computing (MEC) technology can reduce network operation and service delivery delays, so as to improving the QoE (Quality of Experience) of user. In MEC environment, this article builds a simulation platform for multi-bitrate video caching and scheduling scenarios VECSim (Video Edge CloudSim). VECSim provides a simulation environment specific to verify multi-bitrate video caching collaboratively and scheduling strategy in the Mobile Edge Computing scenarios. Unlike simple numerical simulations and complex real-world deployments, VECSim provides a simple interface that can be called by the user, besides, it can be used to provide larger-scale, more flexible request scenarios which are closer to the actual environment. Based on the edge computing simulation platform EdgeCloudSim, this platform adds and modifies quite a few functions so that it can be effectively used in multi-bitrate video caching and scheduling scenarios, which now includes seven main modules: Server Management Modules, Network Module, User Mobility Module, Task Loader Generator Module, Video Storage Module, Edge Client Management Module, and Edge Orchestrator Module. With this platform, researchers can easily and quickly verify their video caching and scheduling strategies. © 2022 IEEE.

关键词： Mobile edge computing

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：