2021 IEEE 7th International Conference on Cloud Computing and Intelligent Systems (CCIS)最新文献_第8页

CFPA-Net: Cross-layer Feature Fusion And Parallel Attention Network For Detection And Classification of Prohibited Items in X-ray Baggage Images CFPA-Net: x射线行李图像中违禁物品检测与分类的跨层特征融合并行关注网络

2021 IEEE 7th International Conference on Cloud Computing and Intelligent Systems (CCIS) Pub Date : 2021-11-07 DOI: 10.1109/CCIS53392.2021.9754631

Yifan Wei, Yizhuo Wang, Hong Song

{"title":"CFPA-Net: Cross-layer Feature Fusion And Parallel Attention Network For Detection And Classification of Prohibited Items in X-ray Baggage Images","authors":"Yifan Wei, Yizhuo Wang, Hong Song","doi":"10.1109/CCIS53392.2021.9754631","DOIUrl":"https://doi.org/10.1109/CCIS53392.2021.9754631","url":null,"abstract":"As objects in the baggage are often heavily overlapped and cluttered, the X-ray baggage inspection is an inherently challenging task. In this paper, we propose a cross-layer feature fusion and parallel attention network named CFPA-Net to detect and classify the prohibited items in X-ray baggage images. The CFPA-Net is based on RetinaNet with three modules: cross-layer feature extraction fusion module (CEF-Module), paralleled attention module (PA-Module) and FreeAnchor. In CEF-Module, an improved feature pyramid network is proposed by adding multi-directional lateral connections for cross-layer feature extraction and fusion. It can help detect objects of various scales and supplement deficient semantic and localization information for low layer and high layer features respectively. PA-Module is presented to learn the feature relationship and fully utilize the extracted features by introducing two paralleled attention subnets Squeeze-and-Excitation module and Non-local module. PA-Module can help improve the performance of detecting and classification by emphasizing useful features, suppressing useless features selectively and capturing long-range dependencies in images. FreeAnchor is adopted to deal with the restriction of hand-crafted anchor assignment according to Intersection-over-Unit. It can help find the best anchor for each object by learning, and improve the performance of detecting slender objects and the ones in crowded scenes. On the public dataset OPIXray, CFPA-Net achieves 85.82% detection mean Average Precision. Moreover, achieving 81.61% classification mean Average Precision on the SIXray10 dataset. The experimental results show that our proposed CFPA-Net is more accurate and robust for the X-ray baggage inspection with densely occluded objects and complicated backgrounds.","PeriodicalId":191226,"journal":{"name":"2021 IEEE 7th International Conference on Cloud Computing and Intelligent Systems (CCIS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115420104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Modified Decomposition Based Multi-objective Optimization Algorithm for High Dimensional Feature Selection 基于改进分解的高维特征选择多目标优化算法

2021 IEEE 7th International Conference on Cloud Computing and Intelligent Systems (CCIS) Pub Date : 2021-11-07 DOI: 10.1109/CCIS53392.2021.9754686

Manlin Xuan, Lingjie Li, Qiuzhen Lin, Zhong Ming, Wenhong Wei

引用次数: 1

Spatiotemporal Representation Learning for Taxi Pick-up Point Recommendation 基于时空表征学习的出租车上车点推荐

2021 IEEE 7th International Conference on Cloud Computing and Intelligent Systems (CCIS) Pub Date : 2021-11-07 DOI: 10.1109/CCIS53392.2021.9754610

Yuyuan Huang, Yanwei Yu, Peng Jiang

引用次数: 1

Deep Face Recognition for Intelligent Video Surveillance at Electrical Substations 变电站智能视频监控的深度人脸识别

2021 IEEE 7th International Conference on Cloud Computing and Intelligent Systems (CCIS) Pub Date : 2021-11-07 DOI: 10.1109/CCIS53392.2021.9754622

Bo Dai, Jinxia Jiang, Guizhu Shen, Xue Wang, Qing Wang

引用次数: 0

Design of Intelligent Collision Avoidance System for Fishing Vessels Based on AIS 基于AIS的渔船智能避碰系统设计

2021 IEEE 7th International Conference on Cloud Computing and Intelligent Systems (CCIS) Pub Date : 2021-11-07 DOI: 10.1109/CCIS53392.2021.9754607

Rui Zhuang, Yuanhong Wu, Wen-Jiao Chen, Jianke Zhang

引用次数: 0

A Voronoi Neighborhood Based Differential Evolution Algorithm for Multimodal Multi-objective Optimization 基于Voronoi邻域的多模态多目标优化差分进化算法

2021 IEEE 7th International Conference on Cloud Computing and Intelligent Systems (CCIS) Pub Date : 2021-11-07 DOI: 10.1109/CCIS53392.2021.9754666

Tianqi Huang, Weifeng Gao, Hong Li, J. Xie

引用次数: 0

MLP-Pose: Human Pose Estimation by MLP-Mixer MLP-Pose:基于MLP-Mixer的人体姿态估计

2021 IEEE 7th International Conference on Cloud Computing and Intelligent Systems (CCIS) Pub Date : 2021-11-07 DOI: 10.1109/CCIS53392.2021.9754658

Songkai Xiong, Zhaowei Qu, Yiran Wang, Xiaoru Wang, Han Xia

引用次数: 2

Network Embedding Based Collaborative Filtering Model Equipped With User Purchase Motivation and Potential Interactions 考虑用户购买动机和潜在交互的网络嵌入协同过滤模型

2021 IEEE 7th International Conference on Cloud Computing and Intelligent Systems (CCIS) Pub Date : 2021-11-07 DOI: 10.1109/CCIS53392.2021.9754616

Shuo Wang, Hui Zhou, Mingxin Li, C. Li, Zhongying Zhao

引用次数: 0

Quadrilateral Surface Mesh Generation Algorithm for CFD Model Based on Area-Preserving Parameterization 基于保面积参数化的CFD模型四边形曲面网格生成算法

2021 IEEE 7th International Conference on Cloud Computing and Intelligent Systems (CCIS) Pub Date : 2021-11-07 DOI: 10.1109/CCIS53392.2021.9754613

Peng-yu Wang, Haisheng Li, Xiaoqun Wu, Nan Li

引用次数: 0

Graph Convolutional Neural Network with Inter-layer Cascade Based on Attention Mechanism 基于注意机制的层间级联图卷积神经网络

2021 IEEE 7th International Conference on Cloud Computing and Intelligent Systems (CCIS) Pub Date : 2021-11-07 DOI: 10.1109/CCIS53392.2021.9754620

Lu Wei, Yiting Liu, Kaiyuan Feng, Jianzhao Li, Kai Sheng, Yue Wu

{"title":"Graph Convolutional Neural Network with Inter-layer Cascade Based on Attention Mechanism","authors":"Lu Wei, Yiting Liu, Kaiyuan Feng, Jianzhao Li, Kai Sheng, Yue Wu","doi":"10.1109/CCIS53392.2021.9754620","DOIUrl":"https://doi.org/10.1109/CCIS53392.2021.9754620","url":null,"abstract":"In recent years, graph data in the non-Euclidean space has been widely used, and the methods and techniques for learning graph data in many deep learning fields have been continuously developed, such as the Graph neural network (GNN). The structural characteristics of graph data, the aggregation mode and representation mode of node information, and the node neighbor information are the core issues of GNN. However, most of the existing graph convolutional neural networks have an excessive smoothing problem, which limits the learning ability of the model. Aiming at the over-smoothing problem of the current algorithm, this paper enhances the learning of graph data by improving the expression ability of local information and global features. This paper constructs a cascade structure between graph convolutional layers. This kind of network structure realizes the dense connection of convolutional layers, makes the local feature information is effectively used, and further enhances the graph representation ability. Introduce self-attention and TopK into the Readout module, selectively aggregate and express feature information, and use graph-level information more efficiently. Graph classification is a downstream task to verify the performance of the proposed model. Experimental results prove that this densely structured graph convolutional network can effectively aggregate local node information and global graph-level information.","PeriodicalId":191226,"journal":{"name":"2021 IEEE 7th International Conference on Cloud Computing and Intelligent Systems (CCIS)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123975581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1