Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition最新文献_第3页

Visual Question Answering Model Based on CAM and GCN 基于CAM和GCN的可视化问答模型

Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2022-09-23 DOI: 10.1145/3573942.3574090

Ping Wen, Matthew Li, Zhang Zhen, Wang Ze

{"title":"Visual Question Answering Model Based on CAM and GCN","authors":"Ping Wen, Matthew Li, Zhang Zhen, Wang Ze","doi":"10.1145/3573942.3574090","DOIUrl":"https://doi.org/10.1145/3573942.3574090","url":null,"abstract":"Visual Question Answering (VQA) is a challenging problem that needs to combine concepts from computer vision and natural language processing. In recent years, researchers have proposed many methods for this typical multimodal problem. Most existing methods use a two-stream strategy, i.e., compute image and question features separately and fuse them using various techniques, rarely relying on higher-level image representations, to capture semantic and spatial relationships. Based on the above problems, a visual question answering model (CAM-GCN) based on Cooperative Attention Mechanism (CAM) and Graph Convolutional Network (GCN) is proposed. First, the graph learning module and the concept of graph convolution are combined to learn the problem-specific graph representation of the input image and capture the interactive image representation of the specific problem. Image region dependence, and finally, continue to optimize the fused features through feature enhancement. The test results on the VQA v2 dataset show that the CAM-GCN model achieves better classification results than the current representative models.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125790500","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: 0

Automatic Exposure Control of Line Structured Light Sensor Based on Fuzzy Logic 基于模糊逻辑的线结构光传感器自动曝光控制

Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2022-09-23 DOI: 10.1145/3573942.3574008

Y. Liu, Wangqian Sun

引用次数: 0

Improved Layered Minimum Sum Decoding Algorithm Based on Overestimation 基于过估计的改进分层最小和译码算法

Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2022-09-23 DOI: 10.1145/3573942.3573996

Liu Yu, Lin Bai, Yaohui Hao

引用次数: 0

Full-Rotation Quantum Convolutional Neural Network for Abnormal Intrusion Detection System 变态入侵检测系统的全旋转量子卷积神经网络

Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2022-09-23 DOI: 10.1145/3573942.3574105

Suya Chao, Guang Yang, Min Nie, Yuan-hua Liu, Meiling Zhang

{"title":"Full-Rotation Quantum Convolutional Neural Network for Abnormal Intrusion Detection System","authors":"Suya Chao, Guang Yang, Min Nie, Yuan-hua Liu, Meiling Zhang","doi":"10.1145/3573942.3574105","DOIUrl":"https://doi.org/10.1145/3573942.3574105","url":null,"abstract":"Intrusion detection system (IDS) is a significant mechanism to improve network security. As a promising technique, machine learning (ML) methods has been applied in IDS to obtain high classification accuracy. However, classical ML based IDS methods hit a bottleneck in computing performance in case of huge network traffic and complex high-dimensional data. Due to the parallelism, superposition, entanglement of quantum computing, quantum computing provides a new solution to speed up the classical ML algorithms. This paper proposes a novel IDS scheme based on full-rotation quantum convolutional neural network (FR-QCNN). The key component of the FR-QCNN is the quantum convolution filter, which is composed of coding layer, variational layer and measurement layer. Different from the traditional quantum convolutional neural network, a full-rotation quantum circuit is used in the variational layer of the FR-QCNN, realizing a complete parameter update in the model training. Experiment on dataset from KDD Cup shows that the IDS classification accuracy of FR-QCNN is higher than classical ML models such as convolutional neural network (CNN), decision tree (DT) and support vector machine (SVM), as well as higher than traditional quantum convolutional neural network(QCNN). Meanwhile, FR-QCNN and QCNN have lower space complexity and time complexity than classical ML methods.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130996369","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: 0

Performance Evaluation and Analysis of Deep Learning Frameworks 深度学习框架的性能评估与分析

Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2022-09-23 DOI: 10.1145/3573942.3573948

Xiaoyan Xie, Wanqi He, Yun Zhu, Hao Xu

引用次数: 2

Reduced-Dimension DOA Estimation Based on MUSIC Algorithm in L-Shaped Array 基于MUSIC算法的l形阵列降维方位估计

Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2022-09-23 DOI: 10.1145/3573942.3574113

Junliang Yang, Hu He, Shumin Wang

{"title":"Reduced-Dimension DOA Estimation Based on MUSIC Algorithm in L-Shaped Array","authors":"Junliang Yang, Hu He, Shumin Wang","doi":"10.1145/3573942.3574113","DOIUrl":"https://doi.org/10.1145/3573942.3574113","url":null,"abstract":"According to the heavy computation and high cost of two-dimensional (2D) multiple signal classification (MUSIC) to achieve 2D direction of arrival (DOA) estimation in various complex arrays, this paper proposes a reduced-dimensional (RD) estimation algorithm based on L-shaped uniform array without the need of 2D spectral peak search and secondary optimization. This algorithm makes full use of the structural characteristics of L-shaped array, decomposes the L-shaped uniform array into two uniform linear arrays, and estimates the angle between the source and the X-axis and Y-axis by one-dimensional (1D) search respectively, then obtains the 2D-DOA estimation according to the geometric relationship and uses the maximum likelihood method for angle matching. In this algorithm, the time-consuming 2D search is transformed into 1D search, which greatly reduces the computational complexity. In order to further reduce the complexity and improve the estimation accuracy, the root-finding method can be used instead of one-dimensional search. The simulation results show that the proposed algorithm has higher DOA estimation performance as well as faster operation speed.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130409590","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: 0

First Describe, Then Depict: Generating Covers for Music and Books via Extracting Keywords: This paper presents two methods to generate high resolution uncopyrighted book covers or music album covers. 先描述，再描述:通过提取关键词生成音乐和书籍封面:本文提出了两种生成高分辨率无版权图书封面或音乐专辑封面的方法。

Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2022-09-23 DOI: 10.1145/3573942.3574088

V. Efimova, V. Shalamov, A. Filchenkov

引用次数: 0

Container Anomaly Detection System Based on Improved-iForest and eBPF 基于改进ifforest和eBPF的容器异常检测系统

Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2022-09-23 DOI: 10.1145/3573942.3574110

Yuxuan Bai, Lijun Chen, Fan Zhang

引用次数: 0

Unsupervised Domain Adaptive Semantic Segmentation Based on Improved DAFormer 基于改进DAFormer的无监督域自适应语义分割

Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2022-09-23 DOI: 10.1145/3573942.3574046

Hao Liu, Jingchun Piao

引用次数: 1

A Bounded Model Checking Method for Concurrent Systems in xUML4MC xUML4MC中并发系统的有界模型检验方法

Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition Pub Date : 2022-09-23 DOI: 10.1145/3573942.3574016

Xinfeng Shu, Zewei Yang

引用次数: 0