检索结果-内蒙古大学图书馆

Proceedings of the 2023 12th International Conference on Computing and Pattern Recognition

作者： Xiangqian Zhao Xuebin Xu Reyihanguli Kasenmu Xinjiang University China Xinjiang Key Laboratory of Signal Detection and Processing(Xinjiang University) Xinjiang University China Xinjiang Teachers college China

ISBN: (纸本)9798400707988

In the process of printed document image retrieval, the traditional algorithm, SURF algorithm combined with violent matching, has the problems of low retrieval accuracy and low retrieval efficiency. This paper proposes a FAST + PCA-SURF combined with KNN algorithm based on FLANN for multilingual document image retrieval. Based on FAST, the feature points are detected, and the feature descriptors after dimensionality reduction are extracted by ***, the KNN algorithm based on FLANN is used for feature matching, and finally the appropriate matching results are output. The experimental results show that the proposed algorithm is improved in terms of time complexity and retrieval accuracy compared with the traditional algorithm. The average time complexity and retrieval accuracy of the traditional algorithm are 0.1783 s and 71.8%, respectively, while the proposed algorithm is 0.0464 s and 77.8%, indicating that the proposed algorithm achieves better experimental results in multilingual document image retrieval.

关键词： FAST FLANN matching PCA-SURF Printed multilingual document images keyword search.

来源：评论

学校读者我要写书评

暂无评论

Obstacle detection in Off-road Environments Based on LiDAR

Obstacle Detection in Off-road Environments Based on LiDAR

引用

Pattern Recognition and Machine Learning (PRML), IEEE International Conference on

作者： Arzigul Ahat Eksan Firkat Tayir Mijit Askar Hamdulla School of Information Science and Engineering Xinjiang University of China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China

Mapping off-road terrain is a challenging task, especially when compared to urban terrain. The complexity and roughness of off-road terrain make it difficult to achieve accurate mapping results. Obstacle detection in such environments is also a challenging task, as the performance of LiDAR-based methods depends on the point cloud density at the location of the obstacle. High line beam LiDAR is expensive, while low line beam LiDAR is sparse, making it difficult to obtain dense point clouds. In this paper, we propose a multi-LiDAR fusion approach that uses roof LiDAR as the primary sensor and front LiDAR as a supplement. The approach employs point cloud filtering, dedistortion, and point cloud registration to fuse data from multiple sensors. This results in a richer view of the environment and more intensive measurement data. We combine the voxel map with a twodimensional grid map and accelerate the voxel map using a GPU to generate accurate maps. Experimental results show that our proposed method achieves the highest accuracy and recall rates, improving the accuracy and robustness of obstacle detection in off-road environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MSFSAN: A Novel Multi-Scale Spatio-Temporal Feature Screening Attention Network for Urban Carbon Emission Prediction

MSFSAN: A Novel Multi-Scale Spatio-Temporal Feature Screenin...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Ben Wang Xizhong Qin Jiwei Qin Xiaoyu Zhang Haodong Ma Xinjiang Key Laboratory of Signal Detection and Processing College of Computer Science and Technology Xinjiang University Ürümqi China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

In order to cope with the increasingly severe global energy conservation and emission reduction problems, research on urban carbon emission prediction is of great significance. The existing methods mainly use time series analysis to predict urban carbon emission, but there is a strong spatial correlation between the carbon emission data of several cities. Therefore, this paper designs a multi-scale spatial-temporal feature screening attention network to predict target cities' future carbon emission data. Firstly, this paper combines the daily carbon emission data of the near-neighbouring cities and the daily homologous emission data of the target city to analyze the urban carbon emission data from a spatio-temporal perspective. Then, this paper designs a multi-scale spatial interactive convolution module and a multi-scale temporal convolution module to extract multi-scale spatio-temporal features effectively. In addition, the feature screening module is designed to reduce the adverse effects of redundant features. Finally, the multi-scale features are used to predict the future carbon emissions of the target city through a predictor. The experimental results show that our prediction model is superior to the existing methods in six datasets.

关键词： Correlation Convolution Urban areas Time series analysis Energy conservation Carbon dioxide Predictive models Feature extraction Cybernetics

来源：评论

学校读者我要写书评

暂无评论

LE-CAM++: A Lighter and More Efficient CAM++ for Speaker Verification 14

LE-CAM++: A Lighter and More Efficient CAM++ for Speaker Ver...

引用

14th International Symposium on Chinese Spoken Language processing, ISCSLP 2024

作者： Liu, Shuanghong Song, Zhida Fang, Zhihua He, Liang School of Computer Science and Technology Xinjiang University Urumqi China School of Intelligence Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9798331516826

Due to its superior performance and fewer parameters, CAM++ has become the state-of-the-art model for speaker verification tasks. This model uses 2D convolutional blocks to extract front-end features, which are then fed into a densely connected time-delay neural network backbone to extract deep features. However, the simple stacking of 2D convolutions may lead to the generation of a significant amount of redundant features, which is detrimental to efficient feature extraction. Furthermore, although CAM++ already has a relatively small number of parameters, there is still room for further optimization. To address these issues, this paper first employs depthwise separable convolutions to replace the dilated convolutions in the backend network of CAM++, making the model more lightweight. Next, we introduce spatial and channel reconstruction convolution (SCConv) in the ResBlock module of CAM++ to reduce redundant features and optimize the feature extraction process. Finally, after SCConv, we apply squeeze and excitation attention mechanism to model the interdependencies between channels and recalibrate each channel, further enhancing the model’s representational capacity. We name the resulting model LE-CAM++. Our proposed model achieves an EER of 0.686 and a minDCF of 0.084 on the VoxCeleb1-O dataset. Compared to the baseline model CAM++, the EER is reduced by 11%, and the minDCF is reduced by 28%. Additionally, the model parameters are reduced by 8%. ©2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Relational Classification Model Fusing Entity and Sentence Semantic Information

Enhancing Relational Classification Model Fusing Entity and ...

引用

Pattern Recognition and Machine Learning (PRML), IEEE International Conference on

作者： Chunji Wei Xizhong Qin Taiping Yuan School of Information Science and Engineering Xinjiang University of China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China

Relationship classification aims at mining the relationship between two entities in a sentence and is an essential basis for the information extraction task. However, traditional relationship classification methods, which only use the information of words in a sequence to predict the relationship between entities, cannot use the semantic information of entities and sentences for relationship classification. To solve these problems, this paper proposes a new model, ES-BERT: this model uses the word-to-word association in the BERT model to obtain the semantic information of entities by the positional encoding of entity pairs in a sentence. In addition, we use the rich semantic knowledge in the internal hidden layer of Bert to obtain the semantic information of the sentence, which can better help the model understand the sentence. Finally, the semantic information of entities and the semantic information of sentences in the hidden layer of BERT are fused, and the fused information is used for relationship classification. The experimental results show that the model proposed in this paper achieves an excellent F1 value of 88.87% on the SemEva1-2010 Task 8 dataset, which is better than other Bert-based Sota models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MUNet++: Multilevel wavelet nested UNet++ demoiréing residual network

引用

Displays 2024年 83卷

作者： Gao, Guxue Lai, Huicheng Jia, Zhenhong The College of Computer Science and Technology Xinjiang University Urumqi830017 China Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi830017 China

When mobile phones and digital cameras are used to capture information on a screen or store scenes with rich textures, an unpleasant moiré phenomenon occurs, which seriously degrades the quality of the image and affects subsequent image processing tasks. Therefore, to remove the moiré patterns, we propose a multilevel wavelet nested UNet++ demoiréing residual network called MUNet++. Unlike these methods based on the RGB domain, our method is performed in the frequency domain. The multilevel discrete wavelet transform (DWT) and the inverse discrete wavelet transform (IDWT) are elegantly embedded into the UNet++ encoder-decoder structure and transformed to the multilevel frequency domain, which captures more moiré features and preserves details of the image. In addition, we design a dual branch efficient pixel fusion attention module (DBEPFAM) that combines multiscale information, channel attention and the proposed pixel attention fusion module (PAFM) to improve the representation of features. In the network layer, a simple nonlinear unit (NU) is designed and embedded in the middle of the network layer to improve the representation capability of the network. Experimental results on two public datasets show that MUNet++ can effectively remove the moiré patterns and outperform existing state-of-the-art techniques. © 2024

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Joint Image Restoration For Domain Adaptive Object detection In Foggy Weather Condition

Joint Image Restoration For Domain Adaptive Object Detection...

引用

IEEE International Conference on Image processing

作者： Jing Ma Meng Lin Gang Zhou Zhenhong Jia School of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Driven by deep learning, object detection methods have made significant progress in recent years. However, there is still a domain shift between synthetic foggy data and real foggy data, this leads to a undesirable decrease in detection results when applying the algorithm model trained on synthetic foggy datasets. In this article, we design a domain-adaptive YOLOX object detection algorithm by joint image restoration, in order to improve object detection performance in foggy scenes. Specially, we design an end-to-end domain adaptive framework that combines dehazing module and YOLOX together. To achieve feature alignment, we introduced a domain classifier in the feature spaceand discuss its optimal placement in the framework. Experimental results show that the proposed domain adaptation method achieved 62.60 percent mAP on real foggy image datasets RTTs, outperforming other state-of-the-art methods.

关键词： Deep learning Adaptation models Object detection Feature extraction Data models Image restoration Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Attention-based Dual-Branch Network for Micro-Expression Recognition with Global-Local Feature Fusion

Attention-based Dual-Branch Network for Micro-Expression Rec...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Yupeng Qi Mayire Ibrayim Askar Hamdulla School of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China

ISBN: (数字)9798350364132

ISBN: (纸本)9798350364149

Micro-expression(ME) is an uncontrollable muscle movement that appears on the face when people try to hide or inhibit their real emotions, which has the problems of short duration, small movement amplitude and uneven distribution. In order to solve the problem of localization and asymmetry in the distribution of ME features, this paper proposes a new two-branch attention network to recognize MEs, which utilizes the attention mechanism to capture global and local ME features. The network is mainly divided into three parts: data preprocessing, ME feature learning and feature fusion classification. First, the data preprocessing first extracts the ME optical flow features and then divides them into four regions, which are used as inputs to the two-branch network respectively. Second, the two-branch network uses the Inception-MSFE global multi-scale feature extraction network incorporating the attention mechanism (CBAM) and the Swin Transformer-based local feature extraction network for feature learning, respectively. Finally, MEs are predicted by fusing global and local features of MEs. Experimental validation is carried out on three datasets, CASME II, SAMM, and SMIC, which proves that Acc, UAR, and UF1 are 0.797, 0.702, and 0.698 on the SAMM dataset, respectively; Acc, UAR, and UF1 are 0.734, 0.723, and 0.729 on SMIC, respectively; and on the CASME II dataset, Acc, UAR and UF1 are 0.865, 0.872, and 0.889, respectively, which are competitive with other state-of-the-art methods.

关键词： Representation learning Attention mechanisms Computational modeling Data preprocessing Training data Feature extraction Generative adversarial networks Transformers Data mining Optical flow

来源：评论

学校读者我要写书评

暂无评论

Multi-branch Network with Cross-Domain Feature Fusion for Anomalous Sound detection 1

引用

18th National Conference on Man-Machine Speech Communication, NCMMSC 2023

作者： Fang, Wenjie Fan, Xin Hu, Ying School of Computer Science and Technology Xinjiang University Urumqi China Key Laboratory of signal detection and processing in Xinjiang Urumqi China

ISBN: (数字)9789819706013

ISBN: (纸本)9789819706006

Anomalous sound detection (ASD) is a key technology to identify abnormal sounds in various industries. Self-supervised anomalous sound detection aims at detecting unknown machine anomalous sounds by learning the characteristics of the normal sounds using metainformation. In this paper, we propose a multi-branch network with cross-domain feature fusion (MBN-CFF) for self-supervised ASD task. The multi-branch network splits the complete feature representations and feeds them individually into classifiers to generate category predictions. The weighted loss, calculated by multiple predictions and the real labels, guides the model training process. We also design a cross-domain feature fusion (CFF) block for effectively fusing the time-domain and frequency-domain features and an attentive sandglass (AS) block for effectively extracting features. Experimental results on the DCASE2020 challenge task 2 show that our MBN-CFF network achieves the best performance with the AUC score of 94.73% and pAUC score of 88.74%, respectively, compared to the other five existing methods for anomalous sound detection. The results of ablation experiments show the effectiveness of CFF and AS blocks, multi-brach prediction (MBP). © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

WavLM and Omni-Scale CNNs: Enhancing Boundary detection in Partially Spoofed Audio

WavLM and Omni-Scale CNNs: Enhancing Boundary Detection in P...

引用

Asia-Pacific signal and Information processing Association Annual Summit and Conference (APSIPA)

作者： Menghan Li Zhihua Huang School of Computer Science and Technology Xinjiang University Urumqi China Key Laboratory of Signal Detection and Processing in Xinjiang Urumqi China

ISBN: (数字)9798350367331

ISBN: (纸本)9798350367348

Partially spoofed/fake audio, in which segments of utterances are replaced with synthetic or natural audio clips, has emerged as a new form of deep audio forgery, posing potential severe threats to societal security. To address this issue, we employ a deep learning-based frame-level detection system, introducing a frame-level detection approach. We explore the effectiveness of WavLM in waveform boundary detection, utilizing WavLM as a feature extractor for original audio samples. Acoustic features and frame-level embeddings are concatenated, with an OS block embedded within the frame-level feature extraction process, in conjunction with CNN-1D to form the ResNet-OS network. This system can detect partially deceived audio and pinpoint the manipulated segments, effectively integrating multi-scale convolution to consider the interplay between local and global information in time series classification tasks. Experimental results show that this approach offers substantial generalization capabilities and robustness compared to traditional frame-level detection techniques.

关键词： Convolution Time series analysis Asia Information processing Feature extraction Acoustics Robustness Forgery Security

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：