检索结果-内蒙古大学图书馆

2024 International Conference on Image processing and Artificial Intelligence, ICIPAl 2024

作者： Li, Wen Jia, Zhenhong Huang, Xiaohui Wang, Jiajia Zhou, Gang Shi, Fei School of Computer Science and Technology Urumqi830046 China Key Laboratory of Signal Detection and Processing Xinjiang Uygur Autonomous Region Xinjiang University Urumqi830046 China

ISBN: (纸本)9781510681514

Addressing the problem of poor visual effect and noise interference in foggy video images collected by hawk-eye image sensors, we suggest an approach which utilizes difference images (DIs) fusion and two-stage clustering for detecting changes in monitoring video pictures. First, we utilize a dehazing algorithm based on the color attenuation prior theory to effectively eliminate the haze interference. Then, two DIs are generated using the compressed logarithmic ratio and maximum mean pixel ratio operators. Fusion of two DIs using multi-scale Laplace pyramid and regional energy algorithms, and filtered using the adaptive median filtering algorithm to obtain the final DIs. Finally, the soft threshold function and the FCM clustering algorithm are used to perform two-stage clustering on the DI to obtain the change detection result. Experimental results demonstrate that this approach can effectively and accurately detect subtle changes in hawk-eye surveillance video images under foggy conditions. © 2024 SPIE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Multi-speaker Emotional Speech Synthesis Based on Self-Supervised Speech Representations 5

Multi-speaker Emotional Speech Synthesis Based on Self-Super...

引用

5th IEEE International Conference on Pattern Recognition and Machine Learning, PRML 2024

作者： Yin, Mingming Huang, Zhihua Lu, Kexin Zhou, Haiyang School of Computer Science and Technology Xinjiang University Urumqi China School of Computer Science and Technology Xinjiang University Key Laboratory of Signal Detection and Processing Urumqi China

ISBN: (纸本)9798350355925

In recent years, emotional speech synthesis has shown considerable progress. However, some existing emotional speech synthesis methods only model emotion from a single scale, resulting in only global or average emotional expression, unable to synthesize significant emotional speech. In this paper, we propose a multi-scale multi-speaker emotional speech synthesis method based on self-supervised speech model HuBERT. Firstly, the emotion information is extracted from the feature extractor HuBERT. Secondly, the extracted emotion information is modeled by coarse-grained emotion modeling and fine-grained emotion modeling respectively to obtain utterance-level emotion embedding and phoneme-level emotion embedding. Through subjective and objective evaluation, we verify that the method is significantly better than the comparison model in terms of speech quality and emotional expression. © 2024 IEEE.

关键词： emotional speech synthesis self-supervised speech representation speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Prosody Prediction with Discriminative Representation Method 3

Prosody Prediction with Discriminative Representation Method

引用

3rd International Conference on Pattern Recognition and Machine Learning, PRML 2022

作者： Zhang, Jipeng Yilahun, Hankiz Feng, Xiaoqin Chen, Yunlin Yang, Xipeng Hamdulla, Askar School of Information Science and Engineering Xinjiang University of China China Xinjiang Key Laboratory of Signal Detection and Processing China Xinjiang Key Laboratory of Multilingual Information Technology China Mobvoi Ai Lab Suzhou China

ISBN: (数字)9781665499507

ISBN: (纸本)9781665499507

Rhythm affects the naturalness and intelligibility of Text-To-Speech (TTS). However, rhythm prediction remains a great challenge, usually in two aspects: 1) the united annotation is a relatively difficult task, which depends on expert's experience. 2) traditional methods based on conditional random field (CRF), which heavily rely on feature engineering, such as word segmentation, part of speech(pos) etc. For above problems, we propose a method to reduce the dependency for united annotation data and conduct the joint experiment which use one unified model on independent data. Meanwhile, we also propose an algorithm of Layer Look Up Table (LLUT): use an embedding layer to learn a discriminative representation for different level of prosody data without any feature engineering. By using this method, the classifier can share the parameters and predict for different prosody level separately, which reduces the number of trainable model parameters. In order to better represent the input text, we use the pre-training model, like BERT, to provide the semantic information. Our experiment shows that the method of LLUT, is better able to acquire the discriminative meaning of different prosody levels. And also, our algorithm is proved to be general for sequence annotation tasks thus we can do extra task, like polyphone-prosody prediction. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Recognition of Group Activities Using Complex Wavelet Domain Based Cayley-Klein Metric Learning

引用

Journal of Beijing Institute of Technology 2018年第4期27卷 592-603页

作者： Gensheng Hu Min Li Dong Liang Mingzhu Wan Wenxia Bao Key Laboratory of Intelligent Computing and Signal Processing Ministry of EducationAnhui University Hefei 230039China School of Electronics and Information Engineering Anhui UniversityHefei 230601 China School of Information Science and Technology Fudan UniversityShanghai 200433China Anhui Key Laboratory of Polarization Imaging Detection Technology Hefei 230031China

A group activity recognition algorithm is proposed to improve the recognition accuracy in video surveillance by using complex wavelet domain based Cayley-Klein metric ***-sampled dual-tree complex wavelet packet transform(NS-DTCWPT)is used to decompose the human images in videos into multi-scale and *** improved local binary pattern(ILBP)and an inner-distance shape context(IDSC)combined with bag-of-words model is adopted to extract the decomposed high and low frequency coefficient *** extracted coefficient features of the training samples are used to optimize Cayley-Klein metric matrix by solving a nonlinear optimization *** group activities in videos are recognized by using the method of feature extraction and Cayley-Klein metric *** results on behave video set,group activity video set,and self-built video set show that the proposed algorithm has higher recognition accuracy than the existing algorithms.

关键词： video surveillance group activity recognition non-sampled dual-tree complex wavelet packet transform(NS-DTCWPT) Cayley-Klein metric learning

来源：评论

学校读者我要写书评

暂无评论

Digital image biological detection technology based on the porous silicon periodic crystals film

引用

Optoelectronics Letters 2021年第9期17卷 552-557页

作者： YANG Jianfeng JIA Zhenhong LüXiaoyi HUANG Xiaohui WANG Jiajia School of Physical Science and Technology Xinjiang UniversityUrumqi 830046China School of Information Science and Engineering Xinjiang UniversityUrumqi 830046China Key Laboratory of Signal Detection and Processing Xinjiang Uygur Autonomous RegionXinjiang UniversityUrumqi 830046China

In order to solve this problem,a new biological detection method is proposed,which makes use of the characteristics of optical transmission at the edge of the spectral band gap and sensitive to refractive index *** the probe light with wavelength at the edge of the Bragg band gap of porous silicon is incident on the surface of porous silicon,the change of refractive index caused by deoxyribonucleic acid(DNA)reaction in porous silicon will affect the detection light intensity transmitted from the porous silicon *** analyzing the change of the average gray value of the transmitted light image,the concentration of the DNA can be obtained.

关键词： porous image refractive

来源：评论

学校读者我要写书评

暂无评论

Target detection algorithm with wide field of view in foggy weather based on improved CSLBP operator 4

Target detection algorithm with wide field of view in foggy ...

引用

4th International Conference on Image processing and Intelligent Control, IPIC 2024

作者： Lian, Xiya Jia, Zhenhong Zhou, Gang Wang, Jiajia Song, Sensen Xiao, Xiaohui Shi, Fei College of Computer Science and Technology Xinjiang University Urumqi China Key Laboratory of Signal Detection and Processing Xinjiang Uygur Autonomous Region Xinjiang University Urumqi830046 China

ISBN: (纸本)9781510682313

In order to solve the problem of unclear foreground targets and false foregrounds after performing target detection tasks in foggy video images with wide fields of view, we propose an improved video target detection algorithm for the CSLBP operator to detect foreground targets in different scenes. The improved CSLBP operator is used to extract the texture features of the wide-field image, and the foreground target pixels are judged combined with background modeling. This method is not sensitive to changes in indoor lighting or outdoor sunlight, can effectively solve the shadow problem, and more completely extracts foreground moving targets. It also has obvious effects in bad weather such as foggy weather, and has good robustness. © 2024 SPIE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

BD-YOLO: Optimising Insect Imbalance Data detection Models

BD-YOLO: Optimising Insect Imbalance Data Detection Models

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Wang, Jian-Yi Jia, Zhen-Hong Zhou, Gang Wang, Jia-Jia School of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Uygur Autonomous Region Signal Detection and Processing Key Laboratory Xinjiang University Urumqi830046 China

ISBN: (纸本)9781665410205

Vision-based insect detection is an important task in smart agriculture. Field-collected insect image datasets usually show severe imbalances in categories. Previous models have insufficient accuracy as well as low real-time performance for detecting unbalanced data of insects. To address the issues described above, an improved framework Balance Detect YOLO(BD-YOLO) based on YOLOv8 is proposed in this paper. We innovatively designed Focaler-CPIoU loss to increase the weight of a few classes of samples to achieve the optimisation of pest imbalance data detection. We introduced lightweight convolutional MBConv to improve the recognition accuracy while reducing the number of model parameters. In order to verify the effectiveness of the method in this paper, we established an insect dataset containing six types of insects, in which the most numerous thrips is 431.5 times more than the least numerous chrysopaperla. The experimental results show that compared with YOLOv8, the mAP50 reaches 61.7% with a 73.1% reduction in the number of model parameters, an improvement of 5.4%, and an improvement of 769 in FPS. A feasible approach to optimise the detection of unbalanced number of insects is provided in this paper along with the ability to be deployed on lightweight hardware devices. © 2024 IEEE.

关键词： Invertebrates

来源：评论

学校读者我要写书评

暂无评论

Dynamic Word Vector Based Sentiment Analysis for Microblog Short Text 3

Dynamic Word Vector Based Sentiment Analysis for Microblog S...

引用

3rd International Conference on Pattern Recognition and Machine Learning, PRML 2022

作者： Peiliang, Zhang Ablimit, Mijit Yilahun, Hankiz Hamdulla, Askar Xinjiang University Xinjiang Key Laboratory of Signal Detection and Processing School of Information Science and Engineering Urumqi China Xinjiang University Xinjiang Key Laboratory of Multilingual Information Technology School of Information Science and Engineering Urumqi China

ISBN: (数字)9781665499507

ISBN: (纸本)9781665499507

Aiming at the disadvantage of static word vector model to the problem of polysemy of words, a model based on dynamic word vector and two-way GRU neural network combined with attention mechanism is proposed to recognize emotion of microblog short text comments, which is helpful to analyze and monitor social public opinions. First, the word vector is obtained through ERNIE pre-training model, and then transmitted to the bidirectional GRU neural network. Then, the keywords are weighted in combination with the Attention mechanism. Finally, the emotion is classified through the softmax layer. Experimental results show that the classification accuracy of the proposed model on the weibo_senti_100k data set is 96.51%. © 2022 IEEE.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Improving ECAPA-TDNN Performance with Coordinate Attention

引用

Journal of Shanghai Jiaotong University (Science) 2024年 1-7页

作者： Liu, Shuanghong Song, Zhida He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China Department of Electronic Engineering and Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

The current mainstream networks, such as squeeze and excitation residual neural network (SE-ResNet) and emphasized channel attention, propagation and aggregation based time delay neural network (ECAPA-TDNN), enhance the capability of speaker embedding extractors to extract more discriminative speaker embeddings by incorporating squeeze and excitation (SE) attention within the convolutional blocks. However, the SE attention focuses solely on encoding inter-channel information, overlooking the importance of spatial positional information and time-frequency information, which are crucial for the model’s performance. In this paper, we first experimentally compare the effectiveness of several mainstream attention mechanisms in the computer vision domain for the ECAPA-TDNN model. Next, we focus on the substantial improvements that coordinate attention (CA) brings to the ECAPA-TDNN model. The introduction of CA can help the model embed time-frequency information into the channel representation. Even without using AS-Norm, our proposed model achieves relative reductions of about 5.3% equal error rate (EER) and 5.5% minimum detection cost function (minDCF) on both the Voxceleb-O and Voxceleb-H test sets compared to the ECAPA-TDNN baseline model. In addition, the EER is relatively reduced by 9.46% on the CN-Celeb1 test set. This result strongly demonstrates that the CA module can effectively improve the generalization ability of the ECAPA-TDNN model. © Shanghai Jiao Tong University 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Model Based on Vision Task Level for Saliency Object detection in Foggy Conditions

Multi-Task Model Based on Vision Task Level for Saliency Obj...

引用

IEEE International Conference on Image processing

作者： Yusen Zhu Gang Zhou Jingxu Ren Jiakun Tian Zhenhong Jia Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi China

In recent years, saliency object detection methods based on convolutional neural networks have been widely studied, and have achieved excellent performance in clear images. However, due to the low visibility of images in foggy conditions, the existing saliency object detection methods will be seriously affected or even ineffective. To address this problem, we introduce an end-to-end multi-task learning network. We design two subetworks for depth estimation and image restoration as auxiliary tasks to improve saliency object detection in foggy conditions. According to different characteristics of vision tasks, different shared layers are assigned to improve the performance of saliency object detection. Experiments show that our method has been greatly improved on both synthetic foggy datasets and real-to-world foggy datasets, outperforming many state-to-the-art saliency object detection methods.

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：