检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

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

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

In crowded scenarios, face mask detection algorithms still suffer from the target misdetection and omission, and the difficulty of reconciling real time and effectiveness. To address these issues, we present an G-YOLOv5 face mask detection algorithm. First, we adopt a weighted bidirectional feature pyramid network as the feature fusion network to enhance multiscale feature fusion; second, we utilize the WIoU loss function to strengthen the impact of good anchor frames while weakening the detrimental impact of poor quality anchor frames. Finally, considering the real-time and effectiveness issues of detector, we designed the Ghostv2-C3 module instead of the C3 module of the backbone to improve the inference speed of the model. The results of the experiment demonstrates that compared with other detectors, our detector plays a positive role in solving the target misdetection and omission and balancing the real-time nature of the model.

关键词： Accuracy Neural networks Detectors Object detection Real-time systems Inference algorithms Security

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

Research on ground target vibration signal perception and feature recognition 4

Research on ground target vibration signal perception and fe...

引用

4th International Conference on signal Image processing and Communication, ICSIPC 2024

作者： Luo, Hongsheng Su, Jinshan Key Laboratory of Vibration Signal Capture and Intelligent Processing School of Electronic and Engineering Yili Normal University 448 Jiefang Road Xinjiang Yining835000 China

ISBN: (纸本)9781510682467

The perception of ground target vibration signals is the key to target recognition technology, targeting the vibration signals generated by ground target movements such as walking, jumping, and running of personnel. Firstly, experimental testing was conducted to establish a signal sample database that reflects the characteristic information of target attributes. Then, time-domain and frequency-domain analysis were performed on the characteristics of target vibration signals to achieve the recognition of targets in different motion states. The experiments showed that these two methods are simple, easy to implement, and have good recognition effects. © 2024 SPIE.

关键词： Vibration analysis

来源：评论

学校读者我要写书评

暂无评论

A Standardized-Based Knowledge Distillation Model for Multimodal Emotion Recognition in Conversation

SSRN

引用

SSRN 2024年

作者： Li, Yihao Tohti, Turdi Han, Dongfang Liang, Yi Zuo, Zicheng Liao, Yuanyuan Yang, Qingwen School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China

In recent years, with the rapid development of artificial intelligence and deep learning technology, Multimodal Emotion Recognition in Conversation (MERC) has gradually attracted widespread attention. However, existing methods rely on designed models to learn modal representations, there is a lack of research on enhancing modal representations. Therefore, we propose a method for standardized knowledge distillation. This method uses the intra-modal Transformer module for learning intra-modal representations, as well as employing the Cross-Modal Transformer module to effectively integrate different modalities. In addition, we further design a novel standardized knowledge distillation strategy, which uses the soft labels of the text modality as training supervision, thereby achieving the migration of semantic and contextual information from the text modality to the audio and visual modalities. This strategy fully borrows the idea of information sharing, allowing the audio and visual modalities to learn the fine-grained features and complex decision boundaries of the text modality. To demonstrate the effectiveness of our proposed model, we conduct extensive experiments on two public emotion recognition datasets: IEMOCAP and MELD. Experimental results further demonstrate the superiority of our method compared with the state-of-the-art methods. © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Target Speaker Extraction with Attention Enhancement and Gated Fusion Mechanism

Target Speaker Extraction with Attention Enhancement and Gat...

引用

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

作者： Wang Sijie Askar Hamdulla Mijit Ablimit School of Information Science and Engineering Xinjiang University Urumqi China Key Laboratory of Signal Detection and Processing Urumqi China

The objective of a target speaker extraction system is to extract the speech of the target speaker from a mixture of multiple speakers and noises using a certain amount of additional information of the target speaker. In this paper, we investigate the improvements of the baseline system by incorporating the light-weight CBAM module in the target extractor, and the gated fusion module (GFM) in the fusion layer. The CBAM introduces attention enhancement to baseline model with no significant increase in the number of parameters and complexity, and the previous concatenation-based fusion method used for speaker embedding and input mixture (or intermediate output) is replaced by GFM, enabling the model to better leverage the supplementary information provided by speaker embedding. Experimental results on datasets built from WSJ0-2mix and WHAM! demonstrate that both the CBAM module and the light-weight GFM module individually improve the model performance, and the GFM module shows better improvement on WHAM!. However, the combination of these two modules only exhibits mutually beneficial effects on the clean dataset WSJ0-2mix, while the performance of the combined module on the noisy dataset WHAM! is inferior to that of using the GFM module alone.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Understanding is a Growing Classification Method

SSRN

引用

SSRN 2023年

作者： Liang, Yi Tohti, Turdi Hamdulla, Askar School of Information Science and Engineering Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China

Although existing text classification methods have achieved SOTA results on most tasks, their generalization ability is inferior to their excellent performance on a single task. For this issue, existing research mainly improves the generalization of text classification models by adding label semantics to model training and allowing models to see label semantic information. However, its generalization ability is still limited by the description and quantity of labels. In this article, we use the method of comparative learning to make the model more focused on understanding text semantics during training. In this way, the text classification model is exempt from the limitations of labels. At the same time, due to the general semantic knowledge learned by the model, the model can be applied to tasks in most NLP fields. We verified the model's generalization ability on 17 different zero-shot tasks, verified the model's cross-domain generalization ability and growth potential on 3 question-answer and 2 reading comprehension tasks, and verified the model's performance on supervised tasks on 12 text categorization tasks. Experimental results show that using comparative learning to learn semantic knowledge frees text classification models from the limitations of classification labels and improves them in different dimensions: 1) robustness, 2) cross-domain generalization ability, and 3) growth potential. © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Joint Network Based on Interactive Attention for Speech Emotion Recognition

A Joint Network Based on Interactive Attention for Speech Em...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Ying Hu Shijing Hou Huamin Yang Hao Huang Liang He Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi China Department of Electronic Engineering Tsinghua University Beijing China

Speech emotion recognition (SER) has played a vital role in human-machine interaction. In this paper, we propose a separate spectrum-based SER model and a joint network combining pre-trained and spectrum-based models. In the joint network, we design an interactive attention module to effectively fuse the intermediate features from two models. Our proposed separate spectrum-based model is superior to four compared spectrum-based methods under the speaker-dependent setting. For the application in real scenarios, we compared our proposed joint network with six methods utilizing the pre-trained model under the speaker-independent setting. Experimental results show that our proposed joint network achieves the best performance among four unimodal models on the unweighted accuracy (UA) of 73.32 % and weighted accuracy (WA) of 72.48 %, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-TransPathoNet: A transfer learning-based neural network for pathology image classification with multi-Task learning 3

Multi-TransPathoNet: A transfer learning-based neural networ...

引用

3rd International Conference on Advanced Algorithms and signal Image processing, AASIP 2023

作者： Deng, Xin Li, Min Ren, Xiaojun Zheng, Xiuyan Liang, Fei He, Liang Zhu, Min School of Software Xinjiang University China School of Information Science and Engineering Xinjiang University China Xinjiang Key Laboratory of Clinical Genetic Testing and Biomedical Information China Xinjiang Clinical Research Center for Precision Medicine of Digestive System Tumor China Department of Pathology Karamay Central Hospital China Xinjiang Key Laboratory of Signal Detection and Processing China Dept. of Electron. Eng. and Beijing National Research Center for Information Science and Technology Tsinghua University China

ISBN: (纸本)9781510668522

Histopathological images are one of the common diagnostic tools used in the medical field. However, the complex cellular and tissue structures inside colorectal cancer histopathological images make it difficult for physicians to perform efficient cancer diagnosis and quantitative analysis. Therefore, this study proposed a multi-Task learning-based pathology image classification method Multi-TransPathoNet (A transfer learning-based neural network for pathology image classification with multi-Task learning, Multi-TransPathoNet) for detection and visualization output of colorectal cancer histopathology images, thus helping to improve medical efficiency. To verify the practical application value of this method, this study used the paracancerous, highly differentiated, and high-moderately differentiated histopathological images which are more difficult to distinguish in colorectal cancer as the dataset for classification test, and our method obtained 92% accuracy. Besides, we compared with the single-Task learning models Resnet50 and Vgg19 respectively, which also have good performance in image classification tasks, to comprehensively evaluate the proposed model's performance. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Multi-agricultural Machinery Collaborative Task Assignment Based on Improved Genetic Hybrid Optimization Algorithm

arXiv

引用

arXiv 2023年

作者： Du, Haohao Lai, Huicheng Gao, Guxue Wen, Xiaopeng Li, Yifei Wang, Haidong Zhang, Guo College of Information Science and Engineering Xinjiang University Urumqi 830017 China Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi 830017 China

Agricultural machinery collaboration technology is crucial in improving the efficiency of agricultural machinery utilisation and enhancing the benefits of large-scale production of machinery fleets. To address the challenges of delayed scheduling information, heavy reliance on manual labour, and low operational efficiency in traditional large-scale agricultural machinery operations, this study proposes a method for multi-agricultural machinery collaborative task assignment based on an improved genetic hybrid optimisation algorithm. The proposed method establishes a multi-agricultural machinery task allocation model by combining the path pre-planning of a simulated annealing algorithm and the static task allocation of a genetic algorithm. By sequentially fusing these two algorithms, their respective shortcomings can be overcome, and their advantages in global and local search can be utilised. Consequently, the search capability of the population is enhanced, leading to the discovery of more optimal solutions. Then, an adaptive crossover operator is constructed according to the task assignment model, considering the capacity, path cost, and time of agricultural machinery;two-segment coding and multi-population adaptive mutation are used to assign tasks to improve the diversity of the population and enhance the exploration ability of the population;and to improve the global optimisation ability of the hybrid algorithm, a 2-Opt local optimisation operator and an Circle modification algorithm are introduced. Finally, simulation experiments were conducted in MATLAB to evaluate the performance of the multi-agricultural machinery collaborative task assignment based on the improved genetic hybrid algorithm. The algorithm's capabilities were assessed through comparative analysis in the simulation trials. The results demonstrate that the developed hybrid algorithm can effectively reduce path costs, and the efficiency of the assignment outcomes surpasses that of the classical g

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Recommendation Algorithm with Co-embedded Item Attributes and Ratings

A Hybrid Recommendation Algorithm with Co-embedded Item Attr...

引用

International Conference on Applied Machine Learning (ICAML)

作者： Gaowei Xin Jiwei Qin Jiong Zheng School of Information Science and Engineering Xinjiang University Urumqi China Key Laboratory of Signal Detection and Processing Xinjiang Uygur Autonomous Region Xinjiang University Urumqi China

In today's recommendation algorithm field, attribute feature information of users or items is usually introduced as auxiliary information to alleviate the sparsity problem, which can achieve good recommendation results to some extent. To make better use of the auxiliary information for data compression and dimensionality reduction, autoencoder models are usually employed. However, existing autoencoder-based models require the same input and output dimensions, resulting in data information loss and poor autoencoder scalability, which ultimately leads to low recommendation line performance. To cope with this problem, we propose a hybrid collaborative recommendation algorithm with co-embedded item attributes and ratings (HCR-item). By one-hot encoding the discrete item attribute features and then fusing the rating features with the item attribute features as the input of the autoencoder, the autoencoder completes the data compression and reconstructs the rating interaction prediction matrix. The algorithm proposed in this paper integrates item attribute features and rating features together, flexibly uses different feature information, extends the feature space, and solves the problem of low recommendation performance caused by sparsity. The algorithm has been extensively experimented on several real datasets and compared with other algorithms, and the results show that HCR-item has better recommendation performance.

关键词： Dimensionality reduction Scalability Data compression Collaboration Predictive models Prediction algorithms Data models

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：