检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

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

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

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.

关键词： YOLO Smart agriculture Accuracy Insects Data models Real-time systems Hardware Optimization Monitoring Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Design and Application of Pocket Experiment System Based on STM32F4 2020

Design and Application of Pocket Experiment System Based on ...

引用

2020 The 8th International Conference on Information Technology: IoT and Smart City

作者： YANYUN ZHOU FEI SHI JUAN CHEN School of information science and engineering Xinjiang University and Key Laboratory of Signal Detection and Processing China School of information science and engineering Xinjiang University China

ISBN: (纸本)9781450388559

Aiming at the disadvantages of embedded system in practical teaching, a pocket experiment system based on STM32F4 is developed. The system includes input unit, output unit, logic control unit, power supply unit, peripheral unit and data transmission unit. It has the characteristics of rich resources, low cost, and easy to carry, which meets the needs of students' mobility experiments and extra-curricular innovation practice training. Practical application shows that the system not only stimulates students' enthusiasm for learning, but also trains their creative ability and practical application ability.

关键词： teaching reform pocket experiment system innovation practice

来源：评论

学校读者我要写书评

暂无评论

Residualpath-res-dense-net for retinal vessel segmentation 2

Residualpath-res-dense-net for retinal vessel segmentation

引用

2nd International Conference on Computer Vision, Image, and Deep Learning

作者： Huang, Xiaoming He, Fuyun Tang, Xiaohu Wang, Xun Qiu, Senhui Hu, Cong College of Electronic Engineering Guangxi Normal University Guilin541004 China Guangxi Key Laboratory of Automatic Detection Technology and Instrument Guilin541004 China Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing Guilin541004 China

ISBN: (数字)9781510646827

ISBN: (纸本)9781510646810

Retinal blood vessels segmentation acts as an important part to the treatment of ocular disease. Lately, automatic segmentation based on deep learning can solves problems of low efficiency and strong subjectivity of manual segmentation, and attracts the attention of researchers. In this paper, a novel segmentation model called Residualpath-Res-Dense Net (RRD-Net) is proposed to achieve vessel segmentation. In RRD-Net, Res-block and Dense-block are used to help speeding up the convergence of the network and learning more intrinsic features. In addition, the introduction of Residual Path can cut down the semantic difference between the connected feature and eliminate the potential impact of semantic difference on segmentation accuracy. We apply benchmark datasets DRIVE and CHASE_DB1 to evaluate effectiveness of the proposed network. Accuracy, sensitivity and F1 score demonstrate the effectiveness of RRD-Net. © 2021 SPIE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Inter- and Intra-sentence Interaction Network for Multi-choice Reading Comprehension

Inter- and Intra-sentence Interaction Network for Multi-choi...

引用

Virtual Reality, Human-Computer Interaction and Artificial Intelligence (VRHCIAI), International Conference on

作者： Xiaobo Xu Turdi Tohti Askar Hamdulla Xinjiang Key Laboratory of Signal Detection and Processing School of Information Science and Engineering Xinjiang University Urumqi China Xinjiang Key Laboratory of Multilingual Information Technology School of Information Science and Engineering Xinjiang University Urumqi China

Multiple choice reading comprehension is a challenging task in natural language processing, which aims to select the correct answer from a set of candidate options when given a passage and a question. When modeling the relationship between passages and questions, previous approaches usually focus only on the features between passages and questions and ignore the changes in the information within the passages after the interaction between passages and questions. For example, grammatical features and phrase structure can change. In this work, we propose a Inter- and Intra-sentence Interaction Network, which first performs passage-question and passage-option inter-sentence interactions, focusing on the features among passage, question and option sentences. Then the passages obtained from the inter-sentence interactions are subjected to intra-sentence interactions through an attention mechanism, focusing on the information inside the passages. Finally, the vector representation of question-aware passage and the vector representation of option-aware passage are fused by the gating mechanism to dynamically select the vector of passages containing the answers to the questions. The experimental results show that excellent results are achieved on both RACE and MCTest datasets, confirming that intra-sentence interaction can effectively improve the model's performance.

关键词： Human computer interaction Solid modeling Focusing Virtual reality Natural language processing Task analysis Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Introducing Multilingual Phonetic Information to Speaker Embedding for Speaker Verification

Introducing Multilingual Phonetic Information to Speaker Emb...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Zhida Song Liang He Penghao Wang Ying Hu Hao Huang School of Computer Science and Technology Xinjiang University China Xinjiang Key Laboratory of Signal Detection and Processing China Department of Electronic Engineering Tsinghua University China

Incorporating frame-level phonetic information during the extraction of speaker embeddings has been shown to enhance the performance of speaker verification systems. However, previous studies have primarily relied on phonetic information obtained from pre-trained models of monolingual automatic speech recognition (ASR). Considering that speaker verification datasets typically consist of multiple languages, there are instances where speakers are proficient in multiple languages, resulting in discrepancies between the languages used in the enrolled and test utterances. To address these challenges, we employ a pre-trained multilingual ASR Conformer encoder to initialize the MFA-Conformer network for speaker verification. Experimental results on the VoxCeleb dataset demonstrate a significant improvement in the performance of the system that incorporates multilingual phonetic information across different evaluation sets, including VoxCeleb1-O, E, and H, as well as the VoxSRC21 validation set, which focuses on multilingual verification. The source code is released at https://***/zds-potato/multilingual-phonetic-sv.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Multimodal Sentiment Analysis via CBAM Attention and Double-layer BiLSTM Architecture

arXiv

引用

arXiv 2023年

作者： Wang, Huiru Li, Xiuhong Ren, Zenyu Yang, Dan Ma, Chunming Xinjiang Key Laboratory of Signal Detection and Processing College of Information Science and Engineering Xinjiang University Urumqi China Xinjiang Multilingual Information Technology Laboratory College of Information Science and Engineering Xinjiang University Urumqi China

Because multimodal data contains more modal information, multimodal sentiment analysis has become a recent research hotspot. However, redundant information is easily involved in feature fusion after feature extraction, which has a certain impact on the feature representation after fusion. Therefore, in this papaer, we propose a new multimodal sentiment analysis model. In our model, we use BERT + BiLSTM as new feature extractor to capture the long-distance dependencies in sentences and consider the position information of input sequences to obtain richer text features. To remove redundant information and make the network pay more attention to the correlation between image and text features, CNN and CBAM attention are added after splicing text features and picture features, to improve the feature representation ability. On the MVSA-single dataset and HFM dataset, compared with the baseline model, the ACC of our model is improved by 1.78% and 1.91%, and the F1 value is enhanced by 3.09% and 2.0%, respectively. The experimental results show that our model achieves a sound effect, similar to the advanced model. Copyright © 2023, The Authors. All rights reserved.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Alignment for End-to-End Spoken Language Understanding Based on Momentum Contrastive Learning

Cross-Modal Alignment for End-to-End Spoken Language Underst...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Beida Zheng Mijit Ablimit Askar Hamdulla School of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China School of Future Technology Xinjiang University Urumqi China

The end-to-end spoken language understanding system extracts the semantic intent directly from an input speech. It effectively avoids problems such as semantic drift in traditional cascade models. However, the lack of semantically labeled speech data makes the model training process diffi-cult. Several recent multi-modal research perspectives have demonstrated that aligning speech and text embeddings based on space distance can improve the model’s performance. In this study, inspired by the work related to contrastive learning, a speech and text aligning method using momentum contrast learning is proposed, and a momentum distillation method is also used in the model to learn from imperfectly matched speech and text data. The proposed method has improved intent detection accuracy by 2.14% and 5.98% on Fluent Speech Command and SmartLights datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Graph Isomorphism Network with Weighted Multiple Aggregators for Speech Emotion Recognition

arXiv

引用

arXiv 2022年

作者： Hu, Ying Tang, Yuwu Huang, Hao He, Liang Key Laboratory of Signal Detection and Processing in Xinjiang China School of Information Science and Engineering Xinjiang University Urumqi China Department of Electronic Engineering Tsinghua University China

Speech emotion recognition (SER) is an essential part of human-computer interaction. In this paper, we propose an SER network based on a Graph Isomorphism Network with Weighted Multiple Aggregators (WMA-GIN), which can effectively handle the problem of information confusion when neighbour nodes' features are aggregated together in GIN structure. Moreover, a Full-Adjacent (FA) layer is adopted for alleviating the over-squashing problem, which is existed in all Graph Neural Network (GNN) structures, including GIN. Furthermore, a multi-phase attention mechanism and multi-loss training strategy are employed to avoid missing the useful emotional information in the stacked WMA-GIN layers. We evaluated the performance of our proposed WMA-GIN on the popular IEMOCAP dataset. The experimental results show that WMA-GIN outperforms other GNN-based methods and is comparable to some advanced non-graph-based methods by achieving 72.48% of weighted accuracy (WA) and 67.72% of unweighted accuracy (UA). Copyright © 2022, The Authors. All rights reserved.

关键词： Graphic methods

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

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

引用

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

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

ISBN: (数字)9798350355925

ISBN: (纸本)9798350355932

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.

关键词： Speech recognition Machine learning Feature extraction Speech synthesis Data mining

来源：评论

学校读者我要写书评

暂无评论

Dbswin: Transformer Based Dual Branch Network for Single Image Deraining

SSRN

引用

SSRN 2021年

作者： Tan, Fuxiang Qian, Yurong Kong, Yuting Zhang, Hao Zhou, Daxin Chen, Long Fan, Yinyin Xiao, Zhengqing College of Software Xinjiang University Urumqi830046 China Key Laboratory of Software Engineering Xinjiang University Urumqi830046 China Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region Urumqi830046 China

Rain streaks severely affect the perception of the content and structure of an image sohigh-performance deraining algorithms are needed in order to eliminate the effects ofvarious rain streaks for high-level computer vision tasks. Although much progress hasbeen made with existing deraining methods, the task of single image deraining remainschallenging. In this paper, we first point out that existing Transformers lack sufficientability to capture channel attention which restricted the ability of models in *** improve the performance of deraining model, we propose a dual branch derainingnetwork based on Transformer. One branch uses dense connections to connect Transformermodules which embed the attention of a composite channel. This branch captureschannel attention more finely to learn the representation of rain streaks *** other branch first obtains features at different scales by gradually expanding thereceptive field, then uses these features to obtain attention for regional features, and finallyuses the attention to guide the model to focus on areas of high rain streaks densityand large scales. By fusing these two branches, the model is able to capture channel attentionmore finely and to focus on regions of high rain streaks density and large *** extensive experimental results on synthetic and real datasets demonstrate that theproposed method outperforms most advanced deraining methods. © 2021, The Authors. All rights reserved.

关键词： Rain

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：