检索结果-内蒙古大学图书馆

Artificial Intelligence, Human-Computer Interaction and Robotics (AIHCIR), International Conference on

作者： Yefei Qian Mayire Ibrayim Askar Hamdulla Chunhu Zhang Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China School of Computer Science and Technology Xinjiang University Xinjiang China

Although scene text recognition (STR) methods have made great progress, reading the text of irregularly shaped scenes remains a challenge. The current conversion of two-dimensional (2D) images to one-dimensional (1D) feature maps for sequence recognition may lose a large amount of spatial information and cannot recognize text with a large degree of curvature. In this paper, we propose an network infrastructure to recognize texts of arbitrary shapes, named COT2D Attention Text Recognition Network (COT2Net). Firstly, deformable convolution is added to the feature extraction module, which can perform feature extraction according to the shape of the character and expand the receptive field of feature extraction; Finally, in the Transformer encoding stage, the multi-head attention is changed to Contextual 2D Multi-head Attention (COT2D), which can make full use of the relationship between the input keys Q, K, and V to guide the learning of dynamic attention, thereby enhancing the visual expression ability of text images. The COT2DNet uses COT2D to learn the relevance of each character in a scene text image and achieves excellent results on public datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Methodological Study of Document Layout Analysis

A Methodological Study of Document Layout Analysis

引用

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

作者： Chunhu Zhang Mayire Ibrayim Askar Hamdulla Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China School of Information Science and Engineering Xinjiang University Xinjiang China

Document layout analysis is an important part of document information processing systems, which is essential for many applications such as optical character recognition (OCR) systems, machine translation, information retrieval, and document structured data extraction, as well as for digitizing paper documents and classifying and identifying document image regions. Document-like images contain a wealth of information, and in order to automatically extract and classify regions of interest in document images, the document images are programmed to analyze the layout content for subsequent OCR and automatic transcription. However, the proposed algorithms still have more limitations due to various document layouts and variations of block positions, inter-class and within-class variations, and background noise. This paper first summarizes the traditional learning algorithms based on tour smoothing and segmentation projection, deep learning algorithms using recurrent convolutional neural networks and twin networks, and algorithms combining traditional learning and deep learning proposed in recent years. The current mainstream algorithms and common datasets in experiments for deep learning and their access are highlighted. As well as the comparison of some algorithms on benchmark datasets, and some experimental results with good robustness are given. Finally, the future research areas are prospected for further development.

关键词： Deep learning Text analysis Smoothing methods Layout Optical character recognition Virtual reality Information processing

来源：评论

学校读者我要写书评

暂无评论

Sub-word based unsupervised bilingual dictionary induction for Chinese-Uyghur

Sub-word based unsupervised bilingual dictionary induction f...

引用

International Conference on Asian Language processing (IALP)

作者： Anwar Aysa Mijit Ablimit Hankiz Yilahun Askar Hamdulla Xinjiang Key Laboratory of Signal Detection and Processing School of Information Science and Engineering Xinjiang University of China Urumqi Xinjiang China

ISBN: (数字)9781665476744

ISBN: (纸本)9781665476751

In this paper, we focus on the task of bilingual dictionary induction for the Chinese-Uyghur language pair. Usually, correlating long-distance linguistic information requires cross-linguistic information as supervision, which often requires parallel corpora to link in seed lexicons. And the parallel corpora are expensive. The low-resource Uyghur language text data are only available in a small amount, and the derivative morphological structure is vibrant and complex. In bilingual processing aligning most similar units and entity stems is the first step. So separating sentences into morpheme sequences is essential in the cross-lingual processing tasks. Uyghur words in text sentences consist of stems joined with several suffixes/prefixes. Rich and complex multiple affix forms exist in the text, forming many derivative words. This situation can easily lead to an increase in the repetition rate of intentional features in the text, which affects the efficiency of bilingual dictionary extraction. In this work, we actively explore the resource construction and granularity optimization of minority low-resource languages and learn cross-language word embeddings without the supervision of parallel data. A Chinese-Uyghur bilingual dictionary extraction method is proposed based on the neural network cross-language word embedding vector technology and the multilingual morphological analyzer. Experiments show that the way based on morpheme sequence significantly improved compared to the baseline model of the word sequence.

关键词： Dictionaries Error analysis Neural networks Linguistics Feature extraction Task analysis Unsupervised learning

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

A High Isolation Design Used Between Broadband Dual Polarization Transceiver Antennas

A High Isolation Design Used Between Broadband Dual Polariza...

引用

International Symposium on Antennas, Propagation and EM Theory (ISAPE)

作者： Yuke Guo Xiaosheng Zhang Luyu Zhao National Key Laboratory of Radar Detection and Sensing Xidian University Xi'an China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

ISBN: (数字)9798350353129

ISBN: (纸本)9798350353136

We proposed a high isolation design between two broadband dual polarization transceiver antennas in this paper. It employs periodic metal isolation walls with equal spacing and height to strongly suppress the low-frequency band (LB) coupling. Covering the vertical and horizontal surfaces of the metal with flexible graphene high resistive metasurfaces that easily conform to the structure improves 40 dB in isolation between different polarizations at 6–18 GHz. This device has less impact on the radiation pattern of the antenna. This design not only enhances the isolation between different polarizations but also optimizes equipment heat dissipation and improves device performance.

关键词： Performance evaluation Heating systems Couplings Graphene Metals Metasurfaces Transceivers Broadband communication Broadband antennas Antenna radiation patterns

来源：评论

学校读者我要写书评

暂无评论

G-YOLOv5: A Face Mask Detector That Balances Effectiveness and Real-Time

G-YOLOv5: A Face Mask Detector That Balances Effectiveness a...

引用

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

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

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

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：