检索结果-内蒙古大学图书馆

Domain-adaptive transfer network for visual–textual cross-domain sentiment classification

Journal of Supercomputing 2025年第7期81卷 1-30页

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

Cross-domain sentiment analysis aims to address the problem of insufficient labeled data by transferring invariant knowledge across domains. Existing studies focus on unimodal domain transfer, but modal differences hinder the transfer of domain information and limit the acquisition of domain-invariant knowledge in multimodal data. Therefore, we propose a domain-adaptive transfer network (DATN) for multimodal cross-domain sentiment analysis. The joint representation is acquired through a bidirectional visual–textual interactive fusion network, and adversarial discriminative domain adaptation is employed to learn the marginal domain shared knowledge in the joint representation. The performance of multimodal domain adaptive modules aligns with conditional distributions. Extensive experiments on public and self-constructed datasets demonstrate the effectiveness of the model and show that self-constructed datasets have the potential to serve as a new benchmark. Compared with the best-performing method, the model’s accuracy on public datasets increased by 3.6% and 8.2%, respectively, and on self-built datasets by 9.2% and 3.3%, respectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

An Evolutionary Multitasking Algorithm for Efficient Multiobjective Recommendations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第3期6卷 518-532页

作者： Tian, Ye Ji, Luke Hu, Yiwei Ma, Haiping Wu, Le Zhang, Xingyi Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Hefei230601 China Anhui University Institutes of Physical Science and Information Technology Hefei230601 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Hefei230029 China

Represented by evolutionary algorithms and swarm intelligence algorithms, nature-inspired metaheuristics have been successfully applied to recommender systems and amply demonstrated effectiveness, in particular, for multiobjective recommendation. Owing to the population-based search paradigm, these algorithms can produce a number of recommendation lists, making diverse tradeoffs between multiple metrics and meeting the requirements of accuracy, novelty, diversity, and other user preferences. However, these algorithms are criticized for the low efficiency of the optimization process, especially when the number of users is large. To address this issue, this article proposes an evolutionary multitasking-based recommendation method, where each task corresponds to a user and all the tasks are optimized simultaneously, thus highly improving the efficiency of recommendation. To enhance the convergence speed, all the users are divided into multiple populations according to the similarity between their preferences, where each population evolves with internal knowledge transfer between users, and all the populations evolve with external knowledge transfer between populations. Experimental results on various datasets verify that the proposed method can better balance between multiple metrics than classical and deep neural network-based recommendation methods and exhibits significantly higher efficiency than evolutionary multiobjective optimization-based recommendation methods. © 2024 IEEE. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Dual-function radar-communication System: Joint Design Method of Transmit Waveform and Receive Weight 16

Dual-function Radar-communication System: Joint Design Metho...

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Liu, Xuchen Liu, Yongjun Lu, Jiaguo Liao, Guisheng Zhang, Daisheng Tang, Hao Wang, Heming Dong, Xiaoyang National Key Laboratory of Radar Signal Processing Xidian University China The 38th Research Institute of China Electronics Technology Group Corporation China Jianghuai Advanced Technology Center China

ISBN: (纸本)9781510689251

In the dual-function radar-communication (DFRC) system, the radar and communication waveforms will be distorted and the signal-to-interference-plus-noise ratio (SINR) of DFRC system and downlink user will decrease when the mutual interference between radar and communication is not suppressed. To this end, a joint design method of transmit waveform and receive weight is proposed in this paper. Firstly, the signal model involving the DFRC system and the downlink user is developed. Then, the joint design problem of transmit waveform and receive weight is formulated. In this problem, the radar and communication SINR is maximize with the energy constrains. To solve the problem, the joint design method based on the block coordination descent (BCD) framework is proposed. Finally, the effectiveness of the proposed joint design method is verified via simulation results. © 2025 SPIE.

关键词： signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Joint Motion Compensation radar Imaging Based on Bi-XLSTM and BP Algorithm

IEEE Transactions on Radar Systems

引用

IEEE Transactions on radar Systems 2025年 3卷 738-755页

作者： Ren, Xuemei Li, Xiaoyong Rong, Pengshuai Zhou, Wanting Liu, Lei Bai, Xueru Zhou, Feng Xidian University National Key Lab of Radar Signal Processing Xi’an710071 China Xidian University Hangzhou Institute of Technology Hangzhou311231 China Xidian University Key Laboratory of Electronic Information Countermeasure and Simulation Technology of Ministry of Education Xi’an710071 China Xidian University School of Aerospace Science and Technology Xi’an710071 China

Advances in high-speed digital acquisition and storage technologies have enabled the sampling of radar echoes at intermediate frequencies. Precise gate control and recording techniques facilitate translational compensation based on echo coherence, enabling robust imaging even in low SNR conditions. Despite these advancements, existing approaches face inefficiencies in parameter estimation and encounter significant difficulties in azimuth focusing when increasing imaging resolution at large angles. To address these challenges, a novel joint motion compensation imaging algorithm that integrates Bidirectional Extended Long Short-Term Memory (Bi-XLSTM) networks with back projection (BP) is proposed. This approach initiates with the development of a comprehensive joint motion echo model for the target to reduce cumulative errors, thereby establishing a solid foundation for further joint motion compensation. Next, Bi-XLSTM is utilized for the efficient extraction of motion parameters from coherent echoes. The Adam optimization algorithm is then applied during the BP imaging process to jointly optimize motion and rotation parameters, targeting optimal image quality and resulting in highly focused images. Experiments conducted on point simulations, electromagnetic simulations, and real data confirm that this technique outperforms traditional methods. © 2023 IEEE.

关键词： Motion analysis

来源：评论

学校读者我要写书评

暂无评论

HF signal Protocol Unique Sequence Classification based on Deep Learning 16

HF Signal Protocol Unique Sequence Classification based on D...

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Li, Weihao Wang, Keren You, Ling Huang, Zhitao Xiong, Gang College of Electronic Science and Technology National University of Defense Technology Changsha410073 China National Key Laboratory on Blind Signal Processing Chengdu610041 China

ISBN: (纸本)9781510689251

This paper studies the classification of high frequency (HF) signal unique sequence like the preamble, which helps to identify the HF communication protocol. Targeting at a processing flow of sliding window-based unique sequence classification in the narrowband data, and considering the disadvantages of the traditional unique sequence template correlation method, such as relying on the unique sequence knowledge and its strong correlation, slow calculation speed and the calculation times increase with the number of classes, this paper uses deep learning technology to classify the unique sequence classes. The main improvements are that, based on the two classical convolutional neural networks, the relationship between the model receptive field and signal symbol rate is analyzed and adjusted accordingly;and in order to make the local symbol features extracted by convolutional network context-related, a multi-head self-attention layer is introduced behind it. In the experiments, 7 types of real-world signals and background signals are used. The results show that the improved neural networks obtain classification F1 performances similar to that of the traditional high-precision template correlation method, and their processing speed is dozens of times faster than the latter. © 2025 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Shared Vision Transformer Helps Scene Text Retrieval 4th

Shared Vision Transformer Helps Scene Text Retrieval

引用

4th International Conference on Pattern Recognition and Artificial Intelligence, ICPRAI 2024

作者： Luo, Hailong Ibrayim, Mayire Hamdulla, Askar Deng, Qilin School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China

ISBN: (纸本)9789819787043

The scene text retrieval system can search all the images containing the query text in the gallery based on the input query text and locate the position of the query text at the same time. The current state-of-the-art approach is to match query images and text instances based on visual information, which somewhat mitigates the heterogeneous differences between the two modalities and can support the zero-shot training approach. But there is no consideration of two branches of features interacting on information as a way to enhance the features. In this paper, we improve this method. First, we design a structure that enhances features using a shared-visual embedding transformer (S-VET). Text instance features and query input features are brought closer visually by a visual transformer with shared parameters and then spliced and fused with the original features to enrich the visual information of the two branch features. We then design a Multi-Scale Residual Channel Attention (MRCA) module to obtain features at different scales by using convolution kernels at multiple scales and then use channel attention to mine beneficial information from features at different scales. Facilitated by the above scheme, our method achieved a more advanced performance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

MFDPonzi: Detecting Ethereum Ponzi Schemes Using Static Features from Novel Opcode Sequences

MFDPonzi: Detecting Ethereum Ponzi Schemes Using Static Feat...

引用

2025 IEEE International Conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Cao, Longwei Qin, Jiwei Zhang, Xuzi College of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi China

ISBN: (纸本)9798350368741

Ethereum, the first blockchain platform to support smart contracts, has become a target for various cybercrimes, particularly financial frauds like Ponzi schemes. Ponzi schemes on Ethereum are known as Smart Ponzi Schemes (or Ponzi Contracts) and have caused huge financial losses. Current Ponzi contract detection models face three main challenges: simple opcode sequence processing does not effectively distinguish Ponzi from non-Ponzi contracts, single-feature-based models lack accuracy, and reliance on transaction records hinders early detection. To address these issues, this paper proposes a Multi-Feature Ponzi Scheme Detection Model (MFDPonzi). MFDPonzi tracks the changes in stack, memory, and storage parameters during the execution of smart contracts, reconstructing opcode sequences and extracting diverse features, including semantic and developer features. Finally, a multi-feature fusion algorithm is used to enhance model stability. Additionally, MFDPonzi can identify Ponzi contracts at the early stage of smart contract creation without relying on transaction data. Experimental results show that MFDPonzi achieves an 85.9% recall and an 88.7% F-score on Ethereum smart contracts, outperforming baselines in both performance and robustness. © 2025 IEEE.

关键词： Blockchain Ethereum Ponzi scheme Smart contract

来源：评论

学校读者我要写书评

暂无评论

Difference Bonds Consistency and Complementarity to Enhance Multimodal Representation Learning

Difference Bonds Consistency and Complementarity to Enhance ...

引用

2025 IEEE International Conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： He, Congbing Song, Sensen Jia, Zhenhong Zhao, Hui Xinjiang Uygur Autonomous Region Signal Detection and Processing Key Laboratory School of Computer Science and Technology Xinjiang University Urumqi830046 China

ISBN: (纸本)9798350368741

In the field of multimodal representation learning, existing research has primarily focused on exploring modal consistency and modal complementarity, while overlooking the positive role of modal difference. Moreover, modal difference establishes a bonding relationship between modal consistency and modal complementarity. However, existing algorithms lack the study of this relationship, resulting in an accuracy that still needs to be improved on multimodal classification tasks. To tackle the above issues, We propose a novel multimodal representation learning framework. It enhances multimodal representation learning by modal difference constructing connecting bonds of modal consistency and modal complementarity. We conducted experiments on two widely used multimodal emotion recognition datasets, IEMOCAP and MELD. The results demonstrate that our method outperforms existing multimodal representation learning approaches in terms of accuracy on the multimodal emotion recognition task. © 2025 IEEE.

关键词： Multimodal Difference Multimodal Emotion Recognition Multimodal Representation Learning

来源：评论

学校读者我要写书评

暂无评论

Improving Speaker Verification Back-End with Graph Neural Networks

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-9页

作者： Chen, Jinfeng Fang, Zhihua He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China School of Intelligence Science and Technology Xinjiang University Urumqi830017 China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

Currently, research on speaker verification tasks is primarily concentrated on enhancing deep speaker models to extract high-quality speaker embeddings. Nevertheless, this speaker embeddings can be regarded as potential graph structures. Therefore, this paper introduces a graph neural network-based speaker verification back-end approach, treating the speaker embeddings derived from the front-end as graph structures and leveraging graph neural networks to uncover the relationships among embeddings, thereby achieving superior-quality speaker embeddings. In addition, we propose a group updating method to solve the problem of memory overflow when the number of nodes is excessive. Extensive experiments and ablation studies were carried out on the VoxCeleb dataset, and the experimental outcomes validate the effectiveness of our proposed graph neural network speaker back-end in significantly boosting the performance of speaker verification systems. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Anomalous Sound Detection Using Time-Frequency Feature and Mixbatch

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-8页

作者： Huang, Shun Zhang, Yunxiang Fang, Zhihua Tang, Minrui Xu, Ruifeng He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China School of Intelligence Science and Technology Xinjiang University Urumqi830017 China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

The sound emitted by machines under abnormal working conditions exhibits various frequency patterns. Currently, the most advanced anomalous sound detection (ASD) approach is to apply a multi-head self-attention mechanism to the Log-Mel spectrogram for automatic frequency pattern analysis. However, the Log-Mel spectrogram may filter out high-frequency components of abnormal sounds;thus the use of self-attention mechanisms on Log-Mel spectrogram seems to have certain limitations. In this paper, we construct a simple convolutional neural network to extract comprehensive frequency features from raw audio to complement spectral-temporal information fusion. The parameters of this neural network are continuously updated during the training process to extract better frequency features for downstream classification neural networks in ASD. Additionally, a method for data augmentation in the batch dimension was developed to help the classification model learn both types of comprehensive features simultaneously. The proposed method achieved an AUC of 94.13% and a pAUC of 89.09% on the DCASE 2020 Challenge Task 2 dataset. Even when using only the features proposed in this paper, an AUC of 84.62% was achieved. (Figure presented.). © Shanghai Jiao Tong University 2025.

关键词： Spectrographs

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：