检索结果-内蒙古大学图书馆

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

作者： Zhou, Chenyang Monghjaya Wu, Licheng School of Chinese Ethnic Minority Languages and Literatures Minzu University of China Beijing100081 China College of Computer Science Inner Mongolia University Hohhot010021 China School of Information Engineering Minzu University of China Beijing100081 China Key Laboratory of Ethnic Language Intelligent Analysis and Security Management of MOE Minzu University of China Beijing100081 China National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot010021 China Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology Hohhot010021 China

ISBN: (纸本)9798350368741

The traditional Mongolian script poses significant challenges for text rendering due to its vertical orientation, complex glyph variations, and context-dependent shapes, compounded by limited linguistic resources. This paper introduces the first method specifically designed to address the out-of-vocabulary (OOV) word problem in traditional Mongolian script conversion. We present a novel dataset and propose MonTransformer, the first Transformer-based model tailored for converting Unicode phonetic sequences into glyph sequences. MonTransformer utilizes dynamic optimization and contrastive learning to effectively manage OOV cases and improve sequence generation accuracy, transforming Unicode inputs into visually accurate glyph representations. Our approach achieves state-of-the-art performance, maintaining the script's visual fidelity and advancing efforts in digital preservation for complex scripts. © 2025 IEEE.

关键词： Contrastive learning Dynamic optimization Out-of-vocabulary (OOV) Sequence generation Traditional Mongolian script

来源：评论

学校读者我要写书评

暂无评论

Learning Features by Minimizing the Interframe Differences 19th

Learning Features by Minimizing the Interframe Differences

引用

19th Chinese Conference on Image and Graphics Technologies and Applications, IGTA 2024

作者： Zhao, Dong Zhang, Dan School of Computer Qinghai Normal University Xining810016 China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining810016 China

ISBN: (纸本)9789819799183

In this paper, we present a novel yet intuitive unsupervised feature learning approach, referred to as Minimizing Interframe Differences (MID). The idea is the following: as long as the unsupervised features successfully encode the essential information about the visual structures of the frames, the differences between the before and after frames can be minimally encoded. MID is implemented with a difference encoding module and a frame reconstruction module. The former tries to minimize the difference between frames, while the latter first maps the difference encoding to optical flow and then realizes frame reconstruction based on the learned optical flow. All the modules are jointly learned in an end-to-end way through the reconstruction loss. We verify the feasibility of MID in the image datasets by replacing the natural transformation of videos to artificially parameterized transformation for images. Experimental results show that MID is able to predict optical flow accurately based on the minimum difference coding and learn a powerful visual representation that greatly enhances other visual tasks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

HybridFL: Hybrid Approach Toward Privacy-Preserving Federated Learning 6th

HybridFL: Hybrid Approach Toward Privacy-Preserving Federate...

引用

6th International Conference on Security and Privacy in New computing Environments, SPNCE 2023

作者： Ali, Sheraz Mamoon, Saqib Usman, Areeba Abidin, Zain ul Zhao, Chuan School of Information Science and Engineering University of Jinan Jinan250022 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China University of Sargodha Sargodha Pakistan Shandong Provincial Key Laboratory of Network-Based Intelligent Computing University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Software Engineering University of Jinan Jinan250022 China

ISBN: (纸本)9783031736988

In this study, we introduce a novel Hybrid Federated Learning (HybridFL) approach aimed at enhancing privacy and accuracy in collaborative machine learning scenarios. Our methodology integrates Differential Privacy (DP) and secret sharing techniques to address inference risks during training and protect against information leakage in the output model. Drawing inspiration from recent advances, we present a HybridFL framework that combines the strengths of Homomorphic Encryption (HE) and Multi-Party Computation (MPC) to achieve secure computation without the computational overhead of pure HE methods. Our contributions include a privacy-preserving design for Federated Learning (FL) that ensures local data privacy through secret sharing while leveraging DP mechanisms for noise addition. The system offers resilience against unreliable participants and is evaluated using various machine learning models, including Convolutional Neural Networks (CNN), Multi-Layer Perceptrons (MLP), and linear regression. Furthermore, we address potential external threats by deploying predictive model outputs as robust services against inference attacks. Experimental results demonstrate improved accuracy and convergence speed, establishing the viability of HybridFL as an effective solution for collaborative machine learning with enhanced privacy guarantees. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Time-independent Spiking Neuron via Membrane Potential Estimation for Efficient Spiking Neural Networks

Time-independent Spiking Neuron via Membrane Potential Estim...

引用

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

作者： Hanqi Chen Lixing Yu Shaojie Zhan Penghui Yao Jiankun Shao Yunnan Key Laboratory of Intelligent Systems and Computing School of Information Science and Engineering Yunnan University China State Key Laboratory of Explosion Science and Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The computational inefficiency of spiking neural networks (SNNs) is primarily due to the sequential updates of membrane potential, which becomes more pronounced during extended encoding periods compared to artificial neural networks (ANNs). This highlights the need to parallelize SNN computations effectively to leverage available hardware parallelism. To address this, we propose Membrane Potential Estimation Parallel Spiking Neurons (MPE-PSN), a parallel computation method for spiking neurons that enhances computational efficiency by enabling parallel processing while preserving the intrinsic dynamic characteristics of SNNs. Our approach exhibits promise for enhancing computational efficiency, particularly under conditions of elevated neuron density. Empirical experiments demonstrate that our method achieves state-of-the-art (SOTA) accuracy and efficiency on neuromorphic datasets. Codes are available at https://***/chrazqee/MPE-PSN.

关键词： Neuromorphics Computational modeling Neurons Membrane potentials Estimation Spiking neural networks Parallel processing Signal processing Computational efficiency Speech processing

来源：评论

学校读者我要写书评

暂无评论

VAGeo: View-specific Attention for Cross-View Object Geo-Localization

VAGeo: View-specific Attention for Cross-View Object Geo-Loc...

引用

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

作者： Zhongyang Li Xin Yuan Wei Liu Xin Xu School of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Cross-view object geo-localization (CVOGL) aims to locate an object of interest in a captured ground- or drone-view image within the satellite image. However, existing works treat ground-view and drone-view query images equivalently, overlooking their inherent viewpoint discrepancies and the spatial correlation between the query image and the satellite-view reference image. To this end, this paper proposes a novel View-specific Attention Geo-localization method (VAGeo) for accurate CVOGL. Specifically, VAGeo contains two key modules: view-specific positional encoding (VSPE) module and channel-spatial hybrid attention (CSHA) module. In object-level, according to the characteristics of different viewpoints of ground and drone query images, viewpoint-specific positional codings are designed to more accurately identify the click-point object of the query image in the VSPE module. In feature-level, a hybrid attention in the CSHA module is introduced by combining channel attention and spatial attention mechanisms simultaneously for learning discriminative features. Extensive experimental results demonstrate that the proposed VAGeo gains a significant performance improvement, i.e., improving acc@0.25/acc@0.5 on the CVOGL dataset from 45.43%/42.24% to 48.21%/45.22% for ground-view, and from 61.97%/57.66% to 66.19%/61.87% for drone-view.

关键词： Location awareness Accuracy Attention mechanisms Image coding Signal processing Encoding Satellite images Object recognition Speech processing Drones

来源：评论

学校读者我要写书评

暂无评论

Research on Feature Selection Methods Based on Hypergraph Theory in Multi-scale Decision information System 24

Research on Feature Selection Methods Based on Hypergraph Th...

引用

3rd International Conference on Artificial Intelligence and intelligent information processing, AIIIP 2024

作者： Zheng, Ziwei Geng, Shengling Zhou, Mingquan School of Computer Science Qinghai Normal University Qinghai Xining China Academy of Plateau Science and Sustainability People’s Government of Qinghai Province Beijing Normal University Qinghai Xining China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Qinghai Normal University Qinghai Xining China

ISBN: (纸本)9798400707308

Feature selection is critical for enhancing data processing efficiency and decision accuracy. In multi-scale decision information systems, a novel hypergraph-based feature selection method is proposed to address the challenge of selecting the optimal scale combination from multi-scale features. An adjacency relationship matrix is defined to induce a hypergraph, which visualizes the relationships among multi-scale features and transforms the feature selection problem into a minimal vertex cover problem within the hypergraph. This approach facilitates the selection of the optimal scale feature subset. Additionally, the algorithm incorporates a priority queue to manage the sorting of features, significantly reducing time complexity and improving solution efficiency. © 2024 Copyright held by the owner/author(s).

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Decoder Model Based On Spiking Neural Networks For Address Event Representation Object Recognition

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Du, Sichun Zhu, Haodi Zhang, Yang Hong, Qinghui Hunan University College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN) provides an energy-saving solution for AER object recognition. However, SNN with spike timing dependent plasticity (STDP) learning rule has not achieved satisfying AER object recognition performance. This work proposes an SNN-based encoder-decoder model to improve the recognition performance of AER objects. An STDP-based locally connected spiking neural network (LC-SNN) is proposed as an encoder to extract rich spatiotemporal features from AER event flows more flexibly. After the encoder extracts and learns primary features, we propose a fully connected spiking neural network (FC-SNN) based on the reward-modulated spike-timing-dependent plasticity (R-STDP) learning rule as a decoder to learn higher-level features for classification. In addition, we improved the winner-take-all (WTA) mechanisms and R-STDP learning rule in the decoder based on the reward and punish decision, enabling the network to perform better. The experiments are performed on the N-MNIST, MNIST-DVS, and the DVS Gesture datasets, improving the accuracy of the best existing plasticity-based SNN by 0.19%, 0.27% and 1.35%, respectively. © 2016 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Editable Portrait Synthesis with 3D GAN Inversion

High-Fidelity Editable Portrait Synthesis with 3D GAN Invers...

引用

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

作者： Jindong Xie Jiachen Liu Yupei Lin Jinbao Wang Xianxu Hou Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Information Engineering Guangdong University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Information Processing School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The 3D generative adversarial network (GAN) inversion converts an image into 3D representation to attain high-fidelity reconstruction and facilitate realistic image manipulation within the 3D latent space. However, previous approaches face challenges regarding the trade-off between the reconstruction ability and editability. That is, reversing a real-world image to a low-dimensional latent code would inevitably lead to information loss, and achieving a near-perfect reconstruction using high-rate triplane representation often limits the ability to manipulate the image freely in the latent space. To address these issues, we propose a novel latent conditioning encoder-based framework with the alignment between the low-dimensional latent and high-dimensional triplane. A non-semantic guided editing strategy bridges the intrinsic relation between the latent condition and triplane generation, making it possible to edit the high-dimensional representation by latent manipulation. As a result, our method can achieve high-fidelity reconstruction and editing simultaneously by directly controlling the latent code. Experimental results demonstrate that our approach excels in reconstruction and editing quality compared to previous 3D inversion methods. Furthermore, our method can also edit even real faces with large poses and out-of-domain cases.

关键词： Bridges Three-dimensional displays Codes Signal processing Generative adversarial networks Vectors Acoustics Speech processing Image reconstruction Faces

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Haptic Compression Inspired by Embodied AI for Haptic Communications

引用

IEEE Transactions on Multimedia 2025年

作者： Lu, Hang Tan, Xinmeng Chen, Mingkai Zhang, Zhe Zhang, Xuguang Chen, Jianxin Wei, Xin Zhao, Tiesong Nanjing University of Posts and Telecommunications Key Laboratory of Broadband Wireless Communication and Sensor Network Technology China Fuzhou University Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou350108 China Fuzhou University Fujian Science & Technology Innovation Laboratory for Optoelectronic Information Fuzhou350108 China

Haptic data compression has gradually become a key issue for emerging real-time haptic communications in Tactile Internet (TI). However, it is challenging to achieve a tradeoff between high perceptual quality and compression ratio in haptic data compression scheme. Inspired by the perspective of embodied AI, we propose a cross-modal haptic compression scheme for haptic communications to improve the perception quality on TI devices in this paper. Since multimodal fusion is routinely employed to improve the ability of system in cognition, we assume that haptic codec is guided by visual semantics to optimize parameter settings in the coding process. We first design a multi-dimensional tactile feature fusion network (MTFFN) relying on multi-head attention mechanism. The MTFFN extracts the multi-dimensional features from the material surface and maps them to infer the coding parameters. Secondly, we provide second-order difference and linear interpolation to establish an criterion for the determination of optimal codec parameters, which are customized by the material categories so as to give high robustness. Finally, the simulation results reveal that our compression scheme can efficiently make a personalized codec procedure for different materials, obtaining more than 17% improvement in terms of compression ratio with high perceptual quality at the same time. © 2025 IEEE.

关键词： Data compression ratio

来源：评论

学校读者我要写书评

暂无评论

Robust Self-Localization of Wireless Acoustic Sensor Networks

引用

IEEE Internet of Things Journal 2025年

作者： Wang, Xu Hu, De Liu, Rui Bao, Feilong Inner Mongolia University College of Computer Science Hohhot010021 China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot 010021 China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Hohhot 010021 China

Wireless acoustic sensor networks (WASNs), or the so-called internet of audio things (IoAuTs), have attracted increasing attention in the IoT community. As the geometry structure of WASNs is required in audio/speech processing tasks like source localization or acoustic beamforming, automatic self-localization of sensors is necessary. However, most of the existing approaches suffer from poor stability, as their constructed cost functions involve non-convex programming. To address this issue, we investigate the robust self-localization (or geometry calibration) of WASNs in this paper. Specifically, a rough self-localization (RSL) method is first presented based on measurements including time-difference-of-arrivals (TDoAs), direction-of-arrivals (DoA), and energy-rates (ERs), and its closed-form solution is further derived. As ER estimates are sensitive to acoustic environments, the performance of the RSL method is somewhat limited. Therefore, a precise self-localization (PSL) method is then developed by building a weighted (and non-convex) TDoA-DoA cost function, after regarding the RSL approach as an initialization step. As the RSL offers better initial values compared with existing initialization strategies, the combination of RSL and PSL methods (named as RSL-PSL method) shows stronger robustness and stability. In addition, computational complexity of both RSL and PSL methods are analyzed in details. Finally, the Cramér-Rao Bound (CRB) of the PSL method is derived to show its theoretical lower bound. The proposed RSL-PSL method outperforms the state-of-the-arts in terms of stability and accuracy, which is confirmed by numerical real-world and simulation experiments. © 2014 IEEE.

关键词： Cost functions

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：