检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Hu, Zhongtian Cui, Yiwen Li, Ronghan Zhao, Meng Wang, Lifang School of Computer Science and Engineering Northwestern Polytechnical University China School of Computer Science and Technology Xidian University China School of Artificial Intelligence and Big Data Henan University of Technology China

Dialogue response generation has made significant progress, but most research has focused on dyadic dialogue. In contrast, multi-party dialogues involve more participants, each potentially discussing different topics, making the task more complex. Current methods often rely on graph neural networks to model dialogue context, which helps capture the structural dynamics of multi-party conversations. However, these methods are heavily dependent on intricate graph structures and dataset annotations, and they often overlook the distinct speaking styles of participants. To address these challenges, we propose CMR, a Contrastive learning-based Multi-party dialogue Response generation model. CMR uses self-supervised contrastive learning to better distinguish "who says what." Additionally, by comparing speakers within the same conversation, the model captures differences in speaking styles and thematic transitions. To the best of our knowledge, this is the first approach to apply contrastive learning in multi-party dialogue generation. Experimental results show that CMR significantly outperforms state-of-the-art models in multiparty dialogue response tasks. © 2025, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Robust Deployment of Sensing UAVs for TDOA Localization with Distance-Dependent Noise

Robust Deployment of Sensing UAVs for TDOA Localization with...

引用

IEEE Conference on Wireless Communications and Networking

作者： Zhongyu He Xin Guan Qingjiang Shi School of Computer Science and Technology Tongji University Shanghai China Shenzhen Research Institute of Big Data Shenzhen China

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Traditional ground-based sensor deployment for time difference of arrival (TDOA) localization usually assumes distance-independent measurement error between the target and the sensors. With the growing popularity of using unmanned aerial vehicles (UAVs) for radio localization, existing TDOA sensor deployment solutions could be no longer applicable due to the high mobility of UAVs. This paper considers a robust deployment problem of the sensing UAVs for TDOA localization with the target located in a circular uncertainty area. The objective is to minimize the Cramér-Rao Bound (CRB), in which the covariance matrix of the TDOA measurement noise is formulated as a function of the distance between the target and the sensing UAVs. To tackle the highly non-convex problem, we reformulate it in a master-slave manner as two subproblems. Inspired by the prevailing Gibbs sampling method, we propose a grid-based dual-space stepwise optimization (GDSSO) algorithm to solve the master problem, while the slave problem for finding the worst-case point in the uncertainty area could be efficiently solved through gradient projection. Simulation results demonstrate the rationality of our problem formulation as well as the effectiveness of the proposed algorithm.

关键词： Location awareness Uncertainty Time difference of arrival Heuristic algorithms Simulation Noise Autonomous aerial vehicles Main-secondary Sensors Covariance matrices

来源：评论

学校读者我要写书评

暂无评论

Can xLLMs Understand the Structure of Dialog? Exploring Multilingual Response Generation in Complex Scenarios

arXiv

引用

arXiv 2025年

Multilingual research has garnered increasing attention, especially in the domain of dialogue systems. The rapid advancements in large language models (LLMs) have fueled the demand for high-performing multilingual models. However, two major challenges persist: the scarcity of high-quality multilingual datasets and the limited complexity of existing datasets in capturing realistic dialogue scenarios. To address these gaps, we introduce XMP, a high-quality parallel Multilingual(X) dataset sourced from Multi-party Podcast dialogues1. Each sample in the dataset features at least three participants discussing a wide range of topics, including society, culture, politics, and entertainment. Through extensive experiments, we uncover significant limitations in previously recognized multilingual capabilities of LLMs when applied to such complex dialogue scenarios. For instance, the widely accepted multilingual complementary ability of LLMs is notably impacted. By conducting further experiments, we explore the mechanisms of LLMs in multilingual environments from multiple perspectives, shedding new light on their performance in real-world, diverse conversational contexts. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Subpart Suppression Network for Few-Shot Object Counting

Subpart Suppression Network for Few-Shot Object Counting

引用

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

作者： Lanxin Liu Xinyan Liu Guorong Li School of Computer Science and Technology Key Lab of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences School of Computer Science and Technology Harbin Institute of Technology (Weihai)

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Few-shot object counting and detection aim to count objects along with their bounding boxes specified by exemplar bounding boxes. Current mainstream methods predict density maps by applying similarity between exemplar and image features to get counting results and detecting peak points from the density map as the positions of objects. However, the sub-parts of objects can also have high similarity to the exemplars, harming the counting and detection performance. To address these issues, we propose a two-stage Subpart Suppression Network (SSN), consisting of a Subpart Suppression Density map Predictor (SSDP), which enforces the model focus on whole objects rather than subparts, and a SAM-based Detector and Verifier, which refines the final prediction by a clustering method. Extensive experiments on two popular datasets show an advantage in performance over the state-of-the-art methods and prove the components’ effectiveness.

关键词： Accuracy Filtering Convolution Clustering methods Detectors Predictive models Feature extraction Acoustics Speech processing Kernel

来源：评论

学校读者我要写书评

暂无评论

Cross-Scale Bilevel Aggregation for Multi-exposure Fusion via Conditional Generative Adversarial Network 9th

Cross-Scale Bilevel Aggregation for Multi-exposure Fusion v...

引用

9th International Conference on Internet of Things, ICIOT 2024, Held as Part of the Services Conference Federation, SCF 2024

作者： Wang, Longchun Yu, Mali Zhang, Hai Yang, Taojun Leng, Qingming Dong, Xiwei Guo, Jingjuan Wang, Guangxing School of Computer and Big Data Science Jiujiang University Jiujiang332005 China School of Information Management Jiangxi University of Finance and Economics Nanchang330013 China Jiujiang Engineering Research Center for Collaborative Cyber Security Protection Jiujiang332005 China School of Electronic and Information Engineering Jiujiang University Jiujiang332005 China

ISBN: (纸本)9783031770029

The aim of multi-exposure fusion (MEF) is to generate a high-dynamic-range-like image from images captured by common cameras under different exposure settings. The existing generative adversarial network (GAN)-based MEF methods have achieved fair performance. However, when addressing extremely exposed images, these existing GAN-based MEF methods still face numerous limitations, such as detail loss and unnatural visual effects, partly due to their inability to sufficiently aggregate multiscale context information. To address these limitations, we propose a cross-scale bilevel aggregation-based conditional generative adversarial network (CBA-cGAN). The generator contains two subnetworks: a cross-scale aggregation GhostNetV2 (CSA-GhostNetV2) for capturing and integrating multiscale context information with long-range dependencies and a U-shaped local network (ULN) for extracting local features. To fully aggregate short-range and multiscale long- range dependencies, we propose the use of bilevel aggregation in CSA-GhostNetV2: intrablock and interblock aggregation. The intrablock aggregation scheme based on dilated convolution and GhostBlockV2 is designed to aggregate multiscale context information and long-range relationships. The interblock aggregation scheme is designed to balance local and global contextual information during the fusion process by combining features acquired from CSA-GhostNetV2 and the ULN. Additionally, to better align the visual effect with human perception, we take the average of the input images for the discriminator. We compare the performance of the proposed method with that of traditional and deep learning methods on two publicly available datasets in terms of six objective metrics. Extensive experiments are conducted to demonstrate that the proposed CBA-cGAN outperforms the existing state-of-the-art methods in retaining local details while preserving overall visual effects. © The Author(s), under exclusive license to Springer Nature Switzerla

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

FANformer: Improving Large Language Models Through Effective Periodicity Modeling

arXiv

引用

arXiv 2025年

作者： Dong, Yihong Li, Ge Jiang, Xue Tao, Yongding Zhang, Kechi Zhu, Hao Liu, Huanyu Ding, Jiazheng Li, Jia Deng, Jinliang Mei, Hong School of Computer Science Peking University China aiXcoder The Hong Kong University of Science and Technology Hong Kong Advanced Institute of Big Data

Periodicity, as one of the most important basic characteristics, lays the foundation for facilitating structured knowledge acquisition and systematic cognitive processes within human learning paradigms. However, the potential flaws of periodicity modeling in Transformer affect the learning efficiency and establishment of underlying principles from data for large language models (LLMs) built upon it. In this paper, we demonstrate that integrating effective periodicity modeling can improve the learning efficiency and performance of LLMs. We introduce FANformer, which integrates Fourier Analysis Network (FAN) into attention mechanism to achieve efficient periodicity modeling, by modifying the feature projection process of attention mechanism. Extensive experimental results on language modeling show that FANformer consistently outperforms Transformer when scaling up model size and training tokens, underscoring its superior learning efficiency. To further validate the effectiveness of FANformer, we pretrain a FANformer-1B on 1 trillion tokens. FANformer-1B exhibits marked improvements on downstream tasks compared to open-source LLMs with similar model parameters or training tokens. The results position FANformer as an effective and promising architecture for advancing LLMs. Our code and pretrained model are available at https://***/YihongDong/FANformer. Copyright © 2025, The Authors. All rights reserved.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Super-Resolution of Diffusion-Weighted Images via TDI-Conditioned Diffusion Model 15th

Super-Resolution of Diffusion-Weighted Images via TDI-Cond...

引用

15th International Workshop on Computational Diffusion MRI, CDMRI 2024, held in conjunction with 27th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2024

作者： Ma, Jiquan Teng, Yujun Chen, Geng Jiang, Haotian Zhang, Kai Liu, Feihong Rekik, Islem Shen, Dinggang School of Computer Science and Technology Heilongjiang University Harbin China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China School of Biomedical Engineering and State Key Laboratory of Advanced Medical Materials and Devices ShanghaiTech University Shanghai China School of Information Science and Technology Northwest University Xi’an China BASIRA Lab Imperial-X and Department of Computing Imperial College London London United Kingdom

ISBN: (纸本)9783031869198

Diffusion-Weighted Imaging (DWI) is a significant technique for studying white matter. However, it suffers from low-resolution obstacles in clinical settings. Post-acquisition Super-Resolution (SR) can enhance the resolution of DWIs and has gained increasing research interest in recent years. An advanced generative model, the Diffusion Model (DM), exhibits particularly promising performance in image SR. However, effective conditions are required to bootstrap the DM for DWI SR. To this end, we proposed the first DM-based DWI SR model with two effective conditions based on low-solution DWIs and Track Density Imaging (TDI) maps, which possess rich high-resolution prior knowledge Additionally, we consider another condition based on features from low-resolution DWIs. These two conditions are integrated into our model, which comprises three components: DWI Resolution Enhancer (DRE), DWI Feature Extractor (DFE), and TDI Feature Extractor (TFE). DRE combines low-resolution DWI features from DFE with TDI features from TFE to progressively generate high-resolution DWIs. We performed extensive experiments on DWIs of normal subjects from human connectome projects and patients with Parkinson’s disease. The results demonstrate that our model outperforms existing DWI SR models, both qualitatively and quantitatively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Decomposing and Fusing Intra- and Inter-Sensor Spatio-Temporal Signal for Multi-Sensor Wearable Human Activity Recognition

arXiv

引用

arXiv 2025年

作者： Xie, Haoyu Li, Haoxuan Zheng, Chunyuan Yuan, Haonan Liao, Guorui Liao, Jun Liu, Li School of Big Data and Software Engineering Chongqing University China Center for Data Science Peking University China School of Mathematical Sciences Peking University China School of Computer Science and Engineering Beihang University China

Wearable Human Activity Recognition (WHAR) is a prominent research area within ubiquitous computing. Multi-sensor synchronous measurement has proven to be more effective for WHAR than using a single sensor. However, existing WHAR methods use shared convolutional kernels for indiscriminate temporal feature extraction across each sensor variable, which fails to effectively capture spatio-temporal relationships of intra-sensor and inter-sensor variables. We propose the DecomposeWHAR model consisting of a decomposition phase and a fusion phase to better model the relationships between modality variables. The decomposition creates high-dimensional representations of each intra-sensor variable through the improved Depth Separable Convolution to capture local temporal features while preserving their unique characteristics. The fusion phase begins by capturing relationships between intra-sensor variables and fusing their features at both the channel and variable levels. Long-range temporal dependencies are modeled using the State Space Model (SSM), and later cross-sensor interactions are dynamically captured through a self-attention mechanism, highlighting inter-sensor spatial correlations. Our model demonstrates superior performance on three widely used WHAR datasets, significantly outperforming state-of-the-art models while maintaining acceptable computational efficiency. Our codes and supplementary materials are available at https://***/Anakin2555/DecomposeWHAR. © 2025, CC BY.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

CrossFi: A Cross Domain Wi-Fi Sensing Framework Based on Siamese Network

引用

IEEE Internet of Things Journal 2025年

作者： Zhao, Zijian Chen, Tingwei Cai, Zhijie Li, Xiaoyang Li, Hang Chen, Qimei Zhu, Guangxu Shenzhen Research Institute of Big Data Shenzhen518115 China Sun Yat-sen University School of Computer Science and Engineering Guangzhou510275 China Shenzhen Research Institute of Big Data Shenzhen518115 China Wuhan University School of Electronic Information Wuhan430072 China

In recent years, Wi-Fi sensing has garnered significant attention due to its numerous benefits, such as privacy protection, low cost, and penetration ability. Extensive research has been conducted in this field, focusing on areas such as gesture recognition, people identification, and fall detection. However, many data-driven methods encounter challenges related to domain shift, where the model fails to perform well in environments different from the training data. One major factor contributing to this issue is the limited availability of Wi-Fi sensing datasets, which makes models learn excessive irrelevant information and over-fit to the training set. Unfortunately, collecting large-scale Wi-Fi sensing datasets across diverse scenarios is a challenging task. To address this problem, we propose CrossFi, a siamese network-based approach that excels in both in-domain scenario and cross-domain scenario, including few-shot, zero-shot scenarios, and even works in few-shot new-class scenario where testing set contains new categories. The core component of CrossFi is a sample-similarity calculation network called CSi-Net, which improves the structure of the siamese network by using an attention mechanism to capture similarity information, instead of simply calculating the distance or cosine similarity. Based on it, we develop an extra Weight-Net that can generate a template for each class, so that our CrossFi can work in different scenarios. Experimental results demonstrate that our CrossFi achieves state-of-the-art performance across various scenarios. In gesture recognition task, our CrossFi achieves an accuracy of 98.17% in in-domain scenario, 91.72% in one-shot cross-domain scenario, 64.81% in zero-shot cross-domain scenario, and 84.75% in one-shot new-class scenario. The code for our model is publicly available at https://***/RS2002/CrossFi. © 2014 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

A Secure and Efficient Privacy data Aggregation Mechanism 18th

A Secure and Efficient Privacy Data Aggregation Mechanism

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Ma, Wenshuo Liu, Xinru Yu, Kan Luo, Chuanwen Wang, Guopeng Liu, Xiaowu School of Artificial Intelligence and Big Data Zibo Vocational Institute Zibo China Weifang Engineering Vocational College Weifang China School of Computer Science and Engineering Macau University of Science and Technology Taipa China The Key Laboratory of Universal Wireless Communications Ministry of Education Beijing University of Posts and Telecommunications Beijing China School of Information Science and Technology Beijing Forestry University Beijing China School of Computer Science Qufu Normal University Rizhao China Zhejiang Ocean University Zhoushan China The Open University of China Beijing China

ISBN: (纸本)9783031714665

data aggregation (DA) plays an important role in conserving the limited resources and extending the network lifetime of Wireless Sensor Networks (WSNs). Privacy preservation has garnered considerable attention and is considered one of the most viable schemes to address issues such as communication eavesdropping, information leakage, and unauthorized access in WSNs employing DA. In this paper, we propose an improved Secure Privacy-preserving data Aggregation (iSECPDA) mechanism. It dynamically selects cluster heads through an enhanced Stable Election Protocol (SEP), which considers the residual energy of sensor nodes to enhance network lifetime. In our proposed SEPPDA, we integrate interference information into the sensing data and ensure data transmission privacy through a proposed slicing mechanism. Theoretical analysis and simulation experiments demonstrate that iSECPDA exhibits significant performance improvements in terms of communication overhead and privacy preservation levels. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： data aggregation

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：