检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Tan, Zihan Wan, Guancheng Huang, Wenke Ye, Mang National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan University Wuhan China Taikang Center for Life and Medical Sciences Wuhan University Wuhan China

Personalized Federated Graph Learning (pFGL) facilitates the decentralized training of Graph Neural networks (GNNs) without compromising privacy while accommodating personalized requirements for non-IID participants. In cross-domain scenarios, structural heterogeneity poses significant challenges for pFGL. Nevertheless, previous pFGL methods incorrectly share non-generic knowledge globally and fail to tailor personalized solutions locally under domain structural shift. We innovatively reveal that the spectral nature of graphs can well reflect inherent domain structural shifts. Correspondingly, our method overcomes it by sharing generic spectral knowledge. Moreover, we indicate the biased message-passing schemes for graph structures and propose the personalized preference module. Combining both strategies, we propose our pFGL framework FedSSP which Shares generic Spectral knowledge while satisfying graph Preferences. Furthermore, We perform extensive experiments on cross-dataset and cross-domain settings to demonstrate the superiority of our framework. The code is available at https://***/OakleyTan/FedSSP. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Speech Enhancement by Cross- and Sub-band Processing with State Space Model

Improving Speech Enhancement by Cross- and Sub-band Processi...

引用

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

作者： Li, Jizhen Tu, Weiping Yang, Yuhong Xu, Xinmeng Zhang, Yiqun Ren, Yanzhen NERCMS School of Computer Science Hubei Luojia Laboratory Wuhan University China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China School of Cyber Science and Engineering Wuhan University China

ISBN: (纸本)9798350368741

Recently, the state space model (SSM) represented by Mamba has shown remarkable performance in long-term sequence modeling tasks, including speech enhancement. However, due to substantial differences in sub-band features, applying the same SSM to all sub-bands limits its inference capability. Additionally, when processing each time frame of the time-frequency representation, the SSM may forget certain high-frequency information of low energy, making the restoration of structure in the high-frequency bands challenging. For this reason, we propose Cross- and Sub-band Mamba (CSMamba). To assist the SSM in handling different sub-band features flexibly, we propose a band split block that splits the full-band into four sub-bands with different widths based on their information similarity. We then allocate independent weights to each subband, thereby reducing the inference burden on the SSM. Furthermore, to mitigate the forgetting of low-energy information in the high-frequency bands by the SSM, we introduce a spectrum restoration block that enhances the representation of the cross-band features from multiple perspectives. Experimental results on the DNS Challenge 2021 dataset demonstrate that CSMamba outperforms several state-of-the-art (SOTA) speech enhancement methods in three objective evaluation metrics with fewer parameters. © 2025 IEEE.

关键词： band split spectrum restoration speech enhancement state space model

来源：评论

学校读者我要写书评

暂无评论

HAPG-SAQAM: Human Auditory Perception Guided Spatial Audio Quality Assessment Metric

HAPG-SAQAM: Human Auditory Perception Guided Spatial Audio Q...

引用

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

作者： Zheng, Yuanming Yao, Jiaxuan Deng, Xiangyu Yang, Yuhong Liao, Ruiqi Tu, Weiping Lin, Cedar National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan China Guangdong OPPO Mobile Telecommunications Corp. Guangdong China

ISBN: (纸本)9798350368741

Spatial audio quality evaluation is essential for applications like virtual and augmented reality, where accurate sound reproduction enhances user immersion. While subjective listening tests are the gold standard, they are costly and time-consuming. To address this, we propose HAPG-SAQAM, an objective metric for assessing timbre quality, spatial quality, and overall quality of binaural audio, guided by human auditory perception. Our contributions include: (1) the Multi-scale Auditory Guided Feature Extraction (MAGFE) module, incorporating gammatone frequency cepstral coefficients for better alignment with human perception;(2) Perceptual Weighted Loss (PWL), optimizing the weighting of timbre quality (TQ) and spatial quality (SQ) loss based on subjective test data;and (3) data augmentation techniques to enhance robustness by amplifying perceptual distortions. Experimental results show HAPG-SAQAM improves correlation with subjective scores by 10%, with ablation studies confirming the contributions of its components to enhanced spatial and overall audio quality. © 2025 IEEE.

关键词： auditory perception spatial audio Speech and audio quality assessment subjective experiment timbre quality

来源：评论

学校读者我要写书评

暂无评论

Predicting the Unseen: A Novel Dataset for Hidden Intention Localization in Pre-abnormal Analysis 24

Predicting the Unseen: A Novel Dataset for Hidden Intention ...

引用

32nd ACM International Conference on multimedia, MM 2024

作者： Qi, Zehao Zhang, Ruixu Hu, Xinyi Liu, Wenxuan Wang, Zheng National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan China School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China

ISBN: (纸本)9798400706868

Our paper introduces a novel video dataset specifically for Temporal Intention Localization (TIL), aimed at identifying hidden abnormal intention in densely populated and complex environments. Traditional Temporal Action Localization (TAL) frameworks, focusing on overt actions within constrained temporal intervals, often miss subtle pre-abnormal actions that unfold over extended periods. Our dataset comprises 228 videos with 5790 clips, each annotated to capture fine-grained actions within ambiguous temporal boundaries using the Joint-Linear-Assignment methodology. This approach enables detailed analysis of the evolution of abnormal intention over time. To detect subtle, hidden intention, we developed the Intention-Action Fusion module, an creative approach integrating dynamic feature fusion across 11 behavioral subcategories, significantly enhancing the model's ability to discern nuanced intention. This enhancement has led to performance improvements of up to 139% in specific scenarios, dramatically boosting the model's sensitivity and interpretability, crucial for advancing proactive surveillance systems. By pushing the boundaries of technology, our dataset and methodologies foster proactive surveillance systems capable of preemptively identifying potential threats from nuanced behavioral patterns, encouraging further exploration into the complexities of intention beyond observable actions. The dataset is available at https://***/Zzz99999/Hidden-Abnormal-Intention. © 2024 ACM.

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

Freevc: Towards High-Quality Text-Free One-Shot Voice Conversion 48

Freevc: Towards High-Quality Text-Free One-Shot Voice Conver...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Li, Jingyi Tu, Weiping Xiao, Li Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science Wuhan430072 China Hubei Luojia Laboratory China Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan430072 China

ISBN: (纸本)9781728163277

Voice conversion (VC) can be achieved by first extracting source content information and target speaker information, and then reconstructing waveform with these information. However, current approaches normally either extract dirty content information with speaker information leaked in, or demand a large amount of annotated data for training. Besides, the quality of reconstructed waveform can be degraded by the mismatch between conversion model and vocoder. In this paper, we adopt the end-to-end framework of VITS for high-quality waveform reconstruction, and propose strategies for clean content information extraction without text annotation. We disentangle content information by imposing an information bottleneck to WavLM features, and propose the spectrogram-resize based data augmentation to improve the purity of extracted content information. Experimental results show that the proposed method outperforms the latest VC models trained with annotated data and has greater robustness. © 2023 IEEE.

关键词： data augmentation information bottleneck self-supervised learning voice conversion

来源：评论

学校读者我要写书评

暂无评论

A Theory of Transfer-Based Black-Box Attacks: Explanation and Implications 37

A Theory of Transfer-Based Black-Box Attacks: Explanation an...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Chen, Yanbo Liu, Weiwei School of Computer Science Wuhan University National Engineering Research Center for Multimedia Software Wuhan University Institute of Artificial Intelligence Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University

ISBN: (纸本)9781713899921

Transfer-based attacks [1] are a practical method of black-box adversarial attacks in which the attacker aims to craft adversarial examples from a source model that is transferable to the target model. Many empirical works [2-6] have tried to explain the transferability of adversarial examples from different angles. However, these works only provide ad hoc explanations without quantitative analyses. The theory behind transfer-based attacks remains a mystery. This paper studies transfer-based attacks under a unified theoretical framework. We propose an explanatory model, called the manifold attack model, that formalizes popular beliefs and explains the existing empirical results. Our model explains why adversarial examples are transferable even when the source model is inaccurate as observed in Papernot et al. [7]. Moreover, our model implies that the existence of transferable adversarial examples depends on the "curvature" of the data manifold, which further explains why the success rates of transfer-based attacks are hard to improve. We also discuss our model's expressive power and applicability. © 2023 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adversarial Self-Training Improves Robustness and Generalization for Gradual Domain Adaptation 37

Adversarial Self-Training Improves Robustness and Generaliza...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Shi, Lianghe Liu, Weiwei School of Computer Science Wuhan University National Engineering Research Center for Multimedia Software Wuhan University Institute of Artificial Intelligence Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University

ISBN: (纸本)9781713899921

Gradual Domain Adaptation (GDA), in which the learner is provided with additional intermediate domains, has been theoretically and empirically studied in many contexts. Despite its vital role in security-critical scenarios, the adversarial robustness of the GDA model remains unexplored. In this paper, we adopt the effective gradual self-training method and replace vanilla self-training with adversarial self-training (AST). AST first predicts labels on the unlabeled data and then adversarially trains the model on the pseudo-labeled distribution. Intriguingly, we find that gradual AST improves not only adversarial accuracy but also clean accuracy on the target domain. We reveal that this is because adversarial training (AT) performs better than standard training when the pseudo-labels contain a portion of incorrect labels. Accordingly, we first present the generalization error bounds for gradual AST in a multiclass classification setting. We then use the optimal value of the Subset Sum Problem to bridge the standard error on a real distribution and the adversarial error on a pseudo-labeled distribution. The result indicates that AT may obtain a tighter bound than standard training on data with incorrect pseudo-labels. We further present an example of a conditional Gaussian distribution to provide more insights into why gradual AST can improve the clean accuracy for GDA. © 2023 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Deep Understanding Video Q&A System for Film Education in Acting Department

A Deep Understanding Video Q&A System for Film Education in ...

引用

2023 International Conference on Intelligent Education and Intelligent Research, IEIR 2023

作者： Wu, Zhengqian Li, Ruizhe Guo, Jiahao Wang, Zhongyuan Liang, Chao Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science China National Engineering Research Center for Multimedia Software School of Computer Science China Wuhan University School of Computer Science China

ISBN: (纸本)9798350342895

Recently, advancements in artificial intelligence technology have greatly influenced the field of education, particularly in the area of intelligent homework assistance. However, current approaches are primarily designed for procedural and logical tasks and often lack comprehension abilities. This limitation is particularly evident when it comes to multi-hop and continuous tasks. To address this challenge, the integration of Large Language Model (LLM) has significantly enhanced the capability of AI systems to handle multi-hop and highly interconnected inputs. In this study, we focus on the learning needs of students in Acting Department, specifically their study of movies and the significance of classic movie videos in their learning process. However, assessing deep comprehension of classic movies poses its own challenges. To overcome these challenges, we develop a quiz system utilizing Knowledge Graphs (KG) and LLM to facilitate a deeper understanding of classic films. The generation of video quiz pairs is achieved through the use of Automatic Speech Recognition (ASR) technology, which leverages movie subtitles for question generation. For answering these questions, we employ techniques KG and LLM to process questions and retrieve corresponding answers. The proposed method achieves good performance in Deep Video Understanding (DVU) task of NIST TRECVID, demonstrating its effectiveness. © 2023 IEEE.

关键词： Motion pictures

来源：评论

学校读者我要写书评

暂无评论

A Privacy-Preserving Scheme for Multi-Party Vertical Federated Learning

引用

ZTE communications 2024年第4期22卷 89-96页

作者： FAN Mochan ZHANG Zhipeng LI Difei ZHANG Qiming YAO Haidong School of Information&Communication Engineering University of Electronic Science and Technology of ChinaChengdu 611731China ZTE Corporation Shenzhen 518057China State Key Laboratory of Mobile Network and Mobile Multimedia Technology Shenzhen 518055China

As an important branch of federated learning,vertical federated learning(VFL)enables multiple institutions to train on the same user samples,bringing considerable industry ***,VFL needs to exchange user features among multiple institutions,which raises concerns about privacy ***,existing multi-party VFL privacy-preserving schemes suffer from issues such as poor reli-ability and high communication *** address these issues,we propose a privacy protection scheme for four institutional VFLs,named FVFL.A hierarchical framework is first introduced to support federated training among four *** also design a verifiable repli-cated secret sharing(RSS)protocol(32)-sharing and combine it with homomorphic encryption to ensure the reliability of FVFL while ensuring the privacy of features and intermediate results of the four *** theoretical analysis proves the reliability and security of the pro-posed *** experiments verify that the proposed scheme achieves excellent performance with a low communication overhead.

关键词： vertical federated learning privacy protection replicated secret sharing

来源：评论

学校读者我要写书评

暂无评论

FIMD: Fusion-Inspired Modality Distillation for Enhanced MRI Segmentation in Incomplete Multi-Modal Scenarios 24

FIMD: Fusion-Inspired Modality Distillation for Enhanced MRI...

引用

7th International Conference on Image and Graphics Processing, ICIGP 2024

作者： Yang, Rui Wang, Xiao Xu, Xin Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology China School of Computer Science and Technology Wuhan University of Science and Technology China Hubei Provincial Key Laboratory of Multimedia and Network Communication Engineering Wuhan China

ISBN: (纸本)9798400716720

Magnetic Resonance Imaging (MRI) is an invaluable tool for brain tumor segmentation. However, in clinical practice, certain modalities might be unavailable, leading to potential performance degradation in prediction tasks. According to current implementations, different modalities are treated as independent entities during the feature extraction phase, ignoring their inherent complementary nature. In this paper, inspired by knowledge distillation techniques, we introduce the Fusion-Inspired Modality Distillation (FIMD) framework. FIMD leverages the output from a fused multi-modal model as a teacher to guide the training of individual modalities. Each modality benefits from the collective knowledge of all modalities, enhancing its performance. Our FIMD method, devoid of specific architectural constraints, seamlessly integrates into existing multi-modal brain tumor segmentation frameworks. Notably, extensive experiments on BraTS2020, BraTS2018, and BraTS2015 datasets indicate that FIMD can enhance the performance of current state-of-the-art (SOTA) algorithms on Dice by an average of 0.55-1.60%. Especially in the case of missing modalities, the effectiveness of the FIMD framework in enhancing the robustness and accuracy of brain tumor segmentation is demonstrated. © 2024 ACM.

关键词： Semantic Segmentation

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：