检索结果-内蒙古大学图书馆

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 797-811页

作者： Ruijie Tao Xinyuan Qian Yidi Jiang Junjie Li Jiadong Wang Haizhou Li Department of Electrical and Computer Engineering National University of Singapore Singapore Department of Computer Science and Technology University of Science and Technology Beijing Beijing China Chinese University of Hong Kong Shenzhen China Guangdong Provincial Key Laboratory of Big Data Computing Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China University of Bremen Bremen Germany

Audio-visual target speaker extraction (AV-TSE) aims to extract the specific person's speech from the audio mixture given auxiliary visual cues. Previous methods usually search for the target voice through speech-lip synchronization. However, this strategy mainly focuseson the existence of target speech, while ignoring the variations of the noise characteristics, i.e., interference speaker and the background noise. That may result in extracting noisy signals from the incorrect sound source in challenging acoustic situations. To this end, we propose a novel selective auditory attention mechanism, which can suppress interference speakers and non-speech signals to avoid incorrect speaker extraction. By estimating and utilizing the undesired noisy signal through this mechanism, we design an AV-TSE framework named Subtraction-and-ExtrAction network (SEANet) to suppress the noisy signals. We conduct abundant experiments by re-implementing three popular AV-TSE methods as the baselines and involving nine metrics for evaluation. The experimental results show that our proposed SEANet achieves state-of-the-art results and performs well for all five datasets.

关键词： Noise measurement Lips Visualization Synchronization Noise Correlation data mining Speech processing Interference Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Fence Theorem: Towards Dual-Objective Semantic-Structure Isolation in Preprocessing Phase for 3D Anomaly Detection

arXiv

引用

arXiv 2025年

作者： Liang, Hanzhe Zhou, Jie Chen, Xuanxin Dai, Tao Wang, Jinbao Gao, Can College of Computer Science and Software Engineering Shenzhen University China Shenzhen Audencia Financial Technology Institute Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Faculty of Education Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

3D anomaly detection (AD) is prominent but difficult due to lacking a unified theoretical foundation for preprocessing design. We establish the Fence Theorem, formalizing preprocessing as a dual-objective semantic isolator: (1) mitigating cross-semantic interference to the greatest extent feasible and (2) confining anomaly judgements to aligned semantic spaces wherever viable, thereby establishing intra-semantic comparability. Any preprocessing approach achieves this goal through a two-stage process of Semantic-Division and Spatial-Constraints stage. Through systematic deconstruction, we theoretically and experimentally subsume existing preprocessing methods under this theorem via tripartite evidence: qualitative analyses, quantitative studies, and mathematical proofs. Guided by the Fence Theorem, we implement Patch3D, consisting of Patch-Cutting and Patch-Matching modules, to segment semantic spaces and consolidate similar ones while independently modeling normal features within each space. Experiments on Anomaly-ShapeNet and Real3D-AD with different settings demonstrate that progressively finer-grained semantic alignment in preprocessing directly enhances point-level AD accuracy, providing inverse validation of the theorem’s causal logic. Copyright © 2025, The Authors. All rights reserved.

关键词： Fences

来源：评论

学校读者我要写书评

暂无评论

Towards high-throughput and low-latency billion-scale vector search via CPU/GPU collaborative filtering and re-ranking 25

Towards high-throughput and low-latency billion-scale vector...

引用

Proceedings of the 23rd USENIX Conference on File and Storage Technologies

作者： Bing Tian Haikun Liu Yuhang Tang Shihai Xiao Zhuohui Duan Xiaofei Liao Hai Jin Xuecang Zhang Junhua Zhu Yu Zhang National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Huawei Technologies Co. Ltd Towards high-throughput and low-latency billion-scale vector search via CPU/GPU collaborative filtering and re-ranking

ISBN: (纸本)9781939133458

Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure. Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services. None of modern ANNS systems can address these issues simultaneously. In this paper, we present Fusion-ANNS, a high-throughput, low-latency, cost-efficient, and high-accuracy ANNS system for billion-scale datasets using SSDs and only one entry-level GPU. The key idea of Fusion-ANNS lies in CPU/GPU collaborative filtering and reranking mechanisms, which significantly reduce I/O operations across CPUs, GPU, and SSDs to break through the I/O performance bottleneck. Specifically, we propose three novel designs: (1) multi-tiered indexing to avoid data swapping between CPUs and GPU, (2) heuristic re-ranking to eliminate unnecessary I/Os and computations while guaranteeing high accuracy, and (3) redundant-aware I/O deduplication to further improve I/O efficiency. We implement FusionANNS and compare it with the state-of-the-art SSD-based ANNS system-SPANN and GPU-accelerated in-memory ANNS system-RUMMY. Experimental results show that FusionANNS achieves 1) 9.4-13.1× higher query per second (QPS) and 5.7-8.8× higher cost efficiency compared with SPANN; 2) and 2-4.9× higher QPS and 2.3-6.8× higher cost efficiency compared with RUMMY, while guaranteeing low latency and high accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The role of testosterone in modulating positive and negative empathy in social interactions

引用

Neuropharmacology 2025年 274卷 110465页

作者： Zhuo, Shiwei Zhang, Yinhua Lin, Chennan Wu, Wen Peng, Weiwei School of Psychology Shenzhen University Guangdong Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen China Department of Rehabilitation Zhujiang Hospital Southern Medical University Guangdong Guangzhou China

Empathy encompasses both negative (e.g., distress) and positive (e.g., shared joy) dimensions, yet the effects of testosterone on positive empathy and its modulation of intrinsic neural dynamics remain underexplored. This double-blind, placebo-controlled study examined how testosterone influences neural sensitivity to empathy within social inclusion and exclusion contexts, as well as its impact on resting-state EEG microstates—millisecond-scale transient patterns of brain activity. Healthy male participants received either testosterone or placebo before completing resting-state EEG recordings and an empathy task featuring social scenarios. While self-reported empathy ratings remained unchanged, testosterone amplified neurophysiological responses: it enhanced anterior N2 amplitude (250–310 ms), associated with negative empathy toward social exclusion, and increased posterior α-event-related desynchronization (8.28–10 Hz;1226–1901 ms), linked to positive empathy during social inclusion. These findings suggest that testosterone enhances neural responsiveness to both threatening and affiliative social cues, reinforcing its role in adaptive social vigilance. Resting-state EEG microstate analysis further revealed that testosterone prolonged the temporal dominance of microstate E—a centro-parietal activity pattern associated with interoceptive awareness and emotional processing. Notably, these microstate E changes predicted increased emotional empathy across both positive and negative contexts. Together, our findings suggest that testosterone indirectly enhances empathy-related responsiveness by amplifying baseline interoceptive sensitivity to socially salient stimuli. These dual effects—enhanced intrinsic interoceptive processing and heightened neural reactivity to social cues—position testosterone as a key neuromodulator of context-adaptive social perception. © 2025 Elsevier Ltd

关键词： Empathy Event-related desynchronization Event-related potentials Microstate analysis Testosterone

来源：评论

学校读者我要写书评

暂无评论

UICopilot: Automating UI Synthesis via Hierarchical Code Generation from Webpage Designs 25

UICopilot: Automating UI Synthesis via Hierarchical Code Gen...

引用

Proceedings of the ACM on Web Conference 2025

作者： Yi Gui Yao Wan Zhen Li Zhongyi Zhang Dongping Chen Hongyu Zhang Yi Su Bohua Chen Xing Zhou Wenbin Jiang Xiangliang Zhang National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Huazhong University of Science and Technology Wuhan China Chongqing University Chongqing China Hubei University of Automotive Technology Shiyan China Rabbitpre AI Shenzhen China University of Notre Dame Notre Dame USA

ISBN: (纸本)9798400712746

Automating the synthesis of User Interfaces (UIs) plays a crucial role in enhancing productivity and accelerating the development lifecycle, reducing both development time and manual effort. Recently, the rapid development of Multimodal Large Language Models (MLLMs) has made it possible to generate front-end Hypertext Markup Language (HTML) code directly from webpage designs. However, real-world webpages encompass not only a diverse array of HTML tags but also complex stylesheets, resulting in significantly lengthy code. The lengthy code poses challenges for the performance and efficiency of MLLMs, especially in capturing the structural information of UI designs. To address these challenges, this paper proposes UICopilot, a novel approach to automating UI synthesis via hierarchical code generation from webpage designs. To validate the effectiveness of UICopilot, we conduct experiments on a real-world dataset, i.e., WebCode2M. Experimental results demonstrate that UICopilot significantly outperforms existing baselines in both automatic evaluation metrics and human evaluations. Specifically, statistical analysis reveals that the majority of human annotators prefer the webpages generated by UICopilot over those produced by GPT-4V.

关键词： UI automation

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient and Privacy-preserving Edge Intelligence for 6G-Empowered Intelligent Transportation systems

引用

IEEE Network 2025年

作者： Zhu, Chenlu Fan, Xiaoxuan Deng, Xianjun Xiao, Ziheng Guo, Tingting Liu, Shenghao Sun, Jiaqi Park, Jong Hyuk Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Wuhan Kedao Geographic Information Engineering Co. Wuhan China Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of

6G-empowered Intelligent Transportation systems (ITS) generate large amounts of data through millions of devices and sensors at the terminal and network edge. Edge intelligence advances the frontier of data-driven artificial intelligence (AI) to the network edge, which enables AI applications to better utilize edge data. Broader connectivity, higher device density, and stronger data exchange present challenges for reliable device communication and privacy data protection in 6G-empowered ITS. To address these challenges, this paper proposes an energy-efficient and privacy-preserving edge intelligence framework named EP-EI. EP-EI deploys a deep reinforcement learning-based cluster head selection model at the edge to ensure energy-efficient communication for terminal devices. Meanwhile, EP-EI designs a privacy-aware hierarchical computing framework for terminal-edge-cloud to prevent privacy leakage. Furthermore, the application scenarios, challenges, and future directions of EP-EI are discussed. Finally, simulation experiments in a specific intelligent transportation case study demonstrate that EP-EI can provide energy-efficient and privacy-protecting services. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Dual Graph Inference Network for Weakly Supervised Semantic Segmentation

引用

IEEE Transactions on Circuits and systems for Video technology 2025年

作者： Zhang, Jia Peng, Bo Wu, Xi Southwest Jiaotong University School of Computing and Artificial Intelligence Sichuan Chengdu611756 China Southwest Jiaotong University National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu611756 China Chengdu University of Information Technology School of Computer Science Sichuan Chengdu610225 China

Establishing global contextual relationships between objects is crucial for weakly supervised semantic segmentation (WSSS) tasks that lack pixel-level labels. Limited by the efficiency of convolutional operations in capturing long-range dependencies with a limited receptive field and to bridge the gap between image-level annotations and pixel-level labels, we propose a Dual Graph Reasoning Mapping (DGRM) module. When integrated into a convolutional network, it conducts contextual graph reasoning on both spatial and interaction spaces of visual features. The first component of this graph reasoning module involves incorporating commonsense knowledge extracted from an external knowledge base into visual features to promote global contextual reasoning for visual graphs. The second component focuses on reasoning in the projected interaction space, utilizing abstracted object class attributes from high-level visual features to establish dependencies among channels in a potential low-dimensional space. Moreover, to capture correspondences at different semantic levels, we model the feature maps in a pyramid-like structure for graph reasoning at various levels. Extensive experiments on popular datasets, such as PASCAL VOC 2012 and MS COCO 2014, demonstrate the superiority of our approach. Our code is provided at https://***/JIAZHANG666/DGRM. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Vision-Amplified Semantic Entropy for Hallucination Detection in Medical Visual Question Answering

arXiv

引用

arXiv 2025年

作者： Liao, Zehui Hu, Shishuai Zou, Ke Fu, Huazhu Zhen, Liangli Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Institute of High Performance Computing Agency for Science Technology and Research Singapore138632 Singapore National University of Singapore Singapore119077 Singapore

Multimodal large language models (MLLMs) have demonstrated significant potential in medical Visual Question Answering (VQA). Yet, they remain prone to hallucinations—incorrect responses that contradict input images, posing substantial risks in clinical decision-making. Detecting these hallucinations is essential for establishing trust in MLLMs among clinicians and patients, thereby enabling their real-world adoption. Current hallucination detection methods, especially semantic entropy (SE), have demonstrated promising hallucination detection capacity for LLMs. However, adapting SE to medical MLLMs by incorporating visual perturbations presents a dilemma. Weak perturbations preserve image content and ensure clinical validity, but may be overlooked by medical MLLMs, which tend to over rely on language priors. In contrast, strong perturbations can distort essential diagnostic features, compromising clinical interpretation. To address this issue, we propose Vision Amplified Semantic Entropy (VASE), which incorporates weak image transformations and amplifies the impact of visual input, to improve hallucination detection in medical VQA. We first estimate the semantic predictive distribution under weak visual transformations to preserve clinical validity, and then amplify visual influence by contrasting this distribution with that derived from a distorted image. The entropy of the resulting distribution is estimated as VASE. Experiments on two medical open-ended VQA datasets demonstrate that VASE consistently outperforms existing hallucination detection methods. Copyright © 2025, 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

Semi-Supervised Feature Selection With Multi-Scale Fuzzy Information Fusion: From Both Global and Local Perspectives

引用

IEEE Transactions on Fuzzy systems 2025年

作者： Zhou, Nan Liao, Shujiao Chen, Hongmei Ding, Weiping Lu, Yaqian Minnan Normal University School of Mathematics and Statistics Fujian Key Laboratory of Granular Computing and Applications Zhangzhou363000 China Southwest Jiaotong University School of Computing and Artificial Intelligence National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu611756 China Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China City University of Macau Faculty of Data Science 999078 China

In reality, the laborious nature of label annotation leads to the widespread existence of limited labeled data. Moreover, multi-scale data have received widespread attention due to its rich knowledge representation. However, current research on multi-scale data primarily focuses on supervised learning environments, while semi-supervised feature selection for multi-scale data with limited labels remains inadequately explored. Meanwhile, existing studies on multi-scale data often emphasize selecting optimal scales and further conducting feature selection, but this strategy may result in losing potentially valuable information from other scales. To overcome these limitations, by adopting a multi-scale fuzzy information fusion mechanism, this article proposes two new semi-supervised feature selection approaches for multi-scale data with limited labels from both global and local perspectives. Initially, by fusing fuzzy information at various scales, a label learning method is proposed to convert the decision of missing labels into a fuzzy decision of label distribution. Subsequently, label-distributed multi-scale fuzzy global and local rough sets are constructed from global and local perspectives, respectively. Based on the two models, two semi-supervised feature selection algorithms are developed based on global and local multi-scale fuzzy information fusion. Experimental results demonstrate that, compared to other advanced feature selection algorithms, the two proposed algorithms can effectively handle multi-scale data with limited labels and exhibit superior classification performance, computational efficiency and robustness. © 1993-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Triangular Stable Node Network based on Self-supervised Learning for personalized prediction

A Triangular Stable Node Network based on Self-supervised Le...

引用

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

作者： Liu, Qing Gao, Qian Fan, Jun Zhang, Zhiqiang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Qilu University of Technology Shandong Academy of Sciences Jinan250014 China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology Shandong Academy of Sciences Jinan250353 China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan250014 China China Telecom Digital Intelligence Techonology Co Ltd. No.1999 Shunhua road Shandong Jinan250101 China

ISBN: (纸本)9798350368741

In recent years, research has illuminated the potency of implicit data processing in enhancing user preferences. Nevertheless, barriers remain in breaking through the constraints of implicit information. This study aims to bridge this gap by firstly constructing a triangular stable node network model, tailored to manage implicit information with precision. Recognizing the challenge of pinpointing novel structures within large-scale graphs, we propose SLTSNN-a triangular stable node network based on self-supervised learning for personalized prediction. SLTSNN innovates by maximizing mutual information between graph-level and patch-level representations, while augmenting graph representations through extended enhanced representations. Additionally, it incorporates triangular data associations and introduces a triangular allocation attention network, which emphasizes strongly correlated preference features among similar users. Furthermore, SLTSNN employs contrastive learning to maximize mutual information between graph vectors and hidden representations, distinguishing between high-order global and local representations. The model's effectiveness in enhancing user preferences and capturing new graph structures is evidenced by its performance on hit rate and normalized discounted cumulative gain metrics across three datasets. © 2025 IEEE.

关键词： graph contrastive learning graph neural networks recommender systems self-supervised learning

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：