检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Qiquan Wickramasinghe, Buddhi Ambikairajah, Eliathamby Sethu, Vidhyasaharan Li, Haizhou School of Electrical Engineering and Telecommunications The University of New South Wales Sydney2052 Australia School of Electrical and Computer Engineering Purdue University West LafayetteIN United States Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen518172 China Shenzhen Research Institute of Big Data Shenzhen51872 China

Hand-crafted features, such as Mel-filterbanks, have traditionally been the choice for many audio processing applications. Recently, there has been a growing interest in learnable front-ends that extract representations directly from the raw audio waveform. However, both hand-crafted filterbanks and current learnable front-ends lead to fixed computation graphs at inference time, failing to dynamically adapt to varying acoustic environments, a key feature of human auditory systems. To this end, we explore the question of whether audio front-ends should be adaptive by comparing the Ada-FE front-end (a recently developed adaptive front-end that employs a neural adaptive feedback controller to dynamically adjust the Q-factors of its spectral decomposition filters) to established learnable front-ends. Specifically, we systematically investigate learnable front-ends and Ada-FE across two commonly used back-end backbones and a wide range of audio benchmarks including speech, sound event, and music. The comprehensive results show that our Ada-FE outperforms advanced learnable front-ends, and more importantly, it exhibits impressive stability or robustness on test samples over various training epochs. Copyright © 2025, The Authors. All rights reserved.

关键词： Gabor filters

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

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

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

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

Homophily Induced Contrastive Attributed Graph Clustering

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Chen, Man-Sheng Lai, Pei-Yuan Liao, De-Zhang Wang, Chang-Dong Lai, Jian-Huang Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Guangxi Zhuang Autonomous Region Information Center Guangxi Key Laboratory of Digital Infrastructure Nanning China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China South China Technology Commercialization Center Guangzhou China Guangdong Key Laboratory of Information Security Technology Guangzhou China

Attributed graph clustering, aiming to discover the underlying graph structure and partition the graph nodes into several disjoint categories, is a basic task in graph data analysis. Although recent efforts over graph contrastive clustering have achieved decent performances, most of them get accustomed to construct the positive neighbor set by the generated pseudo clustering information, directly ignoring the ready-made neighbor nodes and the underlying semantics of edges in a graph. How to well deal with the graph neighbor-specific information to facilitate the performance of graph contrastive clustering is still a challenging problem. Therefore, in this work, we propose a novel Homophily Induced Contrastive Attributed Graph Clustering (HomoCAGC) method, where the power of homophily is exploited in facilitating the performance of contrastive attributed graph clustering, while the pseudo homophily in a graph is also explored and distinguished. Especially, the node feature as reliable information guidance is used to compute the underlying feature-oriented pair-wise node similarity, based on which the positive node pairs in contrastive regularizer are adjusted for better node representation characterization. According to the refined node representations, a triplet self-supervised clustering objective is well-designed to ensure the output embedding is cluster-oriented, and suitable for the downstream clustering task. Extensive experiments on seven benchmarks are conducted to demonstrate the effectiveness of HomoCAGC. © 1991-2012 IEEE.

关键词： Attributed graph clustering contrastive learning graph homophily self-supervised clustering

来源：评论

学校读者我要写书评

暂无评论

DDNet: Deformable Convolution and Dense FPN for Surface Defect Detection in Recycled Books

DDNet: Deformable Convolution and Dense FPN for Surface Defe...

引用

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

作者： Jun Yu WenJian Wang School of Computer and Information Technology (School of Big Data) Shanxi University Taiyuan China Taihang Laboratory In Shanxi Province (Advanced Computing Laboratory In Shanxi Province) Taiyuan China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Taiyuan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Recycled and recirculated books, such as ancient texts and reused textbooks, hold significant value in the secondhand goods market, with their worth largely dependent on surface preservation. However, accurately assessing surface defects is challenging due to the wide variations in shape, size, and the often imprecise detection of defects. To address these issues, we propose DDNet, an innovative detection model designed to enhance defect localization and classification. DDNet introduces a surface defect feature extraction module based on a deformable convolution operator (DC) and a densely connected FPN module (DFPN). The DC module dynamically adjusts the convolution grid to better align with object contours, capturing subtle shape variations and improving boundary delineation and prediction accuracy. Meanwhile, DFPN leverages dense skip connections to enhance feature fusion, constructing a hierarchical structure that generates multi-resolution, high-fidelity feature maps, thus effectively detecting defects of various sizes. In addition to the model, we present a comprehensive dataset specifically curated for surface defect detection in recycled and recirculated books. This dataset encompasses a diverse range of defect types, shapes, and sizes, making it ideal for evaluating the robustness and effectiveness of defect detection models. Through extensive evaluations, DDNet achieves precise localization and classification of surface defects, recording a mAP value of 46.7% on our proprietary dataset—an improvement of 14.2% over the baseline model—demonstrating its superior detection capabilities.

关键词： Location awareness Accuracy Convolution Shape Semisupervised learning Feature extraction Robustness Speech processing Surface treatment Defect detection

来源：评论

学校读者我要写书评

暂无评论

GAML: Geometry-Aware Mutual Learning for polyp segmentation

引用

Biomedical Signal Processing and Control 2025年 108卷

作者： Wang, Kun Lu, Yuting Liu, Jin Zhang, Xiaohong School of Computer and Information Anhui Polytechnic University Wuhu241000 China Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education Chongqing University Chongqing400044 China School of Big Data and Software Engineering Chongqing University Chongqing401331 China

Accurate and automatic polyp segmentation plays a pivotal role in early colorectal cancer diagnosis. However, this task remains challenging due to (i) the diverse sizes and irregular shapes of colonic polyps, and (ii) the ambiguity in polyp boundaries with the surrounding mucosa. To overcome these challenges, we propose a novel and effective Geometry-Aware Mutual Learning (GAML) for precise polyp segmentation, incorporating the following steps. First, we design a region feature and boundary-wise extractor to mine the internal and external geometric features of the target. Secondly, we introduce a geometry-aware context aggregation module (GACA) to learn long-range dependencies between pixels in the external structure region and pixels within the object. Thirdly, we present a geometry-aware graph reasoning module (GAGR) that enhances and propagates features across different domains. This is accomplished by utilizing region and boundary features as nodes in the graph, leading to accurate segmentation along the boundaries. Finally, the network incorporates latent representations of internal and external geometric structures and is adaptively trained to recognize and segment polyp lesions. Experimental results on four benchmark datasets (e.g., Kvasir-SEG, CVC-ClinicDB, BKAI, and Kvasir-Sessile) demonstrate that our method outperforms current state-of-the-art methods regarding various evaluation metrics. The source code is available at https://***/DLWK/GAML. © 2025 Elsevier Ltd

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Medical Image Segmentation Based on 3d Pdc with Swin Transformer

SSRN

引用

SSRN 2025年

作者： Fan, Lin Ding, Xiaojia Wang, Zhongmin Wang, Hai Zhang, Rong School of Computer Science and Technology Xi’an University of Posts and Telecommunications Shaanxi Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi’an710121 China Xi’an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi’an710121 China The School of Information Science and Technology Northwest University Shaanxi Xi’an710121 China

3D medical image segmentation is vital for disease diagnosis and effective treatment strategies. Despite the advancements in Convolutional Neural Networks (CNN), their fixed receptive fields constrain global context modeling, leading to suboptimal performance, particularly with complex shapes and multi-scale variations. Transformer enhances the global modeling capability through self-attention mechanism. However, challenges persist in capturing fine-grained local features and extracting edge features. To overcome these issues, In this study, a dual-path encoder is proposed, which consists of a 3D PDC and a Swin Transformer and is combined with a CNN for the decoder. The 3D PDC module extracts local features by calculating the differences between neighboring pixels. To improve the ability of capturing edge structures, three 3D PDC variants (3D CPDC, 3D APDC, and 3D RPDC) are proposed to optimize the processing ability of complex edges, multi-directional edges, and multi-scale structures, respectively. After performance evaluation, the selected CARV combinations (3D CPDC, 3D APDC, 3D RPDC, and 3D ordinary convolution) achieve a compromise between high segmentation accuracy and low computational cost. The Swin Transformer encoder captures global context using a hierarchical shift-window mechanism, while the CNN decoder fuses features progressively to produce precise pixel-level segmentation. The proposed method exceeds the performance of existing state-of-the-art techniques, as shown by experiments conducted on the BTCV, FLARE21, and AMOS22 datasets. © 2025, The Authors. All rights reserved.

关键词： Image segmentation

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

Dual Encoders for Diffusion-based Image Inpainting

Dual Encoders for Diffusion-based Image Inpainting

引用

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

作者： Dezhi Zheng Kaijun Deng Jinbao Wang Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Current diffusion-based inpainting models struggle to preserve unmasked regions or generate highly coherent content. Additionally, it is hard for them to generate meaningful content for 3D inpainting. To tackle these challenges, we design a plug-and-play branch that runs through the entire generation process to enhance existing models. Specifically, we utilize dual encoders - a Convolutional Neural Network (CNN) encoder and the pre-trained Variational AutoEncoder (VAE) encoder, to encode masked images. The latent code and the feature map from the dual encoders are fed to diffusion models simultaneously. In addition, we apply Zero-padded initialization to solve the problem of mode collapse caused by this branch. Experiments on BrushBench and EditBench demonstrate that models with our plug-and-play branch can improve the coherence of inpainting, and our model achieves new state-of-the-art results.

关键词： Visualization Three-dimensional displays Codes Autoencoders Coherence Signal processing Diffusion models Decoding Convolutional neural networks Speech processing

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Malicious Web Request Detection based on Transformer and Contrastive Learning

引用

IEEE Transactions on Network and Service Management 2025年

作者： He, Shiming Zhang, Ying Liang, Diqing Sharma, Pradip Kumar Changsha University of Science and Technology School of Computer Science and Technology Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha410114 China University of Aberdeen Department of Computing Science AberdeenAB24 3UE United Kingdom

The World Wide Web (Web) is a crucial part of the Internet. Web attacks are becoming more and more serious and complex. Malicious Web request detection aims to rapidly and accurately identify abnormal attacks on the network. Deep learning is being applied to malicious Web request detection, resulting in high detection performance. However, most deep learning-based methods are supervised and ignore special characters, which are hard to detect unknown malicious Web requests. The labels of Web request are fewer and Web request data is insufficient. Therefore, we propose an unsupervised malicious Web request detection based on transformer and contrastive learning (UTCDetector). UTCDetector exploits preprocessing and 2-gram word segmentationto preserve special characters, extracts semantic feature by Transformer, and leverages hypersphere loss function and contrastive learning to handle insufficient Web data without abnormal label. Since the public Web request datasets (CSIC 2010, CSIC TORPEDA 2012, and ECML/PKDD 2007) were created before 2012, we collected Web requests from a university Web application server in 2023 to build a private dataset named School 2023. This dataset contains more modern and complex attacks. The experimental results on the four datasets demonstrate that our method achieves a higher F1-score than other existing methods and ablation variants. © 2004-2012 IEEE.

关键词： Contrastive 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：