检索结果-内蒙古大学图书馆

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

Disentangle Nighttime Lens Flares: Self-supervised Generation-based Lens Flare Removal

arXiv

引用

arXiv 2025年

作者： He, Yuwen Wang, Wei Wang, Wanyu Jiang, Kui Wu, Wanyu Computer Science and Technology 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 Harbin Institute of Technology China

Lens flares arise from light reflection and refraction within sensor arrays, whose diverse types include glow, veiling glare, reflective flare and so on. Existing methods are specialized for one specific type only, and overlook the simultaneous occurrence of multiple typed lens flares, which is common in the real-world, e.g. coexistence of glow and displacement reflections from the same light source. These co-occurring lens flares cannot be effectively resolved by the simple combination of individual flare removal methods, since these coexisting flares originates from the same light source and are generated simultaneously within the same sensor array, exhibit a complex interdependence rather than simple additive relation. To model this interdependent flares’ relationship, our Nighttime Lens Flare Formation model is the first attempt to learn the intrinsic physical relationship between flares on the imaging plane. Building on this physical model, we introduce a solution to this joint flare removal task named Self-supervised Generation-based Lens Flare Removal Network (SGLFR-Net), which is self-supervised without pre-training. Specifically, the nighttime glow is detangled in PSF Rendering Network(PSFR-Net) based on PSF Rendering Prior, while the reflective flare is modelled in Texture Prior Based Reflection Flare Removal Network (TPRR-Net). Empirical evaluations demonstrate the effectiveness of the proposed method in both joint and individual glare removal tasks. Copyright © 2025, The Authors. All rights reserved.

关键词： Glare

来源：评论

学校读者我要写书评

暂无评论

EDA: Enhanced Domain-Adversarial Training for Anatomical Landmark Detection

EDA: Enhanced Domain-Adversarial Training for Anatomical Lan...

引用

IEEE International Symposium on Biomedical Imaging

作者： Fan Yang S. Kevin Zhou School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Hefei Anhui China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou Jiangsu China Key Laboratory of Precision and Intelligent Chemistry USTC Hefei Anhui China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Manually annotating anatomical landmarks in medical images requires experienced clinicians and is a labor-intensive process. However, recent AI-assisted methods for landmark detection often rely on the training and test data originating from the same domain. This work introduces a novel unsupervised domain adaptation (UDA) framework aimed at anatomical landmark detection from a medical image, designed to bridge the gap between a source domain with labels and an unlabeled target domain. Specifically, we have developed a new Domain-Adversarial Network that incorporates skip connections to transfer and fuse high-resolution feature maps. Additionally, we proposed Dynamic Gaussian Learning, which allows the model to escape from local error regions. We carry out experiments on landmark detection for both head and chest, and the results demonstrate that our method achieves state-of-the-art performances in each experiment.

关键词： Training Measurement Adaptation models Three-dimensional displays Smoothing methods Head Kernel Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Efficient Algorithms for Minimizing the Kirchhoff Index via Adding Edges

arXiv

引用

arXiv 2025年

作者： Zhou, Xiaotian Zehmakan, Ahad N. Zhang, Zhongzhi Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Research Institute of Intelligent Complex Systems Fudan University Shanghai200433 China School of Computing Australian National University Canberra Australia

The Kirchhoff index, which is the sum of the resistance distance between every pair of nodes in a network, is a key metric for gauging network performance, where lower values signify enhanced performance. In this paper, we study the problem of minimizing the Kirchhoff index by adding edges. We first provide a greedy algorithm for solving this problem and give an analysis of its quality based on the bounds of the submodularity ratio and the curvature. Then, we introduce a gradient-based greedy algorithm as a new paradigm to solve this problem. To accelerate the computation cost, we leverage geometric properties, convex hull approximation, and approximation of the projected coordinate of each point. To further improve this algorithm, we use pre-pruning and fast update techniques, making it particularly suitable for large networks. Our proposed algorithms have nearly-linear time complexity. We provide extensive experiments on ten real networks to evaluate the quality of our algorithms. The results demonstrate that our proposed algorithms outperform the state-of-the-art methods in terms of efficiency and effectiveness. Moreover, our algorithms are scalable to large graphs with over 5 million nodes and 12 million edges. Copyright © 2025, The Authors. All rights reserved.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

A Bi-selection Method Based on Consistent Matrix for Large-Scale Datasets

引用

IEEE Transactions on Fuzzy Systems 2025年

作者： Quan, Jinsheng Qiao, Fengcai Yang, Tian Shen, Shuo Qian, Yuhua Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Institute of Interdisciplinary Studies Changsha410081 China National University of Defense Technology College of Advanced Interdisciplinary Studies Changsha410081 China Shanxi University Institute of Big Data Science and Industry Taiyuan030006 China

Biselection (feature and sample selection) enhances the efficiency and accuracy of machine learning models when handling large-scale data. Fuzzy rough sets, an uncertainty mathematics model known for its excellent interpretability, are widely used in machine learning, particularly for feature selection. While the consistent matrix has significantly improved the computational efficiency and scalability of feature selection, like most fuzzy rough set-based methods, it focuses only on feature selection and seldom incorporates sample selection. This feature-centric approach can limit classification performance, particularly in noisy and large-scale datasets where both features and samples require judicious selection. To overcome these limitations, this article explores the integration of sample selection with feature selection. First, we introduce a β-consistent granulation method to generate more accurate and concise fuzzy information granules, reducing the impact of noisy samples. In addition, a novel membership function is employed to distinguish noise while simultaneously evaluating both features and samples. As a result, a biselection algorithm with linear computation complexity is proposed to select high-quality features and samples. Numerical experiments demonstrate that, compared to eleven representative algorithms, our proposed method achieves an average accuracy improvement of 9.66% and a 933-fold increase in efficiency. © 2025 IEEE.

关键词： Biselection consistent matrix (CM) fuzzy sets granular computing rough sets

来源：评论

学校读者我要写书评

暂无评论

SVFormer: A Direct Training Spiking Transformer for Efficient Video Action Recognition 4th

SVFormer: A Direct Training Spiking Transformer for Efficie...

引用

4th International Workshop on Human Brain and Artificial Intelligence, HBAI 2024

作者： Yu, Liutao Huang, Liwei Zhou, Chenlin Zhang, Han Ma, Zhengyu Zhou, Huihui Tian, Yonghong AI Department Pengcheng Laboratory Shenzhen China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Beijing China Faculty of Computing Harbin Institute of Technology Harbin China

ISBN: (纸本)9789819640003

Video action recognition (VAR) plays crucial roles in various domains such as surveillance, healthcare, and industrial automation, making it highly significant for the society. Consequently, it has long been a research spot in the computer vision field. As artificial neural networks (ANNs) are flourishing, convolution neural networks (CNNs), including 2D-CNNs and 3D-CNNs, as well as variants of the vision transformer (ViT), have shown impressive performance on VAR. However, they usually demand huge computational cost due to the large data volume and heavy information redundancy introduced by the temporal dimension. To address this challenge, some researchers have turned to brain-inspired spiking neural networks (SNNs), such as recurrent SNNs and ANN-converted SNNs, leveraging their inherent temporal dynamics and energy efficiency. Yet, current SNNs for VAR also encounter limitations, such as nontrivial input preprocessing, intricate network construction/training, and the need for repetitive processing of the same video clip, hindering their practical deployment. In this study, we innovatively propose the directly trained SVFormer (Spiking Video transFormer) for VAR. SVFormer integrates local feature extraction, global self-attention, and the intrinsic dynamics, sparsity, and spike-driven nature of SNNs, to efficiently and effectively extract spatio-temporal features. We evaluate SVFormer on two RGB datasets (UCF101, NTU-RGBD60) and one neuromorphic dataset (DVS128-Gesture), demonstrating comparable performance to the mainstream models in a more efficient way. Notably, SVFormer achieves a top-1 accuracy of 84.03% with ultra-low power consumption (21 mJ/video) on UCF101, which is state-of-the-art among directly trained deep SNNs, showcasing significant advantages over prior models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Rethinking attention mechanism for enhanced pedestrian attribute recognition

引用

Neurocomputing 2025年 639卷

作者： Wu, Junyi Huang, Yan Gao, Min Niu, Yuzhen Chen, Yuzhong Wu, Qiang Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fujian Fuzhou350108 China Engineering Research Center of BigData Intelligence Ministry of Education Fujian Fuzhou350108 China Australian Artificial Intelligence Institute University of Technology Sydney SydneyNSW2007 Australia Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou University Fujian Fuzhou350108 China School of Electrical and Data Engineering University of Technology Sydney SydneyNSW2007 Australia

Pedestrian Attribute Recognition (PAR) plays a crucial role in various computer vision applications, demanding precise and reliable identification of attributes from pedestrian images. Traditional PAR methods, though effective in leveraging attention mechanisms, often suffer from the lack of direct supervision on attention, leading to potential overfitting and misallocation. This paper introduces a novel and model-agnostic approach, Attention-Aware Regularization (AAR), which rethinks the attention mechanism by integrating causal reasoning to provide direct supervision of attention maps. AAR employs perturbation techniques and a unique optimization objective to assess and refine attention quality, encouraging the model to prioritize attribute-specific regions. Our method demonstrates significant improvement in PAR performance by mitigating the effects of incorrect attention and fostering a more effective attention mechanism. Experiments on standard datasets showcase the superiority of our approach over existing methods, setting a new benchmark for attention-driven PAR models. © 2025 The Authors

关键词： Perturbation techniques

来源：评论

学校读者我要写书评

暂无评论

Air Pollution Monitoring By Integrating Local and Global information in Self-Adaptive Multiscale Transform Domain

引用

IEEE Transactions on Multimedia 2025年

作者： Gu, Ke Liu, Yuchen Liu, Hongyan Liu, Bo Qiao, Junfei Lin, Weisi Zhang, Wenjun Beijing University of Technology School of Information Science and Technology Engineering Research Center of Intelligent Perception and Autonomous Control of Ministry of Education Beijing Laboratory of Smart Environmental Protection Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing Artificial Intelligence Institute Beijing100124 China Massey University School of Mathematical and Computational Sciences New Zealand Nanyang Technological University College of Computing and Data Science Singapore Shanghai Jiao Tong University Institute of Image Communication and Information Processing Shanghai China

As the deadliest form of pollution, air pollution had a prolonged severe damage to the human health and life safety of nearly 99% of the world's population. Facing to the problem that billions of tons of pollutants discharged into the air per year by industrial activities, this paper proposed a novel image-based air pollution monitor (IAPM) by incorporating local and global information in the self-adaptive multiscale transform domain, so as to achieve the timely and effective leakage detection of typical air pollutants from a single image. To be specific, this paper first developed a screen-shaped module according to two significant findings in visual neuroscience, which include the high sensitivity of human eyes to horizontal and vertical stimuli and the center-surround inhibition, by designing and fusing the square module, horizontal strip module and vertical strip module parallelly for simulating the behaviour of human eyes to extract local features. Second, the learnable weights and proportional mapping were applied to incorporate the screen-shaped module and lightweight vision transformer as backbone, towards more richly exploiting and fusing local and global information just as the way a brain perceives external stimuli. Third, a new self-adaptive multiscale transform domain method was devised based on two motivations from the visual characteristics of multiscale perception and the brain characteristics of self-adaptive domain transform to modify the backbone by using the operations of pooling and pointwise convolution. Extensive experiments implemented on the datasets of carbon particulate matters and ethylene leakage confirmed the superior monitoring performance of the proposed IAPM model beyond the state-of-the-art (SOTA) peers by an accuracy gain of about 4%. Furthermore, the proposed IAPM model only required 0.089 GFLOPs and 0.15 million model parameters, remarkably outperforming SOTA competitors in computational efficiency and storage resources. © 1999-2

关键词： information leakage

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

CPAL: Cross-prompting Adapter with LoRAs for RGB+X Semantic Segmentation

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Liu, Ye Wu, Pengfei Wang, Miaohui Liu, Jun Nanjing University of Posts and Telecommunications School of Automation and Artificial Intelligence Nanjing China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China Lancaster University School of Computing and Communications Lancaster United Kingdom

As sensor technology evolves, RGB+X systems combine traditional RGB cameras with another type of auxiliary sensor, which enhances perception capabilities and provides richer information for important tasks such as semantic segmentation. However, acquiring massive RGB+X data is difficult due to the need for specific acquisition equipment. Therefore, traditional RGB+X segmentation methods often perform pretraining on relatively abundant RGB data. However, these methods lack corresponding mechanisms to fully exploit the pretrained model, and the scope of the pretraining RGB dataset remains limited. Recent works have employed prompt learning to tap into the potential of pretrained foundation models, but these methods adopt a unidirectional prompting approach i.e., using X or RGB+X modality to prompt pretrained foundation models in RGB modality, neglecting the potential in non-RGB modalities. In this paper, we are dedicated to developing the potential of pretrained foundation models in both RGB and non-RGB modalities simultaneously, which is non-trivial due to the semantic gap between modalities. Specifically, we present the CPAL (Cross-prompting Adapter with LoRAs), a framework that features a novel bi-directional adapter to simultaneously fully exploit the complementarity and bridging the semantic gap between modalities. Additionally, CPAL introduces low-rank adaption (LoRA) to fine-tune the foundation model of each modal. With the support of these elements, we have successfully unleashed the potential of RGB foundation models in both RGB and non-RGB modalities simultaneously. Our method achieves state-of-the-art (SOTA) performance on five multi-modal benchmarks, including RGB+Depth, RGB+Thermal, RGB+Event, and a multi-modal video object segmentation benchmark, as well as four multi-modal salient object detection benchmarks. The code and results are available at: https://***/abelny56/CPAL. © 1991-2012 IEEE.

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：