检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Wei Cai, Miaoxin Zhang, Tong Zhuang, Yin Li, Jun Mao, Xuerui Advanced Research Institute of Multidisciplinary Sciences Beijing Institute of Technology Beijing100081 China School of Mechatronical Engineering Beijing Institute of Technology Beijing100081 China Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing314003 China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing100081 China School of Computer Science Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences Wuhan430078 China

Recent advances in prompt learning have allowed users to interact with artificial intelligence (AI) tools in multiturn dialogue, enabling an interactive understanding of images. However, it is difficult and inefficient to deliver information in complicated remote sensing (RS) scenarios using plain language instructions alone, which would severely hinder deep comprehension of the latent content in imagery. Besides, existing prompting strategies in natural scenes are hard to apply to interpret the RS data due to significant domain differences. To address these challenges, the first visual prompting-based multi-modal large language model (MLLM) named EarthMarker is proposed in the RS domain. EarthMarker is capable of interpreting RS imagery at the image, region, and point levels by levering visual prompts (i.e., boxes and points). Specifically, a shared visual encoding method is developed to establish the spatial pattern interpretation relationships between the multi-scale representations of input images and various visual prompts. Subsequently, the mixed visual-spatial representations are associated with language instructions to construct joint prompts, enabling the interpretation of intricate content of RS imagery. Furthermore, to bridge the domain gap between natural and RS data, and effectively transfer domain-level knowledge from natural scenes to the RS domain, a cross-domain learning strategy is developed to facilitate the RS imagery understanding. In addition, to tackle the lack of RS visual prompting data, a dataset named RSVP featuring multimodal multi-granularity visual prompts instruction-following is constructed. Extensive experiments are conducted to demonstrate the competitive performance of the EarthMarker. The proposed EarthMarker represents a significant advance in multi-granularity RS imagery interpretation under the visual prompting learning framework. Our code and dataset are available at https://***/wivizhang/EarthMarker. Copyright © 2024,

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Performer: A High-Performance Global-Local Model-Augmented with Dual Network Interaction Mechanism

引用

IEEE Transactions on Cognitive and Developmental Systems 2024年

作者： Tan, Dayu Hao, Rui Hua, Linfeng Xu, Qi Su, Yansen Zheng, Chunhou Zhong, Weimin Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Institutes of Physical Science and Information Technology Hefei230601 China East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education Shanghai200237 China Dalian University of Technology School of Computer Science and Technology Dalian116024 China

In deep learning, Convolutional Neural Networks (CNNs) focus on local information through convolutional kernels, while transformers attend to global information using self-attention mechanisms. The union of these distinct approaches enables a more comprehensive extraction of image features. However, the feature map dimensions of CNN and Transformer differ, leading to dimension mismatch issues when combining these architectures. Additionally, the parameter size of the hybrid model integrating both architectures remains large, making it difficult to train. To further augmenting the interpretation of complex image patterns, we present Performer, a dual-network architecture that seamlessly combines CNNs and transformers, resulting in a novel and efficient representation learning model. In the Performer model, we innovate by devising a unique interaction methodology for CNN and transformer architectures to enhance the image feature extraction capabilities mutually. To counteract issue of dimensionality mismatch, we also introduce a refined transformer block, a advancement over the transformer block of ViT. To validate the effectiveness of Performer, we conduct extensive experiments on both classification and segmentation tasks. Performer achieve an accuracy of 83.37% on the ImageNet-200 dataset. For semantic segmentation, Performer excels on the CamVid and Hippocampus datasets. On CamVid, our model achieves a mean Intersection over Union (mIoU) of 63.27% and Pixel Accuracy of 92.11%, demonstrating superior performance in capturing fine details and handling complex scenes effectively. The code is available at https://***/hlfthh/ Performer. © 2016 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection

Exploiting Completeness and Uncertainty of Pseudo Labels for...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Chen Zhang Guorong Li Yuankai Qi Shuhui Wang Laiyun Qing Qingming Huang Ming-Hsuan Yang State Key Laboratory of Information Security Institute of Information Engineering CAS School of Cyber Security University of Chinese Academy of Sciences School of Computer Science and Technology University of Chinese Academy of Sciences Australian Institute for Machine Learning The University of Adelaide Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS University of California Merced

Weakly supervised video anomaly detection aims to identify abnormal events in videos using only video-level labels. Recently, two-stage self-training methods have achieved significant improvements by self-generating pseudo labels and self-refining anomaly scores with these labels. As the pseudo labels play a crucial role, we propose an enhancement framework by exploiting completeness and uncertainty properties for effective self-training. Specifically, we first design a multi-head classification module (each head serves as a classifier) with a diversity loss to maximize the distribution differences of predicted pseudo labels across heads. This encourages the generated pseudo labels to cover as many abnormal events as possible. We then devise an iterative uncertainty pseudo label refinement strategy, which improves not only the initial pseudo labels but also the updated ones obtained by the desired classifier in the second stage. Extensive experimental results demonstrate the proposed method performs favorably against state-of-the-art approaches on the UCF-Crime, TAD, and XD-Violence benchmark datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RobNODDI: Robust NODDI Parameter Estimation with Adaptive Sampling Under Continuous Representation 15th

RobNODDI: Robust NODDI Parameter Estimation with Adaptive S...

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： Xiao, Taohui Cheng, Jian Fan, Wenxin Yang, Jing Li, Cheng Dong, Enqing Wang, Shanshan School of Mechanical Electrical and Information Engineering Shandong University Weihai264209 China State Key Laboratory of Software Development Environment Beihang University Beijing China Key Laboratory of Data Science and Intelligent Computing Institute of International Innovation Beihang University Zhejiang Hangzhou China Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China Peng Cheng Laboratory Guangdong Shenzhen China

ISBN: (纸本)9783031869198

Neurite Orientation Dispersion and Density Imaging (NODDI) is an important imaging technology used to evaluate the microstructure of brain tissue, which is of great significance for the discovery and treatment of various neurological diseases. Current deep learning-based methods perform parameter estimation through diffusion magnetic resonance imaging (dMRI) with a small number of diffusion gradients. These methods speed up parameter estimation and improve accuracy. However, the diffusion directions used by most existing deep learning models during testing needs to be strictly consistent with the diffusion directions during training. This results in poor generalization and robustness of deep learning models in dMRI parameter estimation. In this work, we first verify that the parameter estimation performance of current mainstream methods will significantly decrease when the testing diffusion directions and the training diffusion directions are inconsistent. A robust NODDI parameter estimation method with adaptive sampling under continuous representation (RobNODDI) is proposed. Furthermore, long short-term memory (LSTM) units and fully connected layers are selected to learn continuous representation signals. To this end, we use a total of 100 subjects to conduct experiments based on the Human Connectome Project (HCP) dataset, of which 60 are used for training, 20 are used for validation, and 20 are used for testing. The test results indicate that RobNODDI improves the generalization performance and robustness of the deep learning model, enhancing the stability and flexibility of deep learning NODDI parameter estimatimation applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Fine-Grained Anomaly Detection Method Fusing Isolation Forest and Knowledge Graph Reasoning 19th

A Fine-Grained Anomaly Detection Method Fusing Isolation For...

引用

19th International Conference on Web information Systems and Applications, WISA 2022

作者： Xu, Jie Zhou, Jiantao College of Computer Science Engineering Research Center of Ecological Big Data Ministry of Education National and Local Joint Engineering Research Center of Mongolian Intelligent Information Processing Technology Inner Mongolia Cloud Computing and Service Software Engineering Laboratory Inner Mongolia Social Computing and Data Processing Key Laboratory Inner Mongolia Discipline Inspection and Supervision Big Data Key Laboratory Inner Mongolia Big Data Analysis Technology Engineering Laboratory Inner Mongolia University Hohhot China

ISBN: (纸本)9783031203084

Anomaly detection aims to find outliers data that do not conform to expected behaviors in a specific scenario, which is indispensable and critical in current safety environments related studies. However, when performing outlier detection on a large-scale multidimensional dataset, most of the traditional methods make no distinctions between classes of outliers and lack the reasoning ability and the explainability of the analysis results, which leads to the low accuracy of global outlier detection and the inability to effectively identify local outliers. In this paper, we propose a fine-grained anomaly detection method which well utilizes isolation forest and knowledge graph reasoning tactics. First, a better extracting data feature method and a more reasonable weighted strategy are used to find global outliers based on the traditional isolation forest algorithm, and then we construct a custom rule base according to the in-depth research and analysis of global abnormal data, and at last the ontology knowledge is reasoned based on such rule base to achieve the detection of local outliers. Through analysis of extensive experiment results, our method could effectively discover more abnormal data without big loss of time costs, has strong generalization, and correspondingly improves the performance for abnormal detection. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Improved S2ANet based on attention mechanism for small target detection in remote sensing images

Improved S2ANet based on attention mechanism for small targe...

引用

2021 CIE International Conference on Radar, Radar 2021

作者： Lu, Dongdong Tie, Wenjie Lei, Songlin Qiu, Xiaolan Suzhou Aerospace Information Research Institute Laboratory of Spatial Information Intelligent Processing System Suzhou China Chinese Academy of Sciences Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems Beijing China

ISBN: (纸本)9781665498142

Deep learning has achieved remarkable results in the field of target detection and recognition. For small targets in images, image pyramid can be used to fuse multi-scale features to improve detection performance. However, when test on remote sensing images, it is found that some important small goals will still be missed. Aiming at the problems of small target detection in remote sensing images, this paper proposes two S2ANet improved network variants based on the attention mechanism for synthetic aperture radar(SAR) payload and optical payload: for SAR images, CBAM(Convolutional Block Attention Module) attention is added to the backbone network to increase the attention of the feature extraction network for small targets in the channel and space dimensions;For optical images, firstly increase the CBAM channel attention and spatial attention in the backbone, secondly, the SE(Squeeze And Excitation) channel attention is added to the input features before the channel dimension fusion of the pyramid structure, then the attention-enhanced targets are fully integrated through up-sampling and horizontal splicing operations to improve the missed alarm rate and recall rate of small remote sensing targets. Finally, a comparative verification was carried out on the constructed airborne KU-band SAR data set and the optical remote sensing aircraft data set composed of some DOTA1.5 and FAIR1M data sets. The experimental results proved that the designed two variant networks can be used for small remote sensing. There have been certain improvements in the missed alarm rate, accuracy rate, and recall rate of the target. © 2021 IEEE.

关键词： Radar remote sensing Radar detection Object detection Radar imaging Optical imaging Feature extraction Adaptive optics

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Image Segmentation Using Vision Mamba and Multi-Scale Multi-Frequency Feature Fusion

arXiv

引用

arXiv 2024年

作者： Cao, Yice Liu, Chenchen Wu, Zhenhua Yao, Wenxin Xiong, Liu Chen, Jie Huang, Zhixiang The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Electronics and Information Engineering Anhui University Hefei230601 China The 38th Research Institute China Electronics Technology Group Corporation Hefei230088 China

As remote sensing imaging technology continues to advance and evolve, processing high-resolution and diversified satellite imagery to improve segmentation accuracy and enhance interpretation efficiency emerg as a pivotal area of investigation within the realm of remote sensing. Although segmentation algorithms based on CNNs and Transformers achieve significant progress in performance, balancing segmentation accuracy and computational complexity remains challenging, limiting their wide application in practical tasks. To address this, this paper introduces state space model (SSM) and proposes a novel hybrid semantic segmentation network based on vision Mamba (CVMH-UNet). This method designs a cross-scanning visual state space block (CVSSBlock) that uses cross 2D scanning (CS2D) to fully capture global information from multiple directions, while by incorporating convolutional neural network branches to overcome the constraints of Vision Mamba (VMamba) in acquiring local information, this approach facilitates a comprehensive analysis of both global and local features. Furthermore, to address the issue of limited discriminative power and the difficulty in achieving detailed fusion with direct skip connections, a multi-frequency multi-scale feature fusion block (MFMSBlock) is designed. This module introduces multi-frequency information through 2D discrete cosine transform (2D DCT) to enhance information utilization and provides additional scale local detail information through point-wise convolution branches. Finally, it aggregates multi-scale information along the channel dimension, achieving refined feature fusion. Findings from experiments conducted on renowned datasets of remote sensing imagery demonstrate that proposed CVMH-UNet achieves superior segmentation performance while maintaining low computational complexity, outperforming surpassing current leading-edge segmentation algorithms. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

SFDA-rPPG: Source-Free Domain Adaptive Remote Physiological Measurement with Spatio-Temporal Consistency

arXiv

引用

arXiv 2024年

作者： Xie, Yiping Yu, Zitong Wu, Bingjie Xie, Weicheng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Singapore

Remote Photoplethysmography (rPPG) is a non-contact method that uses facial video to predict changes in blood volume, enabling physiological metrics measurement. Traditional rPPG models often struggle with poor generalization capacity in unseen domains. Current solutions to this problem is to improve its generalization in the target domain through Domain Generalization (DG) or Domain Adaptation (DA). However, both traditional methods require access to both source domain data and target domain data, which cannot be implemented in scenarios with limited access to source data, and another issue is the privacy of accessing source domain data. In this paper, we propose the first Source-free Domain Adaptation benchmark for rPPG measurement (SFDA-rPPG), which overcomes these limitations by enabling effective domain adaptation without access to source domain data. Our framework incorporates a Three-Branch Spatio-Temporal Consistency Network (TSTC-Net) to enhance feature consistency across domains. Furthermore, we propose a new rPPG distribution alignment loss based on the Frequency-domain Wasserstein Distance (FWD), which leverages optimal transport to align power spectrum distributions across domains effectively and further enforces the alignment of the three branches. Extensive cross-domain experiments and ablation studies demonstrate the effectiveness of our proposed method in source-free domain adaptation settings. Our findings highlight the significant contribution of the proposed FWD loss for distributional alignment, providing a valuable reference for future research and applications. The source code is available at https://***/XieYiping66/SFDA-rPPG. Copyright © 2024, The Authors. All rights reserved.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

Blind Image Deconvolution Based on Adaptive Weighted L0 Gradient Prior

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2023年第4期50卷 1510页

作者： Lu, Jingjing Zhang, Jun Wang, Xinv Deng, Chengzhi Zhang, Chao Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang Institute of Technology Jiangxi Nanchang330099 China College of Science Nanchang Institute of Technology Jiangxi Nanchang330099 China

The aim of blind image deconvolution is to reconstruct a clear image from a noisy blurred image when the blur kernel is unknown. The approach for blind image deconvolution could be divided into two steps, including blur kernel estimation as well as non-blind image reconstruction. Especially, the quality of the restored image is significantly influenced by the estimation of the blur kernel. To acquire a more accurate blur kernel, it is essential to get the edge information of the image accurately. In this paper, a novel blind image deconvolution model via an adaptive weighted L0 gradient prior is proposed. Due to the incorporation of the adaptive weighted matrix, our proposed model can more effectively describe the edge information of the image so as to make the estimated blur kernel more accurate. In addition, an efficient algorithm is designed to leverage the sparsity of patch-wise minimal pixels (PMPs) in deblurring. Experimental results demonstrate the superiority of the proposed method when compared to other related blind deconvolution methods. © 2023, International Association of Engineers. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

EarthGPT-X: Enabling MLLMs to Flexibly and Comprehensively Understand Multi-Source Remote Sensing Imagery

arXiv

引用

arXiv 2025年

作者： Zhang, Wei Cai, Miaoxin Ning, Yaqian Zhang, Tong Zhuang, Yin Chen, He Li, Jun Mao, Xuerui Advanced Research Institute of Multidisciplinary Sciences Beijing Institute of Technology Beijing100081 China School of Mechatronical Engineering Beijing Institute of Technology Beijing100081 China Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing314003 China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing100081 China School of Optics and Photonics Beijing Institute of Technology Beijing100081 China School of Computer Science Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences Wuhan430078 China

Recent advances in the visual-language area have developed natural multi-modal large language models (MLLMs) for spatial reasoning through visual prompting. However, due to remote sensing (RS) imagery containing abundant geospatial information that differs from natural images, it is challenging to effectively adapt natural spatial models to the RS domain. Moreover, current RS MLLMs are limited in overly narrow interpretation levels and interaction manner, hindering their applicability in real-world scenarios. To address those challenges, a spatial MLLM named EarthGPT-X is proposed, enabling a comprehensive understanding of multi-source RS imagery, such as optical, synthetic aperture radar (SAR), and infrared. EarthGPT-X offers zoom-in and zoom-out insight, and possesses flexible multi-grained interactive abilities. Moreover, EarthGPT-X unifies two types of critical spatial tasks (i.e., referring and grounding) into a visual prompting framework. To achieve these versatile capabilities, several key strategies are developed. The first is the multi-modal content integration method, which enhances the interplay between images, visual prompts, and text instructions. Subsequently, a cross-domain one-stage fusion training strategy is proposed, utilizing the large language model (LLM) as a unified interface for multi-source multi-task learning. Furthermore, by incorporating a pixel perception module, the referring and grounding tasks are seamlessly unified within a single framework. In addition, the experiments conducted demonstrate the superiority of the proposed EarthGPT-X in multi-grained tasks and its impressive flexibility in multi-modal interaction, revealing significant advancements of MLLM in the RS field. Copyright © 2025, The Authors. All rights reserved.

关键词： Image coding

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：