检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 3012-3021页

作者： Wang, Jingcheng Zhang, Yong Hu, Yongli Yin, Baocai Beijing University of Technology Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence Faculty of Information Technology Beijing100124 China

Graph convolutional neural networks, which aim to learn the spatial correlation within multivariate time-series data, have achieved significant advancements in traffic prediction. Despite the proliferation of various spatiotemporal graph neural networks, a fundamental question of the predefined graphs still remain to be explored: how can the graph be dynamically optimized as time shifts? Especially for tasks such as rail transit where travel patterns of passengers change periodically. In other words, the spatial correlation of multivariate traffic time-series data is closely intertwined with temporal features, which are tricky to reflect through static graphs with handcrafted association. To adaptively learn the spatial correlation in feature domain, we propose hierarchical hypergraph attention networks (HHGATs). The hierarchical nature of the framework is reflected in both temporal and spatial dimensions. At different time spans, the model explores the hidden hyperedges with a local hypergraph attention mechanism and optimizes the hypergraph with a global attention mechanism. The nodelevel prediction results are then fused after the downstream tasks of spatiotemporal hypergraph convolutional networks. The effectiveness and accuracy of the proposed model are evaluated on historical datasets of Beijing and Hangzhou. Compared to the baselines, the proposed approach consistently demonstrates superior performance in various evaluation scenarios. © 2020 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Dual Neural Network Approach for Dual-Energy Imaging and Material Decomposition 3rd

Dual Neural Network Approach for Dual-Energy Imaging and Mat...

引用

3rd International Conference on Artificial Intelligence, Robotics, and Communication, ICAIRC 2023

作者： Shen, Ye Ren, Junru Wang, Yizhong Zhang, Xinrui Wang, Shaoyu Cai, Ailong Liang, Ningning Li, Lei Yan, Bin Department of Henan Key Laboratory of Imaging and Intelligent Processing Information Engineering University Zhengzhou450000 China

ISBN: (纸本)9789819721993

Dual-energy computed tomography (DECT) is a promising technology which uses X-ray beams with different energies to obtain the material attenuation information of the scanned object. However, in contrast to single-energy CT (SECT), DECT imaging suffers from high hardware costs, complex systems and increased radiation doses. In order to obtain DECT images easily, in this paper, we propose a dual neural network structure that achieves spectral mapping and material decomposition. Specifically, we developed the mapping U-Net and the material decomposition U-Net, respectively. Finally, we verified the feasibility of the proposed method on the clinical cranial cavity. Numerical results show that the proposed method can obtain high-quality DECT images from SECT images and realize accurate basis material decomposition. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Addressing Imbalance for Class Incremental Learning in Medical Image Classification 24

Addressing Imbalance for Class Incremental Learning in Medic...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Hao, Xuze Ni, Wenqian Jiang, Xuhao Tan, Weimin Yan, Bo Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9798400706868

Deep convolutional neural networks have made significant breakthroughs in medical image classification, under the assumption that training samples from all classes are simultaneously available. However, in real-world medical scenarios, there's a common need to continuously learn about new diseases, leading to the emerging field of class incremental learning (CIL) in the medical domain. Typically, CIL suffers from catastrophic forgetting when trained on new classes. This phenomenon is mainly caused by the imbalance between old and new classes, and it becomes even more challenging with imbalanced medical datasets. In this work, we introduce two simple yet effective plug-in methods to mitigate the adverse effects of the imbalance. First, we propose a CIL-balanced classification loss to mitigate the classifier bias toward majority classes via logit adjustment. Second, we propose a distribution margin loss that not only alleviates the inter-class overlap in embedding space but also enforces the intra-class compactness. We evaluate the effectiveness of our method with extensive experiments on three benchmark datasets (CCH5000, HAM10000, and EyePACS). The results demonstrate that our approach outperforms state-of-the-art methods. © 2024 ACM.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Medical Data-Effective Learning Benchmark for Highly Efficient Pre-training of Foundation Models 24

A Medical Data-Effective Learning Benchmark for Highly Effic...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Yang, Wenxuan Tan, Weimin Sun, Yuqi Yan, Bo Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9798400706868

Foundation models, pre-trained on massive datasets, have achieved unprecedented generalizability. However, is it truly necessary to involve such vast amounts of data in pre-training, consuming extensive computational resources? This paper introduces data-effective learning, aiming to use data in the most impactful way to pre-train foundation models. This involves strategies that focus on data quality rather than quantity, ensuring the data used for training has high informational value. Data-effective learning plays a profound role in accelerating foundation model training, reducing computational costs, and saving data storage, which is very important as the volume of medical data in recent years has grown beyond many people's expectations. However, due to the lack of standards and comprehensive benchmark, research on medical data-effective learning is poorly studied. To address this gap, our paper introduces a comprehensive benchmark specifically for evaluating data-effective learning in the medical field. This benchmark includes a dataset with millions of data samples from 31 medical centers (DataDEL), a baseline method for comparison (MedDEL), and a new evaluation metric (NormDEL) to objectively measure data-effective learning performance. Our extensive experimental results show the baseline MedDEL can achieve performance comparable to the original large dataset with only 5% of the data. Establishing such an open data-effective learning benchmark is crucial for the medical foundation model research community because it facilitates efficient data use, promotes collaborative breakthroughs, and fosters the development of cost-effective, scalable, and impactful healthcare solutions. The benchmark can be accessed at https://***/shadow2469/*** GitHub Repository. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

FacialFlowNet: Advancing Facial Optical Flow Estimation with a Diverse Dataset and a Decomposed Model 24

FacialFlowNet: Advancing Facial Optical Flow Estimation with...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Lu, Jianzhi He, Ruian Zhou, Shili Tan, Weimin Yan, Bo Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9798400706868

Facial movements play a crucial role in conveying altitude and intentions, and facial optical flow provides a dynamic and detailed representation of it. However, the scarcity of datasets and a modern baseline hinders the progress in facial optical flow research. This paper proposes FacialFlowNet (FFN), a novel large-scale facial optical flow dataset, and the Decomposed Facial Flow Model (DecFlow), the first method capable of decomposing facial flow. FFN comprises 9,635 identities and 105,970 image pairs, offering unprecedented diversity for detailed facial and head motion analysis. DecFlow features a facial semantic-aware encoder and a decomposed flow decoder, excelling in accurately estimating and decomposing facial flow into head and expression components. Comprehensive experiments demonstrate that FFN significantly enhances the accuracy of facial flow estimation across various optical flow methods, achieving up to an 11% reduction in Endpoint Error (EPE) (from 3.91 to 3.48). Moreover, DecFlow, when coupled with FFN, outperforms existing methods in both synthetic and real-world scenarios, enhancing facial expression analysis. The decomposed expression flow achieves a substantial accuracy improvement of 18% (from 69.1% to 82.1%) in micro-expressions recognition. These contributions represent a significant advancement in facial motion analysis and optical flow estimation. Codes and datasets can be found here. © 2024 ACM.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Learning Cross-Spectral Prior for Image Super-Resolution 24

Learning Cross-Spectral Prior for Image Super-Resolution

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Ma, Chenxi Tan, Weimin Zhou, Shili Yan, Bo School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China

ISBN: (纸本)9798400706868

With the rising interest in multi-camera cross-spectral systems, cross-spectral images have been widely used in computer vision and image processing. Therefore, an effective super-resolution (SR) method provides high-resolution (HR) cross-spectral images for different research and applications. However, existing SR methods rarely consider utilizing cross-spectral information to assist the SR of visible images. They cannot handle complex degradation (noise, high brightness, low light) and misalignment problems in low-resolution (LR) cross-spectral images. Here, we first explore the potential of using near-infrared (NIR) image guidance for better SR, based on the observation that NIR images can preserve valuable information for recovering adequate image details. To take full advantage of the cross-spectral prior, we propose a novel Cross-Spectral Prior guided image SR approach (CSPSR). The cross-view matching (CVM) module and the dynamic multi-modal fusion (DMF) module can enhance the spatial correlation between cross-spectral images and bridge the multi-modal feature gap, respectively. Extensive experiments demonstrate the effectiveness of our CSPSR. © 2024 ACM.

关键词： Infrared devices

来源：评论

学校读者我要写书评

暂无评论

Probabilistic fault diagnosis of clustered faults for multiprocessor systems

引用

Journal of Computer Science & technology 2023年第4期38卷 821-833页

作者：孙雪丽樊建席程宝雷王岩张力 School of Computer Science and Technology Soochow UniversitySuzhou 215006China Provincial Key Laboratory for Computer Information Processing Technology Soochow UniversitySuzhou 215006China

With the development of high-performance computing and the expansion of large-scale multiprocessor sys-tems,it is significant to study the reliability of *** fault diagnosis is of practical value to the reliabilityanalysis of multiprocessor *** this paper,we design a linear time diagnosis algorithm with the multiprocessor sys-tem whose threshold is set to 3,where the probability that any node is correctly diagnosed in the discrete state can be ***,we give the probabilities that all nodes of a d-regular and d-connected graph can be correctly diag-nosed in the continuous state under the Weibull fault distribution and the Chi-square fault *** prove thatthey approach to 1,which implies that our diagnosis algorithm can correctly diagnose almost all nodes of the graph.

关键词： regular graph clustered fault probabilistic diagnosis algorithm Preparata Metze Chien model(PMCmodel)

来源：评论

学校读者我要写书评

暂无评论

JDC-GCN: joint diversity and consistency graph convolutional network

引用

Neural Computing and Applications 2025年 1-17页

作者： Lin, Renjie Yao, Jie Wang, Shiping Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China

In real-world scenarios, multi-view data comprises heterogeneous features, with each feature corresponding to a specific view. The objective of multi-view semi-supervised classification is to enhance classification performance by leveraging the inherent complementary and consistent information present within diverse views. Nevertheless, many existing frameworks primarily focus on assigning suitable weights to different views while neglecting the importance of consistent information. In this paper, a multi-view semi-supervised classification framework called joint diversity and consistency graph convolutional network (JDC-GCN) is proposed. Firstly, the structure of graph convolutional network is introduced to the multi-view semi-supervised classification, capable of propagating the label information over the topological structure of multi-view data. Secondly, the proposed JDC-GCN captures the complementary and consistent information from multiple views through two indispensable sub-modules, Diversity-GCN and Consistency-GCN, respectively. Finally, the attention mechanism is leveraged to dynamically adjust the weights of various views, allowing us to measure the significance of heterogeneous features and the consistent graph without introducing additional parameters. Comprehensive experiments on eight multi-view datasets are conducted to validate the effectiveness of the JDC-GCN algorithm. The results show that the proposed method exhibits superior classification performance compared to other state-of-the-art methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

RaSTFormer: region-aware spatiotemporal transformer for visual homogenization recognition in short videos

引用

Neural Computing and Applications 2024年第18期36卷 10713-10732页

作者： Zhang, Shuying Zhang, Jing Zhang, Hui Zhuo, Li Faculty of Information Technology Beijing University of Technology Beijing China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing China

With the surge in network traffic, the homogenization of short video content is becoming increasingly prominent, resulting in low-quality entertainment due to proliferation and infringement. Therefore, recognizing visual homogeneity in short videos is of great significance. Considering the extremely similar dynamic evolution in specific regions from intra and inter-frames, introducing region-aware attention is attractive to achieve homogenization recognition. Therefore, we propose a region-aware spatiotemporal Transformer (RaSTFormer) for visual homogenization recognition, including: (1) a region-aware Transformer encoder is designed to extract multi-region frame-level features from short videos;(2) a multi-layer spatiotemporal Transformer decoder is used to aggregate multi-region frame-level features, generating shot-level spatiotemporal features;and (3) measuring symmetric shot-level chamfer similarity to recognize visual homogeneous content. Specially, we established a real-world video homogenization dataset, BJUT-HCD, and conducted extensive experiments. The proposed RaSTFormer achieved the highest mean average precision (mAP) of 98.13% and a top-1 accuracy of 99.37%, outperforming SOTA methods. The results show that our method achieves competitive performance in visual homogenization recognition in short videos. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Homogenization method

来源：评论

学校读者我要写书评

暂无评论

Semantic segmentation via pixel-to-center similarity calculation

引用

CAAI Transactions on Intelligence technology 2024年第1期9卷 87-100页

作者： Dongyue Wu Zilin Guo Aoyan Li Changqian Yu Nong Sang Changxin Gao National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhanChina Meituan Inc. BeijingChina

Since the fully convolutional network has achieved great success in semantic segmentation,lots of works have been proposed to extract discriminative pixel ***,the authors observe that existing methods still suffer from two typical challenges:(i)The intra-class feature variation between different scenes may be large,leading to the difficulty in maintaining the consistency between same-class pixels from different scenes;(ii)The inter-class feature distinction in the same scene could be small,resulting in the limited performance to distinguish different classes in each *** authors first rethink se-mantic segmentation from a perspective of similarity between pixels and class *** weight vector of the segmentation head represents its corresponding semantic class in the whole dataset,which can be regarded as the embedding of the class ***,the pixel-wise classification amounts to computing similarity in the final feature space between pixels and the class *** this novel view,the authors propose a Class Center Similarity(CCS)layer to address the above-mentioned challenges by generating adaptive class centers conditioned on each scenes and supervising the similarities between class *** CCS layer utilises the Adaptive Class Center Module to generate class centers conditioned on each scene,which adapt the large intra-class variation between different *** designed Class Distance Loss(CD Loss)is introduced to control both inter-class and intra-class distances based on the predicted center-to-center and pixel-to-center ***,the CCS layer outputs the processed pixel-to-center similarity as the segmentation *** experiments demonstrate that our model performs favourably against the state-of-the-art methods.

关键词： computer vision deep neural networks image segmentation scene understanding

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：