检索结果-内蒙古大学图书馆

6th Euro-China Conference on Intelligent Data Analysis and Applications, ECC 2019

作者： Zhao, Qingda Zhang, Fuquan Ma, Linjuan Traditional Chinese Medicine Department of Chinese PLA General Hospital Beijing China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350117 China School of Computer Science and Technology Beijing Institute of Technology Beijing China

ISBN: (纸本)9789811650352

Lung detection is attached much importance to in medical imaging to improve the efficiency and accuracy of the doctor’s work. Recently, it has become very popular among the researchers to explore deep medical technology. In our work, we present a new method of lung detection, which based on YOLOv3 Model. Our goal is to make a contribution to a lung detection system to make it more efficiency and accuracy for the doctor’s work. ChestX-ray14 dataset is used to perfrom the experiments and the result is sound. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Language-guided Image Reflection Separation

Language-guided Image Reflection Separation

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Haofeng Zhong Yuchen Hong Shuchen Weng Jinxiu Liang Boxin Shi National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University National Engineering Research Center of Visual Technology School of Computer Science Peking University AI Innovation Center School of Computer Science Peking University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

This paper studies the problem of language-guided re-flection separation, which aims at addressing the ill-posed reflection separation problem by introducing language de-scriptions to provide layer content. We propose a unified framework to solve this problem, which leverages the cross-attention mechanism with contrastive learning strategies to construct the correspondence between language descriptions and image layers. A gated network design and a ran-domized training strategy are employed to tackle the rec-ognizable layer ambiguity. The effectiveness of the pro-posed method is validated by the significant performance advantage over existing reflection separation methods on both quantitative and qualitative comparisons.

关键词： Training computer vision Annotations Natural languages Contrastive learning Logic gates Reflection

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

arXiv

引用

arXiv 2024年

作者： Yu, Liutao Huang, Liwei Zhou, Chenlin Zhang, Han Ma, Zhengyu Zhou, Huihui Tian, Yonghong AI Department Peng Cheng 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

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. Copyright © 2024, The Authors. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Discovering DTI and DDI by Knowledge Graph with MHRW and Improved Neural Network

Discovering DTI and DDI by Knowledge Graph with MHRW and Imp...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Zhang, Shuo Lin, Xiaoli Zhang, Xiaolong Wuhan University of Science and Technology Hubei Key Laboratory of Intelligent Information Processing and Real-time Industrial System School of Computer Science and Technology Wuhan China

ISBN: (纸本)9781665401265

Drug discovery is of great significance in medical and biological research, while the study of Drug-Target Interaction (DTI) and Drug-Drug Interaction (DDI) can help accelerate drug discovery progress. This paper proposes a new hybrid method for DTI prediction and DDI prediction, which is called MHRW2Vec-TBAN that combines graph representation learning and neural network. MHRW2VecTBAN first constructs knowledge graph KG-DTI and KG-DDI that integrate data related to drugs and targets. Then, an improved graph representation learning model, MHRW2Vec model, is used to obtain feature vectors of reflecting the network structure information for improving the performance of representation learning. Finally, the feature vectors obtained are input to the improved neural network model TextCNN-BiLSTM-Attention Network (TBAN). The experimental results show that, compared with other existing methods, our method could discover more deeper the relationship between drugs and their potential neighborhoods, and has great improvements in DTI prediction and DDI prediction. In addition, the case study of prediction COVID-19 DTI also shows that the proposed model has the potential for actual drug discovery. © 2021 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Multivariate Time Series Anomaly Detection by Feature Decoupling in Federated Learning Scenarios

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： He, Yifan Ding, Xi Tang, Yateng Guan, Jihong Zhou, Shuigeng Fudan University School of Computer Science Shanghai200433 China Shanghai Key Laboratory of Intelligent Information Processing Shanghai200433 China Tencent Weixin Group Guangzhou510308 China Tongji University Department of Computer Science and Technology Shanghai201804 China Ministry of Education Key Laboratory of Embedded System and Service Computing Tongji University Shanghai200092 China

Anomalies are usually regarded as data errors or novel patterns previously unseen, which are quite different from most observed data. Accurate detection of anomalies is crucial in various application scenarios. This paper focuses on unsupervised anomaly detection from Multivariate Time Series (MTS), as real-world data collected from sources such as wearable devices, medical equipment and industrial machines typically manifest as MTS and are often unlabeled. Anomaly detection in MTS represents a data-driven challenge that traditionally requires substantial centralized data for training models. However, in practice, data are frequently distributed among multiple institutions, with privacy concerns restricting unrestricted access. To address these issues, we introduce Feature Decoupling Federated Learning (FDFL), an approach designed to collaboratively train a representation learning network over multiple clients for unsupervised anomaly detection in MTS. Unlike previous methods that simply integrate MTS anomaly detection algorithms with federated learning strategies, FDFL specifically addresses heterogeneity among clients by decoupling the representation network into shared and private branches through a contrastive learning mechanism. This method aggregates shared parameters during each federated round while maintaining client-specific private parameters locally. Additionally, we develop a self-attention block that integrates the representations derived from both shared and private parameters to reconstruct MTS and identify anomalies based on reconstruction errors. Extensive experiments conducted on three publicly available datasets demonstrate that FDFL outperforms existing algorithms in most cases, highlighting the effectiveness and superiority of our proposed method in MTS anomaly detection. © 2020 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Signal Fusion of Social Diffusion Graph with Bi-Directional Semantic Consistency

Multi-Signal Fusion of Social Diffusion Graph with Bi-Direct...

引用

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

作者： Huacheng Li Chunhe Xia Tianbo Wang Wanshuang Lin Changnan Jiang Chen Chen Yuan Zhao Key Laboratory of Beijing Network Technology Beihang University Guangxi Collaborative Innovation Center of Multi-Source Information Integration and Intelligent Processing Guangxi Normal University School of Cyber Science and Technology Beihang University Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai

Devising diffusion graph to learn user representations is a crucial step in studying information propagation prediction. However, previous works mainly focused on structural and temporal features. To better incorporate content features, we introduce the Backward Decomposition and Forward Preservation mechanisms. The former involves decomposing content features for initializing node signals in the diffusion graph, thus fusing user features with content features. The latter aims to maintain node features generated by graph encoder consistent with the original content features. A series of experiments demonstrate that our model outperforms state-of-the-art models, and both mechanisms significantly enhance the prediction performance. Furthermore, our methods enables the features generated by the diffusion graph to more effectively incorporate features from various semantic spaces, whether encoded by language models or generated by graph embedding algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Event Stream-based Visual Object Tracking: HDETrack V2 and A High-Definition Benchmark

arXiv

引用

arXiv 2025年

作者： Wang, Shiao Wang, Xiao Wang, Chao Jin, Liye Zhu, Lin Jiang, Bo Tian, Yonghong Tang, Jin School of Computer Science and Technology Anhui University Hefei230601 China Beijing Institute of Technology Beijing China Peng Cheng Laboratory Shenzhen China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China School of Electronic and Computer Engineering Shenzhen Graduate School Peking University China

Recent years have witnessed unprecedented growth in the field of visual object tracking using bio-inspired event cameras. Previous research in this domain has primarily followed two paths: aligning RGB data and event streams for precise tracking or developing trackers that rely solely on events. However, while the former approach often incurs significant computational costs during inference, the latter may struggle with challenges posed by noisy event data or limited spatial resolution. In this paper, we present a hierarchical knowledge distillation framework designed to leverage multi-modal and multi-view information during the training phase, while utilizing only event signals for tracking. Specifically, we first train a teacher Transformer-based multi-modal/multi-view tracking network by simultaneously feeding RGB frames and event streams. We then introduce a novel hierarchical knowledge distillation strategy that incorporates the similarity matrix, feature representation, and response map-based distillation to guide the learning of the student Transformer network. We also enhance the model’s ability to capture temporal dependencies by applying the temporal Fourier transform to establish temporal relationships between video frames. We adapt the network model to specific target objects during testing via a newly proposed test-time tuning strategy to achieve high performance and flexibility in target tracking. Recognizing the limitations of existing event-based tracking datasets, which are predominantly low-resolution (346 × 260), we propose EventVOT, the first large-scale high-resolution (1280 × 720) event-based tracking dataset. It comprises 1141 videos spanning diverse categories such as pedestrians, vehicles, UAVs, ping pong, etc. Extensive experiments on both low-resolution (FE240hz, VisEvent, FELT), and our newly proposed high-resolution EventVOT dataset fully validated the effectiveness of our proposed method. Both the benchmark dataset and source code have

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

De Novo Drug Design via Multi-Label Learning and Adversarial Autoencoder

De Novo Drug Design via Multi-Label Learning and Adversarial...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Ye, Qing Zhang, Xiaolong Lin, Xiaoli Wuhan University of Science and Technology Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System School of Computer Science and Technology Wuhan China

ISBN: (纸本)9781665401265

generating new molecules is very important for drug design. Currently, many deep generative models have been designed, such as variational autoencoder (VAE), adversarial autoencoder (AAE), and reinforcement learning (RL). However, many problems are also existed in these models. Firstly, the information among molecules could be not utilized in optimizing these models. Secondly, some useful molecule information could be not used, such as fingerprint. Thirdly, the information contained in different molecule representations could be not used together. To overcome the above problems, in this paper, a multi-label learning and adversarial autoencoder (MLAAE) based de novo drug design method is designed. MLAAE enhances its learning ability with a new designed multi-label classifier and a new designed double AAEs collaborative optimization framework. These new designs can learn a better latent space whose global distribution is similar with the random distribution, but local distribution contains much information. As a result, the generator can be trained by more information, and the input of generator in testing is similar with that in training. The conducted experiments validate the effectiveness of our MLAAE. © 2021 IEEE.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Editable Portrait Synthesis with 3D GAN Inversion

High-Fidelity Editable Portrait Synthesis with 3D GAN Invers...

引用

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

作者： Jindong Xie Jiachen Liu Yupei Lin Jinbao Wang Xianxu Hou Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Information Engineering Guangdong University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Information Processing School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The 3D generative adversarial network (GAN) inversion converts an image into 3D representation to attain high-fidelity reconstruction and facilitate realistic image manipulation within the 3D latent space. However, previous approaches face challenges regarding the trade-off between the reconstruction ability and editability. That is, reversing a real-world image to a low-dimensional latent code would inevitably lead to information loss, and achieving a near-perfect reconstruction using high-rate triplane representation often limits the ability to manipulate the image freely in the latent space. To address these issues, we propose a novel latent conditioning encoder-based framework with the alignment between the low-dimensional latent and high-dimensional triplane. A non-semantic guided editing strategy bridges the intrinsic relation between the latent condition and triplane generation, making it possible to edit the high-dimensional representation by latent manipulation. As a result, our method can achieve high-fidelity reconstruction and editing simultaneously by directly controlling the latent code. Experimental results demonstrate that our approach excels in reconstruction and editing quality compared to previous 3D inversion methods. Furthermore, our method can also edit even real faces with large poses and out-of-domain cases.

关键词： Bridges Three-dimensional displays Codes Signal processing Generative adversarial networks Vectors Acoustics Speech processing Image reconstruction Faces

来源：评论

学校读者我要写书评

暂无评论

Drug-Target Interaction Prediction via Multiple Output Graph Convolutional Networks 17th

Drug-Target Interaction Prediction via Multiple Output Graph...

引用

17th International Conference on Intelligent Computing, ICIC 2021

作者： Ye, Qing Zhang, Xiaolong Lin, Xiaoli Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9783030845315

Computational prediction of drug-target interaction (DTI) is very important for the new drug discovery. Currently, graph convolutional networks (GCNs) have been gained a lot of momentum, as its performance on non-Euclidean data. Although drugs and targets are two typical non-Euclidean data, many problems are also existed when use GCNs in DTI prediction. Firstly, most state-of-the-art GCN models are prone to the vanishing gradient problem, which is more serious in DTI prediction, as the number of interactions is limit. Secondly, a suitable graph is hardly defined for GCN in DTI prediction, as the relationship between the samples is not explicitly provided. To overcome the above problems, in this paper, a multiple output graph convolutional network (MOGCN) based DTI prediction method is designed. MOGCN enhances its learning ability with many new designed auxiliary classifier layers and a new designed graph calculation method. Many auxiliary classifier layers can increase the gradient signal that gets propagated back, utilize multi-level features to train the model, and use the features produced by the higher, middle or lower layers in a unified framework. The graph calculation method can use both the label information and the manifold. The conducted experiments validate the effectiveness of our MOGCN. © 2021, Springer Nature Switzerland AG.

关键词： Forecasting

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：