检索结果-内蒙古大学图书馆

Traffic Scene Captioning with Multi-Stage Feature Enhancement

Computers, Materials & Continua 2023年第9期76卷 2901-2920页

作者： Dehai Zhang Yu Ma Qing Liu Haoxing Wang Anquan Ren Jiashu Liang School of Software Yunnan UniversityKunming650091China

Traffic scene captioning technology automatically generates one or more sentences to describe the content of traffic scenes by analyzing the content of the input traffic scene images,ensuring road safety while providing an important decision-making function for sustainable *** order to provide a comprehensive and reasonable description of complex traffic scenes,a traffic scene semantic captioningmodel withmulti-stage feature enhancement is proposed in this *** general,the model follows an encoder-decoder ***,multilevel granularity visual features are used for feature enhancement during the encoding process,which enables the model to learn more detailed content in the traffic scene ***,the scene knowledge graph is applied to the decoding process,and the semantic features provided by the scene knowledge graph are used to enhance the features learned by the decoder again,so that themodel can learn the attributes of objects in the traffic scene and the relationships between objects to generate more reasonable *** paper reports extensive experiments on the challenging MS-COCO dataset,evaluated by five standard automatic evaluation metrics,and the results show that the proposed model has improved significantly in all metrics compared with the state-of-the-art methods,especially achieving a score of 129.0 on the CIDEr-D evaluation metric,which also indicates that the proposed model can effectively provide a more reasonable and comprehensive description of the traffic scene.

关键词： Traffic scene captioning sustainable transportation feature enhancement encoder-decoder structure multi-level granularity scene knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A sketch semantic segmentation method using novel local feature aggregation and segment-level self-attention

引用

NEURAL COMPUTING & APPLICATIONS 2023年第21期35卷 15295-15313页

作者： Wang, Lei Zhang, Shihui Wang, Wei Zhao, Weibo Yanshan Univ Sch Informat Sci & Engn Hebei St Qinhuangdao 066004 Hebei Peoples R China Yanshan Univ Key Lab Comp Virtual Technol & Syst Integrat Hebei Hebei St Qinhuangdao 066004 Hebei Peoples R China

Sketch semantic segmentation presents great challenges, since sketches have simpler appearances and more levels of abstraction than natural images. To overcome these challenges, we propose a sketch semantic segmentation method. Concretely, we treat a sketch as a 2D point set and exploit the structures of strokes and the spatial position relationship among 2D points to develop a novel local feature aggregation module. The novel local feature aggregation module encodes informative local features, which are highly useful to analyze semantics. And we define "stroke distance" to balance the two-dimensional spatial distributions of sketches and the internal structures of strokes. Simultaneously, we design a segment-level self-attention module to establish and enhance the relationship between segments by encoding the contents and positions of segment features. Further, based on the above two modules, we construct a similar encoder-decoder structure with two sub-branches, which retains the features of the significant points and integrates the features of several intermediate stages by utilizing a global multi-scale mechanism. Finally, the two outputs of the two sub-branches are fused to obtain the final sketch semantic segmentation result. Extensive experiments on SPG and SketchSeg-150K show that our method achieves state-of-the-art results.

关键词： Sketch semantic segmentation Novel local feature aggregation Segment-level self-attention encoder-decoder structure Global multi-scale mechanism

来源：评论

学校读者我要写书评

暂无评论

Learnable PM diffusion coefficients and reformative coordinate attention network for low dose CT denoising

引用

PHYSICS IN MEDICINE AND BIOLOGY 2023年第24期68卷 245017-245017页

作者： Zhang, Haowen Zhang, Pengcheng Cheng, Weiting Li, Shu Yan, Rongbiao Hou, Ruifeng Gui, Zhiguo Liu, Yi Chen, Yang North Univ China State Key Lab Dynam Testing Technol Taiyuan 030051 Peoples R China Southeast Univ Minist Educ Key Lab Comp Network & Informat Integrat Nanjing 210096 Peoples R China Southeast Univ Lab Image Sci & Technol Nanjing 210096 Peoples R China Ctr Rech Informat Biomed Sino Francais LIA CRIBs F-3500 Rennes France Southeast Univ Jiangsu Prov Joint Int Res Lab Med Informat Proc Nanjing Peoples R China

Objective. Various deep learning methods have recently been used for low dose CT (LDCT) denoising. Aggressive denoising may destroy the edge and fine anatomical structures of CT images. Therefore a key issue in LDCT denoising tasks is the difficulty of balancing noise/artifact suppression and edge/structure preservation. Approach. We proposed an LDCT denoising network based on the encoder-decoder structure, namely the Learnable PM diffusion coefficient and efficient attention network (PMA-Net). First, using the powerful feature modeling capability of partial differential equations, we constructed a multiple learnable edge module to generate precise edge information, incorporating the anisotropic image processing idea of Perona-Malik (PM) model into the neural network. Second, a multiscale reformative coordinate attention module was designed to extract multiscale information. Non-overlapping dilated convolution capturing abundant contextual content was combined with coordinate attention which could embed the spatial location information of important features into the channel attention map. Finally, we imposed additional constraints on the edge information using edge-enhanced multiscale perceptual loss to avoid structure loss and over-smoothing. Main results. Experiments are conducted on simulated and real datasets. The quantitative and qualitative results show that the proposed method has better performance in suppressing noise/artifacts and preserving edges/structures. Significance. This work proposes a novel edge feature extraction method that unfolds partial differential equation into neural networks, which contributes to the interpretability and clinical application value of neural network.

关键词： LDCT encoder-decoder structure attention mechanism perceptual loss Perona-Malik model

来源：评论

学校读者我要写书评

暂无评论

Channel Pyramidal Transformer Network for Single Image Deraining

引用

IEEE SIGNAL PROCESSING LETTERS 2023年 30卷 1757-1761页

作者： Xu, Yifei Long, Zourong Tang, Bin Lei, Siyue Chongqing Univ Technol Chongqing 400054 Peoples R China

In recent years, Convolutional Neural Networks (CNNs) and Visual Transformers have shown remarkable performance in image deraining tasks. However, these state-of-the-art (SOTA) methods exhibit high computational costs in addition to excellent performance. This would hinder the analytical comparison of methods and limit their practical application. We argue that the high computational cost mainly stems from the explosion in the number of parameters due to the surge of feature dimensions. To achieve better results with fewer parameters. By reconstructing the multi-head attention mechanism and feed-forward network, we propose a multi-scale hierarchical Transformer network with a change of width resembling a pyramid, called CPTransNet. The key idea of CPTransNet is to slowly increase the feature dimension during the feature extraction process. This avoids parameter wastage due to feature dimension surge. CPTransNet achieves 33.25 dB PSNR on the classical dataset of image deraining, exceeding the previous state-of-the-art 0.22 dB PSNR with only 19.4% of its computational cost.

关键词： Image restoration channels pyramid encoder-decoder structure

来源：评论

学校读者我要写书评

暂无评论

Multilevel Context Feature Fusion for Semantic Segmentation of ALS Point Cloud

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2023年 20卷 1-1页

作者： Zeng, Tao Luo, Fulin Guo, Tan Gong, Xiuwen Xue, Jingyun Li, Hanshan Xian Technol Univ Sch Mechatron Engn Xian 710054 Peoples R China Chongqing Univ Coll Comp Sci Chongqing 400044 Peoples R China Chongqing Univ Posts & Telecommun Sch Commun & Informat Engn Chongqing 400065 Peoples R China Univ Sydney Fac Engn Camperdown NSW 2002 Australia

Semantic segmentation of airborne laser scanning (ALS) point clouds using deep learning is a hot research in remote sensing and photogrammetry. A current trend is to aggregate contextual features from different scales for boosting network generalization and diversity discrimination capabilities. One main challenge is how to achieve effective fusion with multi-scale information. In this letter, we propose a multilevel context feature fusion network (MCFN) for semantic segmentation of ALS point cloud based on an encoder-decoder structure. More specifically, we design the squeeze-expansion shared multilayer perceptron (SE-MLP) module following kernel point convolution (KPConv) in the encoding stage, which can extend the receptive field of KPConv. To aggregate low-level features and highlevel representations, we establish channel self-attention between skip connections. In the decoding stage, we develop a crosslayer attention fusion (CAF) module to generate additional discriminative channel features by fusing multiscale features at different upsampling layers. Experiments on the ISPRS and LASDU datasets demonstrate the superiority of the proposed method. Code: https://***/SC-shendazt/MCFN.

关键词： Attention mechanism encoder-decoder structure kernel point convolution (KPConv) multilevel fusion point cloud semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

CAE-GAN: A hybrid model for vehicle trajectory prediction

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2022年第12期16卷 1682-1696页

作者： Chen, Long Zhou, Qiyang Cai, Yingfeng Wang, Hai Li, Yicheng Jiangsu Univ Automot Engn Res Inst Zhenjiang 212013 Jiangsu Peoples R China Jiangsu Univ Sch Automot & Traff Engn Zhenjiang Jiangsu Peoples R China

Trajectory prediction of surrounding vehicles is a crucial capability of intelligent driving vehicles. In a scene, a vehicle and its surrounding vehicles constitute an integral system, and the vehicle's future motion trajectory is affected by the actions of surrounding vehicles. The influencing mode and degree are hidden in the relevant historical information of the vehicle and its neighbour vehicle. The existing trajectory prediction methods either do not consider the confidence of the predicted trajectory, or the accuracy requirement is ignored when considering the confidence of the predicted trajectory. In order to address this problem, a mixed Conditional Autoencoder Generative Adversarial Network (CAE-GAN) model based on the multi-loss function is proposed. The proposed model uses the encoder-decoder structure with a convolutional social pool to extract general features. The generative adversarial networks (GANs) are used to extract the confidence features of the generated trajectories, which enables the proposed model to generate trajectories that are close to the real trajectories. In addition, a classifier structure based on an LSTM network is added to output the probability that the predicted trajectory belongs to a particular lateral maneuver so that the generated trajectory lateral maneuver of the model is consistent with the real trajectory lateral maneuver. The proposed model is evaluated using the publicly available NGSIM US-101 and I-80 datasets, and results show that the accuracy of the proposed model is higher than that of the existing methods. The proposed model achieves an average accuracy improvement of 16.34% in comparison to the most advanced existing models.

关键词： convolutional social pool generative adversarial networks deep learning (artificial intelligence) trajectory prediction methods future motion trajectory I-80 dataset LSTM network road traffic intelligent driving vehicles NGSIM US-101 dataset multiloss function encoder-decoder structure recurrent neural nets neighbour vehicle generated trajectory lateral maneuver feature extraction vehicle trajectory prediction mixed conditional autoencoder generative adversarial network model CAE-GAN traffic engineering computing

来源：评论

学校读者我要写书评

暂无评论

Learning Representations for Facial Actions From Unlabeled Videos

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2022年第1期44卷 302-317页

作者： Li, Yong Zeng, Jiabei Shan, Shiguang Chinese Acad Sci Inst Comp Technol CAS Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China CAS Ctr Excellence Brain Sci & Intelligence Techn Beijing 100190 Peoples R China

Facial actions are usually encoded as anatomy-based action units (AUs), the labelling of which demands expertise and thus is time-consuming and expensive. To alleviate the labelling demand, we propose to leverage the large number of unlabelled videos by proposing a twin-cycle autoencoder (TAE) to learn discriminative representations for facial actions. TAE is inspired by the fact that facial actions are embedded in the pixel-wise displacements between two sequential face images (hereinafter, source and target) in the video. Therefore, learning the representations of facial actions can be achieved by learning the representations of the displacements. However, the displacements induced by facial actions are entangled with those induced by head motions. TAE is thus trained to disentangle the two kinds of movements by evaluating the quality of the synthesized images when either the facial actions or head pose is changed, aiming to reconstruct the target image. Experiments on AU detection show that TAE can achieve accuracy comparable to other existing AU detection methods including some supervised methods, thus validating the discriminant capacity of the representations learned by TAE. TAE's ability in decoupling the action-induced and pose-induced movements is also validated by visualizing the generated images and analyzing the facial image retrieval results qualitatively and quantitatively.

关键词： Facial action unit detection self-supervised learning representation learning feature disentanglement encoder-decoder structure

来源：评论

学校读者我要写书评

暂无评论

ICANet: A LIGHTWEIGHT INCREASING CONTEXT AIDED NETWORK FOR REAL-TIME IMAGE SEMANTIC SEGMENTATION

ICANet: A LIGHTWEIGHT INCREASING CONTEXT AIDED NETWORK FOR R...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Chen, Lei Dai, Huhe Zheng, Yuan Inner Mongolia Univ Coll Elect Informat Engn Hohhot Peoples R China Inner Mongolia Univ Coll Comp Sci Hohhot Peoples R China

ISBN: (纸本)9781665468916

Although existing real-time segmentation methods have reduced the network parameters, they still suffer from slow inference speed. To alleviate this problem, we propose a novel lightweight image segmentation method, called Increasing Context Aided Network (ICANet), which brings a significant increase in inference speed while maintaining competitive segmentation accuracy. To do this, we elaborately design both encoder and decoder. Considering that a large reduction in channel numbers brings poor performance, we propose a Inverted Depthwise Separable convolution block (IDS block) that enriches semantic information in channel and spatial dimensions. By stacking several such IDS blocks, we build an efficient encoder that can capture an increasing context by using different dilation rates in IDS blocks to further improve accuracy. Besides, we present a simple decoder that adopts a bottom-up pathway to effectively fuse multiscale feature maps from encoder. Extensive experiments show our ICANet achieves a SOTA balance between accuracy, speed and parameters.

关键词： Image semantic segmentation real-time lightweight network encoder-decoder structure

来源：评论

学校读者我要写书评

暂无评论

Multi-Intersection Traffic Optimisation: A Benchmark Dataset and a Strong Baseline

IEEE OPEN JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS

引用

IEEE OPEN JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS 2022年 3卷 126-136页

作者： Wang, Hu Chen, Hao Wu, Qi Ma, Congbo Li, Yidong Univ Adelaide Sch Comp Sci Adelaide SA 5005 Australia Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing 100044 Peoples R China

The control of traffic signals is fundamental and critical to alleviate traffic congestion in urban areas. However, it is challenging since traffic dynamics are complicated in real-world scenarios. Because of the high complexity of the optimisation problem for modeling the traffic, experimental settings of existing works are often inconsistent. Moreover, it is not trivial to control multiple intersections properly in real complex traffic scenarios due to its vast state and action space. Failing to take intersection topology relations into account also results in inferior solutions. To address these issues, in this work we carefully design our settings and propose a new dataset including both synthetic and real traffic data in more complex scenarios. Additionally, we propose a novel baseline model with strong performance. It is based on deep reinforcement learning with an encoder-decoder structure: an edge-weighted graph convolutional encoder to excavate multi-intersection relations;and an unified structure decoder to jointly model multiple junctions in a comprehensive manner, which significantly reduces the number of the model parameters. By doing so, the proposed model is able to effectively deal with the multi-intersection traffic control optimisation problem. Models are trained/tested on both synthetic and real maps and traffic data with the Simulation of Urban Mobility (SUMO) simulator. Experimental results show that the proposed model surpasses multiple competitive methods. The traffic data and the code can be found at https://***/JPdU1.

关键词： Optimization Junctions Switches Reinforcement learning Convolution Markov processes Urban areas Traffic control optimisation multiple intersections deep reinforcement learning encoder-decoder structure

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Inversion Method Based on SDM and ANNs Considering Electromagnetic Response Laws

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2024年 62卷 1页

作者： Lang, Shinan Huang, Wenbin Huang, Ling Liu, Xiaojun Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China Chinese Acad Sci Inst Elect Key Lab Electromagnet Radiat & Sensing Technol Beijing 100094 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst AIRCAS Beijing 100094 Peoples R China

Among the inversion methods for airborne transient electromagnetic (ATEM) data, the hybrid inversion method integrates the iterative optimization framework with artificial neural networks (ANNs), ensuring inversion accuracy while enhancing the generalization capability of neural networks. However, this method faces challenges in terms of slow computation speeds due to its lower updated step length and the lack of consideration for electromagnetic response laws. Our method adopts a supervised descent method (SDM) framework to supervise the ANNs, obtaining a longer updated step length. On the basis of the SDM framework, we have considered the electromagnetic response laws and designed RNN-ResNet and 1-D-UNet networks to update the conductivity model, improving the computing speed. Through numerical ablation experiments, we validated the effectiveness of our proposed method and compared the inversion results with those obtained using the traditional hybrid method. Additionally, we conducted tests on bundle fringe distribution, inversion fitting loss, noise sensitivity, and inversion speed for both methods using measured data to evaluate their performance in practical applications. The experimental findings demonstrate that our method achieves the same level of inversion accuracy and generalization ability as the traditional hybrid method while enhancing inversion speed by up to 68.5%.

关键词： Conductivity Electromagnetics Accuracy Iterative methods Optimization Data models Atmospheric modeling Airborne transient electromagnetic (ATEM) data inversion controlled-source electromagnetics (CSEM) encoder-decoder structure rapid inversion method supervised descent method (SDM)

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：