检索结果-内蒙古大学图书馆

Learning Representations for Facial Actions From Unlabeled Videos

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

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

RAFNet: Reparameterizable Across-Resolution Fusion Network for Real-Time Image Semantic Segmentation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第2期34卷 1212-1227页

作者： Chen, Lei Dai, Huhe Zheng, Yuan Inner Mongolia Univ Coll Elect Informat Engn Hohhot 010021 Peoples R China Inner Mongolia Univ Coll Comp Sci Natl & Local Joint Engn Res Ctr Intelligent Inform Hohhot 010021 Peoples R China

The demand to implement semantic segmentation networks on mobile devices has increased dramatically. However, existing real-time semantic segmentation methods still suffer from a large number of network parameters, unsuitable for mobile devices with limited memory resources. The reason mainly arises from the fact that most existing methods take the backbone networks (e.g., ResNet-18 and MobileNet) as an encoder. To alleviate this problem, we propose a novel Reparameterizable Channel & Dilation (RCD) block and construct a considerably lightweight yet effective encoder by stacking several RCD blocks according to three guidelines. The strengths of the proposed encoder result in the abilities not only to extract discriminative feature representations via channel convolutions and dilated convolutions, but also to reduce computational burdens while maintaining segmentation accuracy with the help of re-parameterization technique. Except for encoder, we also present a simple but effective decoder that adopts an across-resolution fusion strategy to fuse multi-scale feature maps generated from the encoder instead of a bottom-up pathway fusion. With such an encoder and a decoder, we provide a Reparameterizable Across-resolution Fusion Network (RAFNet) for real-time semantic segmentation. Extensive experiments demonstrate that our RAFNet achieves a promising trade-off between segmentation accuracy, inference speed and network parameters. Specifically, our RAFNet with only 0.96M parameters obtains 75.3% mIoU at 107 FPS and 75.8% mIoU at 195 FPS on Cityscapes and CamVid test sets for full-resolution inputs, respectively. After quantization and deployment on a Xilinx ZCU104 device, our RAFNet obtains a favorable segmentation performance with only 1.4W power.

关键词： Real-time image segmentation encoder-decoder structure lightweight network hardware deployment

来源：评论

学校读者我要写书评

暂无评论

FashionSegNet: a model for high-precision semantic segmentation of clothing images

引用

VISUAL COMPUTER 2024年第3期40卷 1711-1727页

作者： Xiang, Zhong Zhu, Chenglin Qian, Miao Shen, Yujia Shao, Yizhou Zhejiang Sci Tech Univ Sch Mech Engn 928-2 Main StXiasha Higher Educ Pk Hangzhou 310018 Zhejiang Peoples R China

Clothing image segmentation is a method to predict the clothing category label of each pixel in the input image. We reduced the influence of the variability of image shots, the similarity of clothing categories, and the complexity of boundaries on the segmentation accuracy of clothing images by developing an advanced ResNet50-based semantic segmentation model in this study whose primary structure is the encoder-decoder. An improved spatial pyramid pooling module combined with a global feature extraction branch of a large convolution kernel is developed to achieve multi-scale feature fusion and improve the model's ability to identify clothing and its boundary features in different shots. Furthermore, to balance the clothing shape and category information in the model, a spatial and semantic information enhancement module is proposed, which can enhance the circulation of the information between different stages of the network through cross-stage connection technology. The model was finally trained and tested on the Deepfashion2 dataset. The comparison experiment demonstrates that the proposed model obtained the highest mIoU and Boundary IoU of 74.55% and 57.51%, respectively, compared with the DeepLabv3+, PSPNet, and other networks.

关键词： Clothing image segmentation Deep learning Spatial pyramid pooling encoder-decoder structure Large convolution kernel Information enhancement

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

Depth feature fusion based surface defect region identification method for steel plate manufacturing

引用

COMPUTERS & ELECTRICAL ENGINEERING 2024年 116卷

作者： Bai, Dongxu Li, Gongfa Jiang, Du Tao, Bo Yun, Juntong Hao, Zhiqiang Zhou, Dalin Ju, Zhaojie Wuhan Univ Sci & Technol Key Lab Met Equipment & Control Technol Minist Educ Wuhan 430081 Peoples R China Wuhan Univ Sci & Technol Hubei Key Lab Mech Transmiss & Mfg Engn Wuhan 430081 Peoples R China Wuhan Univ Sci & Technol Res Ctr Biomimet Robot & Intelligent Measurement & Wuhan 430081 Peoples R China Wuhan Univ Sci & Technol Precis Mfg Res Inst Wuhan 430081 Peoples R China Univ Portsmouth Sch Comp Portsmouth PO1 3HE England

Computers and electrical engineering have made great strides in steel plate manufacturing. Defect recognition techniques have also evolved. However, due to the large scale of defects, diverse features and sample imbalance problems of steel plates, the general algorithms often suffer from low recognition accuracy and weak robustness in practical detection. Aiming at the problems in recognition, this study proposes an improved defect segmentation network with coder-decoder structure to realize multi-scale interaction of features. Using the split-attention feature extraction module, defect features are learned adaptively. Meanwhile, combined with the group normalization module, a surface defect region recognition model based on depth feature fusion is established. The model was trained for comparative ablation using a migration learning approach. The experimental results confirm the efficiency of the technique. 89.11 % IoU and 94.24 % Dice can be achieved on the Severstal dataset using this method. The research can be applied as an intelligent system for quality monitoring throughout the production process, guiding its rational decision-making and control to realize the improvement of strip steel product quality.

关键词： Steel surface defect identification Depth feature fusion Defect segmentation network Defect detection 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

Ship Segmentation via encoder-decoder Network With Global Attention in High-Resolution SAR Images

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2022年 19卷 1页

作者： Li, Jichao Gou, Shuiping Li, Ruimin Chen, Jia-Wei Sun, Xiaolong Xidian Univ Key Lab Intelligent Percept & Image Understanding Minist Educ Xian 710071 Peoples R China Xidian Univ Acad Adv Interdisciplinary Res Xian 710071 Shaanxi Peoples R China China Elect Technol Grp Corp 20th Res Inst Xian 710068 Shaanxi Peoples R China

Ship detection in the synthetic aperture radar (SAR) image is of great significance in the fields of military and coastal defense. Most ship detection methods are designed based on the object detection framework, which can only provide the vertices' coordinates of the bounding box covering the ship targets but cannot provide more detailed contour information. Target segmentation can further explore the shape and edge information of the objects, which can be used as a blazing novel means for automatic object detection. In this letter, a 3-D atrous encoder-decoder neural network with global attention modules (GAM-EDNet) is proposed to achieve ship segmentation in SAR images. The encoder-decoder structure with atrous convolution is developed as the network body to fully exploit the structural information of the ship targets with various sizes. To increase the structural information of the single-polarization SAR images, a 3-D image cube is designed as the input of the GAM-EDNet. A global attention module is proposed to further improve the segmentation performance by integrating the high-level semantic features with the low-level location features. Besides, an SAR ship segmentation dataset (SAR-HR4) is built to evaluate the segmentation performance, and the experimental results show that the proposed GAM-EDNet achieves better performance than other state-of-the-art methods.

关键词： Marine vehicles Image segmentation Radar polarimetry Semantics Synthetic aperture radar Feature extraction Wavelet transforms encoder-decoder structure global attention module high-resolution synthetic aperture radar (SAR) images ship 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：