检索结果-内蒙古大学图书馆

QCNet: query context network for salient object detection of automatic surface inspection

VISUAL COMPUTER 2023年第10期39卷 4391-4403页

作者： Sun, Jie Yan, Senbo Song, Xiaowen Zhejiang Univ Sch Mech Engn State Key Lab Fluid Power & Mechatron Syst Hangzhou 310027 Peoples R China Zhejiang Univ Sch Mech Engn Key Lab Adv Mfg Technol Zhejiang Prov Hangzhou 310027 Peoples R China Zhejiang Univ Coll Comp Sci & Technol State Key Lab CAD & CG Hangzhou 310027 Peoples R China

Building upon fully convolutional networks (FCNs), deep learning-based salient object detection (SOD) methods achieve gratifying performance in many vision tasks, including surface defect detection. However, most existing FCN-based methods still suffer from the coarse object edge predictions. The state-of-the-art methods employ intricate feature aggregation techniques to refine boundaries, but they are often too computational cost to deploy in the real application. This paper proposes a semantics guided detection paradigm for salient object detection. Guided atrous pyramid module is first applied on the top feature to segment complete salient semantics. Query context modules are further used to build relation maps between saliency and structural information from the top-down pathway. These two modules allow the semantic features to flow throughout the decoder phase, yielding detail enriched saliency predictions. Experimental results demonstrate that the proposed method performs favorably against the state-of-the-art methods on surface defect detection and SOD benchmarks. In addition, this method can detect at 27 FPS in a fully convolutional fashion without any post-processing, which has the potential for real-time detection.

关键词： Salient object detection Fully convolutional network encoder-decoder Query context network Automatic surface inspection

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Enriched Attention Network With Group-Wise Semantic for Visual Storytelling

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第7期45卷 8634-8645页

作者： Li, Tengpeng Wang, Hanli He, Bin Chen, Chang Wen Tongji Univ Dept Comp Sci & Technol Shanghai 201804 Peoples R China Tongji Univ Minist Educ Key Lab Embedded Syst & Serv Comp Shanghai 200092 Peoples R China Frontiers Sci Ctr Intelligent Autonomous Syst Shanghai 201210 Peoples R China Hong Kong Polytech Univ Dept Comp Hung Hom Kowloon Hong Kong Peoples R China

As a technically challenging topic, visual storytelling aims at generating an imaginary and coherent story with narrative multi-sentences from a group of relevant images. Existing methods often generate direct and rigid descriptions of apparent image-based contents, because they are not capable of exploring implicit information beyond images. Hence, these schemes could not capture consistent dependencies from holistic representation, impairing the generation of reasonable and fluent stories. To address these problems, a novel knowledge-enriched attention network with group-wise semantic model is proposed. Three main novel components are designed and supported by substantial experiments to reveal practical advantages. First, a knowledge-enriched attention network is designed to extract implicit concepts from external knowledge system, and these concepts are followed by a cascade cross-modal attention mechanism to characterize imaginative and concrete representations. Second, a group-wise semantic module with second-order pooling is developed to explore the globally consistent guidance. Third, a unified one-stage story generation model with encoder-decoder structure is proposed to simultaneously train and infer the knowledge-enriched attention network, group-wise semantic module and multi-modal story generation decoder in an end-to-end fashion. Substantial experiments on the visual storytelling datasets with both objective and subjective evaluation metrics demonstrate the superior performance of the proposed scheme as compared with other state-of-the-art methods. The source code of this work can be found in https://***.

关键词： encoder-decoder group-wise semantic knowledge-enriched attention multi-modal decoder visual storytelling

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Co-Attention Propagation Network for Zero-Shot Video Object Segmentation

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2023年 32卷 2348-2359页

作者： Pei, Gensheng Yao, Yazhou Shen, Fumin Huang, Dan Huang, Xingguo Shen, Heng-Tao Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China Chinese Acad Ordnance Sci Beijing 100089 Peoples R China Jilin Univ Coll Instrumentat & Elect Engn Changchun 130061 Peoples R China

Zero-shot video object segmentation (ZS-VOS) aims to segment foreground objects in a video sequence without prior knowledge of these objects. However, existing ZS-VOS methods often struggle to distinguish between foreground and background or to keep track of the foreground in complex scenarios. The common practice of introducing motion information, such as optical flow, can lead to overreliance on optical flow estimation. To address these challenges, we propose an encoder-decoder-based hierarchical co-attention propagation network (HCPN) capable of tracking and segmenting objects. Specifically, our model is built upon multiple collaborative evolutions of the parallel co-attention module (PCM) and the cross co-attention module (CCM). PCM captures common foreground regions among adjacent appearance and motion features, while CCM further exploits and fuses cross-modal motion features returned by PCM. Our method is progressively trained to achieve hierarchical spatio-temporal feature propagation across the entire video. Experimental results demonstrate that our HCPN outperforms all previous methods on public benchmarks, showcasing its effectiveness for ZS-VOS.

关键词： Video object segmentation hierarchical co-attention encoder-decoder cross-modal

来源：评论

学校读者我要写书评

暂无评论

Prediction of hourly PM10 concentration through a hybrid deep learning-based method

引用

EARTH SCIENCE INFORMATICS 2024年第1期17卷 37-49页

作者： Molaei, Sahar Nasabpour Salajegheh, Ali Khosravi, Hassan Nasiri, Amin Abadi, Abbas Ranjbar Saadat Univ Tehran Fac Nat Resources Dept Arid & Mt Reg Reclamat Karaj Iran Univ Tennessee Dept Biosyst Engn & Soil Sci Knoxville TN USA Atmospher Sci & Meteorol Res Ctr ASMERC Dept Meteorol Tehran Iran

Air pollution can have detrimental effects on human health as well as the environment. Particulate Matter (PM), as a global issue, is a type of air pollution that consists of small particles suspended in the air. Therefore, it is crucial to estimate and monitor levels of PM in the air in order to protect public health and the environment. This study proposed a novel hybrid method to apply the capability of two various deep learning models, namely, the encoder-decoder convolutional neural network and the Long Short-Term Memory (LSTM) model for PM10 prediction. The first model was utilized as a data argumentation method to enhance dataset diversity, and the LSTM model employed meteorological parameters and spatiotemporal factors to estimate the PM10 levels. The proposed technique achieved performance resulting in a coefficient of determination value of 0.88 and a mean absolute error value of 7.24. The results confirm that the developed hybrid method as an effective tool of PM prediction can be used to inform decision-making about policies and actions to reduce PM levels.

关键词： Particulate matter encoder-decoder CNN LSTM

来源：评论

学校读者我要写书评

暂无评论

MADLINK: Attentive multihop and entity descriptions for link prediction in knowledge graphs

引用

SEMANTIC WEB 2024年第1期15卷 83-106页

作者： Biswas, Russa Sack, Harald Alam, Mehwish Karlsruhe Inst Technol FIZ Karlsruhe Leibniz Inst Informat Infrastruct Karlsruhe Germany Karlsruhe Inst Technol Inst Appl Informat & Formal Descript Syst AIFB Karlsruhe Germany

Knowledge Graphs (KGs) comprise of interlinked information in the form of entities and relations between them in a particular domain and provide the backbone for many applications. However, the KGs are often incomplete as the links between the entities are missing. Link Prediction is the task of predicting these missing links in a KG based on the existing links. Recent years have witnessed many studies on link prediction using KG embeddings which is one of the mainstream tasks in KG completion. To do so, most of the existing methods learn the latent representation of the entities and relations whereas only a few of them consider contextual information as well as the textual descriptions of the entities. This paper introduces an attentive encoder-decoder based link prediction approach considering both structural information of the KG and the textual entity descriptions. Random walk based path selection method is used to encapsulate the contextual information of an entity in a KG. The model explores a bidirectional Gated Recurrent Unit (GRU) based encoder-decoder to learn the representation of the paths whereas SBERT is used to generate the representation of the entity descriptions. The proposed approach outperforms most of the state-of-the-art models and achieves comparable results with the rest when evaluated with FB15K, FB15K-237, WN18, WN18RR, and YAGO3-10 datasets.

关键词： Knowledge Graph embedding encoder-decoder link prediction path selection

来源：评论

学校读者我要写书评

暂无评论

Behavior Anomaly Detection Based On Multi-modal Feature Fusion And Its Application In English Teaching

JOURNAL OF APPLIED SCIENCE AND ENGINEERING

引用

JOURNAL OF APPLIED SCIENCE AND ENGINEERING 2025年第9期28卷 1657-1666页

作者： Kan, Lei Wang, Man Zhengzhou Vocat Coll Intelligent Technol Zhengzhou 451161 Peoples R China Natl Acad Governance Cent Comm CPC Grad Sch Party Sch Beijing 100089 Peoples R China Shenzhen MSU BIT Univ Coll Marxism Shenzhen 518000 Peoples R China

In order to improve the teaching quality, this paper proposes a multi-modal feature fusion-based abnormal behavior detection method, aiming at the problems of false detection, missing detection and imbalance of positive and negative samples in the abnormal behavior detection of students in class. The new method consists of encoder module, detection module and decoder module. The encoder module is used to extract the characteristic information of students behavior image and transfer it to the detection module. The behavior detection module obtains more image information through the feature fusion group to reduce the color distortion and artifacts of the behavior image, and transfers the obtained image information to the deep normalization correction convolution block to reduce the covariate shift and make the model easier to train. The multi-path feature convolution block can obtain image information with richer texture details. Finally, the decoder module converts the low-dimensional feature mapping back to the high-dimensional original input space through deconvolution and up-sampling operations to obtain the behavior detection image.

关键词： Abnormal behavior detection Multimodal feature fusion encoder-decoder Multi-path feature convolution block

来源：评论

学校读者我要写书评

暂无评论

A Framework for Compound Interrupted Sampling Repeater Jamming Parameter Measurement

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Lv, Qinzhe Liu, Liyi Wu, Yaojun Peng, Mimi Quan, Yinghui Xidian Univ Sch Elect Engn Dept Remote Sensing Sci & Technol Key Lab Collaborat Intelligence SystMinist Edc Xian 710071 Peoples R China Xidian Univ Xian Key Lab Adv Remote Sensing Xian 710071 Peoples R China

Active compound jamming, particularly compound interrupted sampling repeater jamming (ISRJ), possesses excellent flexibility and jamming effectiveness, making it one of the major threats to radar systems. Accurately measuring the key parameters of each ISRJ component within the compound ISRJ can provide critical prior information for subsequent anti-jamming efforts. However, most of the existing ISRJ parameter measurement methods target a single ISRJ and lack in-depth research on the measurement of compound ISRJ parameters. Therefore, we propose a unified framework for compound ISRJ parameter measurement that contains a compound ISRJ separation network based on an encoder-decoder architecture and a parameter regression module for measuring the key parameters of each ISRJ component in the compound ISRJ. Experimental results indicate that the proposed framework achieves parameter measurement accuracies of over 89% and 85% for dual-compound and multicompound ISRJ, respectively, significantly outperforming existing methods.

关键词： Compounds Jamming Training Time-domain analysis Feature extraction Time measurement Analytical models Repeaters Kernel Decoding Channel attention compound interrupted sampling repeater jamming (ISRJ) encoder-decoder jamming separation parameter measurement

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Standard Sign Language Discrimination

引用

IEEE ACCESS 2023年 11卷 125822-125834页

作者： Zhang, Menglin Yang, Shuying Zhao, Min Tianjin Univ Technol Sch Comp Sci & Engn Tianjin 300384 Peoples R China Minist Educ Key Lab Comp Vis & Syst Tianjin 300384 Peoples R China

General sign language recognition models are only designed for recognizing categories, i.e., such models do not discriminate standard and nonstandard sign language actions made by learners. It is inadequate to use in a sign language education software. To address this issue, this paper proposed a sign language category and standardization correctness discrimination model for sign language education. The proposed model is implemented with a hand detection and standard sign language discrimination method. For hand detection, the proposed method utilizes flow-guided features and acquires relevant proposals using stable and flow key frame detections. This model can resolve the inconsistency between the forward optical flow and the box center point offset. In addition, the proposed method employs an encoder-decoder model structure for sign language correctness discrimination. The encoder model combines 3D convolution and 2D deformable convolution results with residual structures, and it implements a sequence attention mechanism. A Sign Language Correctness Discrimination dataset (SLCD dataset) was also constructed in this study. In this dataset, each sign language video has two recognition labels, i.e., sign language category and standardization category. The semi-supervised learning method was employed to generate pseudo hand position labels. The hand detection model was getting sufficiently high hand detection result. The sign language correctness discrimination model was tested with hand patches or full images. SLCD dataset is available at https://***/10.21227/p9sn-dz70.

关键词： Sign language Encoding Video coding Object detection Three-dimensional displays Convolution Gesture recognition Assistive technologies Semisupervised learning Educational courses Software packages Continuous sign language recognition encoder-decoder tubelet video object detection 3D convolution

来源：评论

学校读者我要写书评

暂无评论

Real-time efficient semantic segmentation network based on improved ASPP and parallel fusion module in complex scenes

引用

JOURNAL OF REAL-TIME IMAGE PROCESSING 2023年第3期20卷 1-12页

作者： Ding, Peng Qian, Huaming Zhou, Yipeng Yan, Shuya Feng, Shibao Yu, Shuang Harbin Engn Univ Coll Intelligent Syst Sci & Engn Harbin 150001 Peoples R China

Semantic segmentation can help the perception link to better build an understanding of complex scenes, and can assist the unmanned system to better perceive the scene content. To address the problem of detailed information loss and segmentation edge blur in the semantic segmentation task for complex scenes, we propose a modified version of Deeplabv3+ based on the improved ASPP and fusion module. Firstly, we propose an RA-ASPP module combining residual network and asymmetric atrous convolution block (AACB), which further enriches the scale of feature extraction and achieves denser multi-scale feature extraction. It significantly enhances the representation power of the network. Then, we propose a parallel fusion module named convolution combine with bottleneck block (CBB), which combines 1 x 1 convolution and bottleneck block to reduce the information loss in the whole network transmission process. We perform ablation experiments on the PASCAL VOC2012 dataset. When the backbone is Xception, the Mean Intersection over Union (MIoU) of Ours1 is 79.78% . At the cost of 1.72 frames per second (FPS), its MIoU is 2.81% faster than Deeplabv3+. The proposed modules significantly improve the accuracy in semantic segmentation and achieve segmentation results comparable to state-of-the-art algorithms. When MobileNetV2 is the backbone, Ours2 achieves 37.54FPS and a MIoU of 73.32% , which ensures a balance between real-time segmentation speed and accuracy. In summary, our proposed modified module improves the segmentation performance of Deeplabv3+, and the different backbones also provide additional options for semantic segmentation tasks in complex scenes.

关键词： Semantic segmentation Deeplabv3+ ASPP encoder-decoder Atrous convolution

来源：评论

学校读者我要写书评

暂无评论

Multi-scale boundary neural network for gastric tumor segmentation

引用

VISUAL COMPUTER 2023年第3期39卷 915-926页

作者： Wang, Pengfei Li, Yunqi Sun, Yaru He, Dongzhi Wang, Zhiqiang Beijing Univ Technol Fac Informat Technol Beijing Peoples R China Chinese Peoples Liberat Army Gen Hosp Med Ctr 2 Dept Gastroenterol Beijing 100853 Peoples R China Chinese Peoples Liberat Army Gen Hosp Natl Clin Res Ctr Geriatr Dis Beijing 100853 Peoples R China Chinese Peoples Liberat Army Gen Hosp Med Ctr 1 Dept Gastroenterol Beijing 100853 Peoples R China

At present, gastric cancer patients account for a large proportion of all tumor patients. Gastric tumor image segmentation can provide a reliable additional basis for the clinical analysis and diagnosis of gastric cancer. However, the existing gastric cancer image datasets have disadvantages such as small data sizes and difficulty in labeling. Moreover, most existing CNN-based methods are unable to generate satisfactory segmentation masks without accurate labels, which are due to the limited context information and insufficient discriminative feature maps obtained after the consecutive pooling and convolution operations. This paper presents a gastric cancer lesion dataset for gastric tumor image segmentation research. A multiscale boundary neural network (MBNet) is proposed to automatically segment the real tumor area in gastric cancer images. MBNet adopts encoder-decoder architecture. In each stage of the encoder, a boundary extraction refinement module is proposed for obtaining multi granular edge information and refinement firstly. Then, we build a selective fusion module to selectively fuse features from the different stages. By cascading the two modules, the richer context and fine-grained features of each stage are encoded. Finally, the astrous spatial pyramid pooling is improved to obtain the remote dependency relationship of the overall context and the fine spatial structure information. The experimental results show that the accuracy of the model reaches 92.3%, the similarity coefficient (DICE) reaches 86.9%, and the performance of the proposed method on the CVC-ClinicDB and Kvasir-SEG datasets also outperforms existing approaches.

关键词： Gastric tumor segmentation encoder-decoder Convolutional neural network Deep learning

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：