检索结果-内蒙古大学图书馆

Abnormal behavior detection algorithm based on multi-branch convolutional fusion neural network

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第15期82卷 22723-22740页

作者： Xu, Zheng Lu, Yuanyao North China Univ Technol Sch Informat Sci & Technol Beijing Peoples R China

The recognition of abnormal behavior in surveillance video is the focus of current research, which has high research value and broad application possibilities. Its main applications are in the fields of intelligent surveillance, intelligent security, and smart cities, and it is of great significance to study the recognition of abnormal behaviors. Because of the complexity of human movement and the variability of the external environment, the recognition and detection of abnormal behaviors have some challenges. The recognition and detection of abnormal human behaviors in surveillance video still needs further research and development. This paper uses the multi-branch convolutional neural network to extract the spatial features of video frames for the first time, and as an encoder to pass the condensed features to the Gated Recurrent Unit (GRU), which extracts Temporal features from multiple video frames. And then the Gated Recurrent Unit output the result as the decoder. We did a series of comparative experiments on UCF-Crime dataset. And finally, we achieved an accuracy of 86.78% in the test set. The experimental results show that our multi-branch convolutional fusion neural network is better than previous surveillance video abnormal behavior recognition algorithms. At the same time, in order to verify the generalization performance and efficiency of the algorithm, we also conducted an experimental validation on the UCF-101 dataset in this paper, and the results show that the algorithm in this paper can also show a high accuracy rate on the UCF-101 dataset, and the speed of the algorithm is almost close to that of the C3D method with improved accuracy rate, making it possible to develop simple recognition applications based on the algorithm studied in this paper subsequently.

关键词： Abnormal behavior detection Multi-branch convolution GRU encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Paraphrase Generation and Supervised Learning for Improved Automatic Short Answer Grading

引用

INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE IN EDUCATION 2024年第4期34卷 1627-1670页

作者： Ouahrani, Leila Bennouar, Djamal Bouira Univ Fac Appl Sci Comp Sci Dept LIM Lab Bouira 10000 Algeria

We consider the reference-based approach for Automatic Short Answer Grading (ASAG) that involves scoring a textual constructed student answer comparing to a teacher-provided reference answer. The reference answer does not cover the variety of student answers as it contains only specific examples of correct answers. Considering other language variants of the reference answer can handle variability in student responses and improve scoring accuracy. Alternative reference answers may be possible, but manually creating them is expensive and time-consuming. In this paper, we consider two issues: First, we need to automatically generate various reference answers that can handle the diversity of student answers. Second, we should provide an accurate grading model that improves sentence similarity computation using multiple reference answers. Therefore, our proposed approach to solve both problems highlights two components. First, we provide a sequence-to-sequence deep learning model that targets generating plausible paraphrased reference answers conditioned on the provided reference answer. Secondly, we propose a supervised grading model based on sentence embedding features. The grading model enriches features to improve accuracy considering multiple reference answers. Experiments are conducted both in Arabic and English. They show that the paraphrase generator produces accurate paraphrases. Using multiple reference answers, the proposed grading model achieves a Root Mean Square Error of 0,6955, a Pearson correlation of 88,92% for the Arabic dataset, an RMSE of 0,7790, and a Pearson correlation of 73,50% for the English dataset. While fine-tuning pre-trained transformers on the English dataset provided state-of-the-art performance (RMSE: 0.7620), our approach yields comparable results. Simple to construct, load, and embed into the Learning Management System question engine with low computational complexity, the proposed approach can be easily integrated into the Learning Ma

关键词： Short Answer Grading Paraphrase generation Automatic reference answer generation encoder-decoder Natural Language Processing

来源：评论

学校读者我要写书评

暂无评论

High-resolution optical remote sensing image change detection based on dense connection and attention feature fusion network

引用

PHOTOGRAMMETRIC RECORD 2023年第184期38卷 498-519页

作者： Peng, Daifeng Zhai, Chenchen Zhang, Yongjun Guan, Haiyan Nanjing Univ Informat Sci & Technol Sch Remote Sensing & Geomat Engn Nanjing Peoples R China Minist Nat Resources Key Lab Natl Geog Census & Monitoring Wuhan Peoples R China Wuhan Univ Sch Remote Sensing Informat Engn Wuhan Peoples R China Nanjing Univ Informat Sci & Technol Sch Remote Sensing & Geomat Engn Nanjing 210044 Peoples R China

The detection of ground object changes from bi-temporal images is of great significance for urban planning, land-use/land-cover monitoring and natural disaster assessment. To solve the limitation of incomplete change detection (CD) entities and inaccurate edges caused by the loss of detailed information, this paper proposes a network based on dense connections and attention feature fusion, namely Siamese NestedUNet with Attention Feature Fusion (SNAFF). First, multi-level bi-temporal features are extracted through a Siamese network. The dense connections between the sub-nodes of the decoder are used to compensate for the missing location information as well as weakening the semantic differences between features. Then, the attention mechanism is introduced to combine global and local information to achieve feature fusion. Finally, a deep supervision strategy is used to suppress the problem of gradient vanishing and slow convergence speed. During the testing phase, the test time augmentation (TTA) strategy is adopted to further improve the CD performance. In order to verify the effectiveness of the proposed method, two datasets with different change types are used. The experimental results indicate that, compared with the comparison methods, the proposed SNAFF achieves the best quantitative results on both datasets, in which F1, IoU and OA in the LEVIR-CD dataset are 91.47%, 84.28% and 99.13%, respectively, and the values in the CDD dataset are 96.91%, 94.01% and 99.27%, respectively. In addition, the qualitative results show that SNAFF can effectively retain the global and edge information of the detected entity, thus achieving the best visual performance. This paper proposes a novel change detection (CD) method based on dense connections and attention feature fusion, which is capable of recovering detailed information as well as capturing global and local information. A deep supervision module is introduced to further improve the CD performance. Extensive experiment

关键词： attention mechanism change detection dense connection encoder-decoder feature fusion Siamese network

来源：评论

学校读者我要写书评

暂无评论

Cross-Lingual Word Alignment for ASEAN Languages with Contrastive Learning

Cross-Lingual Word Alignment for ASEAN Languages with Contra...

引用

28th International Conference on Asian Language Processing (IALP)

作者： Zhang, Jingshen Qiu, Xinying Shen, Teng Wang, Wenyu Zhang, Kailin Feng, Wenhe Guangdong Univ Foreign Studies Sch Informat Sci & Technolgy Guangzhou Peoples R China Guangdong Univ Foreign Studies Lab Language Engn & Comp Guangzhou Peoples R China Hohai Univ Coll Comp & Software Engn Nanjing Peoples R China

ISBN: (纸本)9798331540869;9798331540852

Cross-lingual word alignment plays a crucial role in various natural language processing tasks, particularly for low-resource languages. Recent study proposes a BiLSTM-based encoder-decoder model that outperforms pre-trained language models in low-resource settings. However, their model only considers the similarity of word embedding spaces and does not explicitly model the differences between word embeddings. To address this limitation, we propose incorporating contrastive learning into the BiLSTM-based encoder-decoder framework. Our approach introduces a multi-view negative sampling strategy to learn the differences between word pairs in the shared cross-lingual embedding space. We evaluate our model on five bilingual aligned datasets spanning four ASEAN languages: Lao, Vietnamese, Thai, and Indonesian. Experimental results demonstrate that integrating contrastive learning consistently improves word alignment accuracy across all datasets, confirming the effectiveness of the proposed method in low-resource scenarios. We will release our data set and code to support future research on ASEAN or more low-resource word alignment.

关键词： Cross-Lingual Word Alignment Contrastive Learning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Image caption generation using transformer learning methods: a case study on instagram image

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第15期83卷 46397页

作者： Dittakan, Kwankamon Prompitak, Kamontorn Thungklang, Phutphisit Wongwattanakit, Chatchawan Prince Songkla Univ Coll Comp Phuket Campus Phuket Thailand Prince Songkla Univ Fac Hospitality & Tourism Phuket Campus Phuket Thailand

Nowadays, images are being used more extensively for communication purposes. A single image can convey a variety of stories, depending on the perspective and thoughts of everyone who views it. To facilitate comprehension, inclusion image captions is highly beneficial, especially for individuals with visual impairments who can read Braille or rely on audio descriptions. The purpose of this research is to create an automatic captioning system that is easy to understand and quick to generate. This system can be applied to other related systems. In this research, the transformer learning process is applied to image captioning instead of the convolutional neural networks (CNN) and recurrent neural networks (RNN) process which has limitations in processing long-sequence data and managing data complexity. The transformer learning process can handle these limitations well and more efficiently. Additionally, the image captioning system was trained on a dataset of 5,000 images from Instagram that were tagged with the hashtag "Phuket" (#Phuket). The researchers also wrote the captions themselves to use as a dataset for testing the image captioning system. The experiments showed that the transformer learning process can generate natural captions that are close to human language. The generated captions will also be evaluated using the Bilingual Evaluation Understudy (BLEU) score and Metric for Evaluation of Translation with Explicit Ordering (METEOR) score, a metric for measuring the similarity between machine-translated text and human-written text. This will allow us to compare the resemblance between the researcher-written captions and the transformer-generated captions.

关键词： Image Captioning Transformer Learning Model Self-Attention Mechanism encoder-decoder Image feature extraction Instagram image

来源：评论

学校读者我要写书评

暂无评论

A Strip Dilated Convolutional Network for Semantic Segmentation

引用

NEURAL PROCESSING LETTERS 2023年第4期55卷 4439-4459页

作者： Zhou, Yan Zheng, Xihong Ouyang, Wanli Li, Baopu Xiangtan Univ Sch Automat & Elect Informat Xiangtan 411105 Peoples R China Univ Sydney Sch Elect & Informat Camperdown NSW 2006 Australia Baidu Res USA Sunnyvale CA 94089 USA

There are frequently a large number of strip objects in segmentation scenarios, and the use of conventional square convolution may yield redundant information. Based on our previously proposed SA-FFNet (Zhou et al. in Neurocomputing 453:50-59, 2021), we study the effect of strip sub-region information extraction on semantic segmentation and propose a network. Our method is conducive to extracting multi-scale strip objects that often appear in segmentation scenes, and using strip dilated convolution to further extract contextual dependencies in other directions. First, we propose a multi-scale strip pooling module that enables the backbone network to effectively obtain multi-scale contexts;Then, we introduce a strip dilated convolution module, which supplements the vertical contexts of the strip pooling by using strip dilated convolution;Finally, we construct a novel network integrating the proposed two modules. The method explicitly takes horizontal and vertical contexts of multi-scale strip objects into consideration, so that scene understanding could benefit from long-range dependencies. The experimental results on the widely used PASCAL VOC 2012 and Cityscapes scene analysis benchmark datasets, which are better than the existing OCRNet, DeeplabV3+, SPNet, etc, both qualitatively and quantitatively.

关键词： Semantic segmentation Multi-scale contexts encoder-decoder Multi-scale strip pooling module Strip dilated convolution module

来源：评论

学校读者我要写书评

暂无评论

MSPNet: Multi-stage progressive network for image denoising

引用

NEUROCOMPUTING 2023年 517卷 71-80页

作者： Bai, Yu Liu, Meiqin Yao, Chao Lin, Chunyu Zhao, Yao Beijing Jiaotong Univ Inst Informat Sci Beijing 100044 Peoples R China Beijing Jiaotong Univ Beijing Key Lab Adv Informat Sci & Network Technol Beijing 100044 Peoples R China Univ Sci & Technol Beijing Sch Comp & Commun Engn Beijing 100083 Peoples R China

Image denoising which aims to restore a high-quality image from the noisy version is one of the most challenging tasks in the low-level computer vision tasks. In this paper, we propose a multi-stage progres-sive denoising network (MSPNet) and decompose the denoising task into some sub-tasks to progressively remove noise. Specifically, MSPNet is composed of three denoising stages. Each stage combines a feature extraction module (FEM) and a mutual-learning fusion module (MFM). In the feature extraction module, an encoder-decoder architecture is employed to learn non-local contextualized features, and the channel attention blocks (CAB) are utilized to retain the local information of the image. In the mutual-learning fusion module, the criss-cross attention is introduced to balance the image spatial details and the contex-tualized information. Compared with the state-of-the-art works, experimental results show that MSPNet achieves notable improvements on both objective and subjective evaluations.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Multi-stage Image denoising Criss-cross attention encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

SDSCNet: an instance segmentation network for efficient monitoring of goose breeding conditions

引用

APPLIED INTELLIGENCE 2023年第21期53卷 25435-25449页

作者： Li, Jiao Su, Houcheng Li, Jianing Xie, Tianyu Chen, Yijie Yuan, Jianan Jiang, Kailin Duan, Xuliang Sichuan Agr Univ Coll Informat Engn 46 Xinkang Rd Yaan 625000 Sichuan Peoples R China Univ Macau Inst Collaborat Innovat Ave Univ Taipa 999077 Macau Peoples R China Tech Univ Munich Sch Computat Informat & Technol Arcisstr 21 D-80333 Munich Bayern Germany Sichuan Agr Univ Coll Sci 46 Xinkang Rd Yaan 625000 Sichuan Provinc Peoples R China

Improve the scientific level of the goose breeding industry and help the development of intelligent agriculture. Instance Segmentation has a pivotal role when the breeders make decisions about geese breeding. It can be used for disease prevention, body size estimation and behavioural prediction, etc. However, instance segmentation requires high performance computing devices to run smoothly due to its rich output. To ameliorate this problem, this paper constructs a novel encoder-decoder module and proposes the SDSCNet model. The reasonable use of depth-separable convolution in the module reduces the number and size of model parameters and increase execution speed. Finally, SDSCNet model enables real-time identification and segmentation of individual geese with the accuracy reached *** compare this model with numerous mainstream instance segmentation models, and the final results demonstrate the excellent performance of our ***, deploying SDSCNet model on the embedded device Raspberry Pi 4 Model B can achieve effective detection of continuous moving scenes.

关键词： Deep learning Intelligent agriculture Goose breeding industry Instance segmentation encoder-decoder Real-time

来源：评论

学校读者我要写书评

暂无评论

Dual attention-based deep learning network for multi-class object semantic segmentation of tunnel point clouds

引用

AUTOMATION IN CONSTRUCTION 2023年 156卷

作者： Ji, Ankang Zhang, Limao Fan, Hongqin Xue, Xiaolong Dou, Yudan Hong Kong Polytech Univ Dept Bldg & Real Estate Hong Kong 999077 Peoples R China Hong Kong Polytech Univ Shenzhen Res Inst Shenzhen 518057 Guangdong Peoples R China Huazhong Univ Sci & Technol Natl Ctr Technol Innovat Digital Construct Sch Civil & Hydraul Engn Wuhan 430074 Peoples R China Guangzhou Univ Sch Management Guangzhou 510006 Guangdong Peoples R China Dalian Univ Technol Dept Construct Management Dalian 116024 Liaoning Peoples R China

Aiming to automatically segment multi-class objects on the tunnel point cloud, a deep learning network named dual attention-based point cloud network (DAPCNet) is developed in this paper to act on point clouds for segmentation. In the developed model, data normalization and feature aggregation are first processed to eliminate data discrepancies and enhance local features, after which the processed data are input into the built network layers based on the encoder-decoder architecture coupled with an improved 3D dual attention module to extract and learn features. Furthermore, a custom loss function called Facal Cross-Entropy ("FacalCE") is designed to enhance the model's ability to extract and learn features while addressing imbalanced data distribution. To validate the effectiveness and feasibility of the developed model, a dataset of tunnel point clouds collected from a real engineering project in China is employed. The experimental results indicate that (1) the developed model has excellent performance with Mean Intersection over Union (MIoU) of 0.8597, (2) the improved 3D dual attention module and "FacalCE" contribute to the model performance, respectively, and (3) the developed model is superior to other state-of-the-art methods, such as PointNet and DGCNN. In summary, the DAPCNet model exhibits exceptional performance, offering effective and accurate results for segmenting multi-class objects within tunnel point clouds.

关键词： Deep learning Semantic segmentation Tunnel point cloud encoder-decoder 3D dual attention module

来源：评论

学校读者我要写书评

暂无评论

A Framework for Image Captioning Based on Relation Network and Multilevel Attention Mechanism

引用

NEURAL PROCESSING LETTERS 2023年第5期55卷 5693-5715页

作者： Sharma, Himanshu Srivastava, Swati GLA Univ Mathura Dept Comp Engn & Applicat Mathura India

Understanding different semantic concepts, such as objects and their relationships in an image, and integrating them to produce a natural language description is the goal of the image captioning task. Thus, it needs an algorithm to understand the visual content of a given image and translates it into a sequence of output words. In this paper, a local relation network is designed over the objects and image regions which not only discovers the relationship between the object and the image regions but also generates significant context-based features corresponding to every region in the image. Inspired by transformer model, we have employed a multilevel attention comprising of self-attention and guided attention to focus on a given image region and its related image regions, thus enhancing the image representation capability of the proposed method. Finally, a variant of traditional long-short term memory, which uses an attention mechanism, is employed which focuses on relevant contextual information, spatial locations, and deep visual features. With these measures, the proposed model encodes an image in an improved way, which gives the model significant cues and thus leads to improved caption generation. Extensive experiments have been performed on three benchmark datasets: Flickr30k, MSCOCO, and Nocaps. On Flickr30k, the obtained evaluation scores are 31.2 BLEU@4, 23.5 METEOR, 51.5 ROUGE, 65.6 CIDEr and 17.2 SPICE. On MSCOCO, the proposed model has attained 42.4 BLEU@4, 29.4 METEOR, 59.7 ROUGE, 125.7 CIDEr and 23.2 SPICE. The overall CIDEr score on Nocaps dataset achieved by the proposed model is 114.3. The above scores clearly show the superiority of the proposed method over the existing methods.

关键词： Relation network Semantic Attention encoder-decoder

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：