检索结果-内蒙古大学图书馆

17th European Conference on Computer Vision (ECCV)

作者： Zhao, Wenqi Gao, Liangcai Peking Univ Wangxuan Inst Comp Technol Beijing Peoples R China

ISBN: (纸本)9783031198144;9783031198151

The Transformer-based encoder-decoder architecture has recently made significant advances in recognizing handwritten mathematical expressions. However, the transformer model still suffers from the lack of coverage problem, making its expression recognition rate (ExpRate) inferior to its RNN counterpart. Coverage information, which records the alignment information of the past steps, has proven effective in the RNN models. In this paper, we propose CoMER, a model that adopts the coverage information in the transformer decoder. Specifically, we propose a novel Attention Refinement Module (ARM) to refine the attention weights with past alignment information without hurting its parallelism. Furthermore, we take coverage information to the extreme by proposing self-coverage and cross-coverage, which utilize the past alignment information from the current and previous layers. Experiments show that CoMER improves the ExpRate by 0.61%/2.09%/1.59% compared to the current state-of-the-art model, and reaches 59.33%/59.81%/62.97% on the CROHME 2014/2016/2019 test sets. (Source code is available at https://***/Green-Wood/CoMER)

关键词： Handwritten mathematical expression recognition Transformer Coverage Alignment encoder-decoder model

来源：评论

学校读者我要写书评

暂无评论

Visual Prompt Learning for Chinese Handwriting Recognition 18th

Visual Prompt Learning for Chinese Handwriting Recognition

引用

18th International Conference on Document Analysis and Recognition (ICDAR)

作者： Yao, Gang Ding, Ning Zhao, Tianqi Zhao, Kemeng Tang, Pei Tao, Yao Peng, Liangrui Tsinghua Univ Dept Elect Engn Beijing Peoples R China Tsinghua Univ Beijing Natl Res Ctr Informat Sci & Technol Beijing Peoples R China Huawei Technol Noahs Ark Lab Shenzhen Peoples R China

ISBN: (纸本)9783031705328;9783031705335

Recognizing Chinese handwriting in unconstrained scenarios remains a challenging task due to wide variations in writing styles and imaging conditions. Recently, prompt learning in natural language processing has shown success in leveraging context awareness in various domains. This paper proposes to incorporate visual prompt learning into an encoder-decoder model for handwriting recognition. For the encoder, multi-scale meta prompts are incorporated to utilize contextual information in internal feature representations. For the decoder, additional character-level visual prompts are used along with the embeddings of previously predicted text to guide the decoding process. Experiments conducted on the SCUT-HCCDoc, SCUT-EPT and CASIA-HWDB Chinese handwriting datasets validate the effectiveness of the proposed methods.

关键词： handwriting recognition visual prompt learning encoder-decoder model

来源：评论

学校读者我要写书评

暂无评论

Real Time Machine Translation System between Indian Languages 6

Real Time Machine Translation System between Indian Language...

引用

6th International Conference on Trends in Electronics and Informatics (ICOEI)

作者： Patil, Aarati H. Patil, Snehal S. Patil, Shubham M. Nagarhalli, Tatwadarshi P. Vidyavardhinis Coll Engn & Technol Comp Engn Vasai India

ISBN: (纸本)9781665483285;9781665483292

Language understanding is one of those perpetual challenges which has dogged research from many decades. As a means of connecting with others, but communication is not limited to a single language. India contains around 121 different languages. As a result, there is a linguistic barrier. Natural Language Processing is the process of developing a communicational interface between machines and humans. A model that turns the supplied source language text (Marathi) into the desired language text (Gujarati) using Text to Text Translation has been developed. Because LSTMs allow us with a vast variety of parameters like as learning rates, input and output biases, and there is no need for existence, this model is constructed by adding multilingual features to the LSTM model based on deep learning Principles. The goal of the proposed is to create a deep learning-based translation system. The suggested system uses a variety of models to perform text-to-text translation, after which the input text will be translated into the target language (text).

关键词： Long Short-Term Memory encoder-decoder model Neural Machine Translation Indian language

来源：评论

学校读者我要写书评

暂无评论

Capturing intrinsic features from field data for predicting the production of natural gas

GEOENERGY SCIENCE AND ENGINEERING

引用

GEOENERGY SCIENCE AND ENGINEERING 2023年 227卷

作者： Wang, Xin Wang, Yong-Sheng Pang, Lan-Su Jiang, Tao Chen, Yu-Fan Wang, Yang Mei, Qing-Yan Qing, Sheng-Lan Jiang, Wei Southwest Petr Univ Sch Comp Sci Chengdu 610500 Peoples R China PetroChina Southwest Oil & Gasfield Co Explorat & Dev Res Inst Chengdu 610043 Peoples R China

Production prediction for gas wells is a popular topic in reservoir engineering as it plays a crucial role in the formulation of development plans. Most traditional techniques can be categorized into two types, i.e., numerical simulation methods and decline curve analysis, while none of them can precisely capture the varying trends of gas production, which leads to poor prediction results. To tackle the issue, we propose a comprehensive approach that works in a pipeline manner to learn intrinsic features from data for production prediction. (1) We propose to group wells with a clustering algorithm which does not need the pre-specified cluster number. To group wells even better, two parameters, i.e., dynamic volatility and static volatility of productions are introduced and involved for clustering. (2) We devise a technique that is based on the maximum likelihood estimation, for well matching. (3) We develop an encoder-decoder model for learning varying trends of well productions, by considering geological, engineering and production data simultaneously. (4) On real-life data, we conduct intensive experiments and find that our approach achieves superior performance and substantially outperforms its counterparts.

关键词： Natural gas Production prediction encoder-decoder model Well clustering & matching

来源：评论

学校读者我要写书评

暂无评论

DeepLabV3-Refiner-Based Semantic Segmentation model for Dense 3D Point Clouds

引用

REMOTE SENSING 2021年第8期13卷

作者： Kwak, Jeonghoon Sung, Yunsick Dongguk Univ Seoul Dept Multimedia Engn 30 Pildong Ro 1 Gil Seoul 04620 South Korea

Three-dimensional virtual environments can be configured as test environments of autonomous things, and remote sensing by 3D point clouds collected by light detection and range (LiDAR) can be used to detect virtual human objects by segmenting collected 3D point clouds in a virtual environment. The use of a traditional encoder-decoder model, such as DeepLabV3, improves the quality of the low-density 3D point clouds of human objects, where the quality is determined by the measurement gap of the LiDAR lasers. However, whenever a human object with a surrounding environment in a 3D point cloud is used by the traditional encoder-decoder model, it is difficult to increase the density fitting of the human object. This paper proposes a DeepLabV3-Refiner model, which is a model that refines the fit of human objects using human objects whose density has been increased through DeepLabV3. An RGB image that has a segmented human object is defined as a dense segmented image. DeepLabV3 is used to make predictions of dense segmented images and 3D point clouds for human objects in 3D point clouds. In the Refiner model, the results of DeepLabV3 are refined to fit human objects, and a dense segmented image fit to human objects is predicted. The dense 3D point cloud is calculated using the dense segmented image provided by the DeepLabV3-Refiner model. The 3D point clouds that were analyzed by the DeepLabV3-Refiner model had a 4-fold increase in density, which was verified experimentally. The proposed method had a 0.6% increase in density accuracy compared to that of DeepLabV3, and a 2.8-fold increase in the density corresponding to the human object. The proposed method was able to provide a 3D point cloud that increased the density to fit the human object. The proposed method can be used to provide an accurate 3D virtual environment by using the improved 3D point clouds.

关键词： dynamic object deep learning encoder-decoder model 3D point cloud LiDAR data fusion dense semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

MS-Pointer Network: Abstractive Text Summary Based on Multi-Head Self-Attention

引用

IEEE ACCESS 2019年 7卷 138603-138613页

作者： Guo, Qian Huang, Jifeng Xiong, Naixue Wang, Pan Shanghai Normal Univ Coll Informat Mech & Elect Engn Shanghai 200030 Peoples R China Northeastern State Univ Dept Math & Comp Sci Tahlequah OK 74464 USA Huanggang Jinghe Sch Xixian New Area Xian 713702 Shaanxi Peoples R China

.Abstractive text summarization plays an important role in the field of natural language processing. However, the abstractive text summary adopts deep learning research method to predict words often appears semantic inaccuracy and repetition and so on. at the present stage, in order to solve the problem that semantic inaccuracy, we propose an MS-Pointer Network that based on the multi-head self-attention mechanism, which a multi-head self-attention mechanism is introduced in the basic encoder-decoder model. Since multi-head self-attention can combine input words into the encoder-decoder arbitrarily, and given a higher weight of these words that combination of the semantics, thereby achieving the purpose of enhancing the semantic features of the text, so that the abstractive text summary is more semantically structured, And the multi-head self-attention mechanism add the position information of the input text, which can enhance the semantic representation of the text. At the same time, in order to solve the problem of out of vocabulary, a pointer network is introduced on the seqtoseq with a multi-head attention mechanism. The model is referred to as MS-Pointer Network. We used CNN/Daily Mail and Gigaword datasets to validate our model, and uses the ROUGE metric to measure model. Experiments have shown that abstractive text summaries generated using the multi-head self-attention mechanism outperforming current open state-of-the-art two points averagely.

关键词： Abstractive text summarization encoder-decoder model multi-head self-attention mechanism

来源：评论

学校读者我要写书评

暂无评论

An adaptive optimization method toward batch-wise variable set point of outlet moisture content for the tobacco drying process

引用

DRYING TECHNOLOGY 2023年第13期41卷 2156-2170页

作者： Gao, Yulei Wang, Tianyu Zhou, Xiaolong Li, Mian Zhang, Chiyuan Qin, Peng Yang, Yaojing Zhang, Libin Hongta Tobacco Grp Co Ltd Yuxi Peoples R China Shanghai Jiao Tong Univ Shanghai Peoples R China

The tobacco drying process in the cigarette production has an important effect on the final product quality. Therefore, the intelligent control methods have been widely investigated to ensure the stability of tobacco's outlet moisture content. The existing work mostly uses a relatively fixed set point of the outlet moisture content for different tobacco batches, which can lead to unforeseen product quality after several processes following the drying process and inaccessible amount of dehydration for the rotary dryer. Some tobacco moisture prediction methods have been studied recently while the relationship with the intelligent control methods remain largely unexplored. To deal with these issues, a novel method is proposed in this paper to identify the optimal set point of the drying outlet moisture content for each tobacco batch. An encoder-decoder model is first developed to forecast the post-drying moisture trajectory. Then, an adaptive filter with specially designed mechanisms and a confidence interval of the dehydration level are constructed to obtain the design constraints. Based on all above, a constrained optimization problem is formulated and solved by the genetic algorithm. Extensive experiments on 895 tobacco batches from a large cigarette factory are carried out, which involves both algorithmic evaluation and field test. It turns out that the proposed method achieves the superior performance and leads to an improvement of the product quality in real production.

关键词： Tobacco drying process final product quality optimal set point encoder-decoder model adaptive filter genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

encoder-decoder Architecture for Ultrasound IMC Segmentation and cIMT Measurement

引用

SENSORS 2021年第20期21卷 6839页

作者： Al-Mohannadi, Aisha Al-Maadeed, Somaya Elharrouss, Omar Sadasivuni, Kishor Kumar Qatar Univ Dept Comp Sci & Engn POB 2713 Doha Qatar Qatar Univ Ctr Adv Mat POB 2713 Doha Qatar

Cardiovascular diseases (CVDs) have shown a huge impact on the number of deaths in the world. Thus, common carotid artery (CCA) segmentation and intima-media thickness (IMT) measurements have been significantly implemented to perform early diagnosis of CVDs by analyzing IMT features. Using computer vision algorithms on CCA images is not widely used for this type of diagnosis, due to the complexity and the lack of dataset to do it. The advancement of deep learning techniques has made accurate early diagnosis from images possible. In this paper, a deep-learning-based approach is proposed to apply semantic segmentation for intima-media complex (IMC) and to calculate the cIMT measurement. In order to overcome the lack of large-scale datasets, an encoder-decoder-based model is proposed using multi-image inputs that can help achieve good learning for the model using different features. The obtained results were evaluated using different image segmentation metrics which demonstrate the effectiveness of the proposed architecture. In addition, IMT thickness is computed, and the experiment showed that the proposed model is robust and fully automated compared to the state-of-the-art work.

关键词： carotid intima-media thickness IMT CCA segmentation deep learning encoder-decoder model

来源：评论

学校读者我要写书评

暂无评论

SED: Searching Enhanced decoder with switchable skip connection for semantic segmentation

引用

PATTERN RECOGNITION 2024年 149卷

作者： Zhang, Xian Quan, Zhibin Li, Qiang Zhu, Dejun Yang, Wankou Southeast Univ Sch Automat Nanjing 210096 Peoples R China SenseTime Res Beijing Peoples R China Tsinghua Univ Dept Hydraul Engn State Key Lab Hydrosci & Hydraul Engn Beijing 100084 Peoples R China

Neural architecture search (NAS) has shown excellent performance. However, existing semantic segmentation models rely heavily on pre-training on Image-Net or COCO and mainly focus on the designing of decoders. Directly training the encoder-decoder architecture search models from scratch to SOTA for semantic segmentation requires even thousands GPU days, which greatly limits the application of NAS. To address this issue, we propose a novel neural architecture Search framework for Enhanced decoder (SED). Utilizing the pre-trained hand-designing backbone and the searching space composed of light-weight cells, SED searches for a decoder which can perform high-quality segmentation. Furthermore, we attach switchable skip connection operations to search space, expanding the diversity of possible network structure. The parameters of backbone and operations selected in searching phrase are copied to retraining process. As a result, searching, pruning and retraining can be done in just 1 day. The experimental results show that the SED proposed in this paper only needs 1/4 of the parameters and calculation in contrast to hand-designing decoder, and obtains higher segmentation accuracy on Cityscapes. Transferring the same decoder architecture to other datasets, such as: Pascal VOC 2012, Camvid, ADE20K proves the robustness of SED.

关键词： NAS Semantic segmentation encoder-decoder model

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature selection using orthogonal encoder-decoder factorization

引用

INFORMATION SCIENCES 2024年 663卷

作者： Mozafari, Maryam Seyedi, Seyed Amjad Mohammadiani, Rojiar Pir Tab, Fardin Akhlaghian Univ Kurdistan Dept Comp Engn Sanandaj Iran

Unsupervised feature selection (UFS) is a fundamental task in machine learning and data analysis, aimed at identifying a subset of non -redundant and relevant features from a high -dimensional dataset. Embedded methods seamlessly integrate feature selection into model training, resulting in more efficient and interpretable models. Current embedded UFS methods primarily rely on self -representation or pseudo -supervised feature selection approaches to address redundancy and irrelevant feature issues, respectively. Nevertheless, there is currently a lack of research showcasing the fusion of these two approaches. This paper proposes the Orthogonal encoderdecoder factorization for unsupervised Feature Selection (OEDFS) model, combining the strengths of self -representation and pseudo -supervised approaches. This method draws inspiration from the self -representation properties of autoencoder architectures and leverages encoder and decoder factorizations to simulate a pseudo -supervised feature selection approach. To further enhance the part -based characteristics of factorization, orthogonality constraints and local structure preservation restrictions are incorporated into the objective function. The optimization process is based on the multiplicative update rule, ensuring efficient convergence. To assess the effectiveness of the proposed method, comprehensive experiments are conducted on 14 datasets and compare the results with eight state-of-the-art methods. The experimental results demonstrate the superior performance of the proposed approach in terms of UFS efficiency.

关键词： Unsupervised feature selection encoder-decoder model Self-representation learning Pseudo-supervised learning Nonnegative matrix factorization

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：