检索结果-内蒙古大学图书馆

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Zhu, Ziyi Zhao, Wenqi Gao, Liangcai Peking Univ Inst Comp Sci & Technol Beijing Peoples R China

ISBN: (纸本)9789819785100;9789819785117

Extensive researches have demonstrated the effectiveness of Image-to-Sequence (img2seq) approaches in table structure recognition (TSR) task. However, when dealing with long tables, these methods always suffer from the inherent limitations of their attention mechanism, which hinders the further progress of this technical route. Based on the repetitive nature of table body structures, we present a novel approach for compressing table HTML code, resulting in a significant reduction in the overall length of the HTML code by more than 65%. Additionally, to address the relatively complex structure of table heads and the dense arrangement of rows and cells in long tables, we integrate coverage information into the transformer decoder. Experiments show that our method achieves performance comparable to the state-of-the-art methods with a simple model structure. What's more, our method effectively mitigates the performance degradation commonly observed in img2seq methods when the length of the target sequence increases.

关键词： Table Structure Recognition encoder-decoder model Transformer

来源：评论

学校读者我要写书评

暂无评论

Explainable multi-step heating load forecasting: Using SHAP values and temporal attention mechanisms for enhanced interpretability

ENERGY AND AI

引用

ENERGY AND AI 2025年 20卷

作者： Neubauer, Alexander Brandt, Stefan Kriegel, Martin Tech Univ Berlin Hermann Rietschel Inst D-10587 Berlin Germany

The role of heating load forecasts in the energy transition is significant, given the considerable increase in the number of heat pumps and the growing prevalence of fluctuating electricity generation. While machine learning methods offer promising forecasting capabilities, their black-box nature makes them difficult to interpret and explain. The deployment of explainable artificial intelligence methodologies enables the actions of these machine learning models to be made transparent. In this study, a multi-step forecast was employed using an encoder-decoder model to forecast the hourly heating load for an multifamily residential building and a district heating system over a forecast horizon of 24-h. By using 24 instead of 48 lagged hours, the simulation time was reduced from 92.75 s to 45.80 sand the forecast accuracy was increased. The feature selection was conducted for four distinct methods. The Tree and Deep SHAP method yielded superior results in feature selection. The application of feature selection according to the Deep SHAP values resulted in a reduction of 3.98% in the training time and a 8.11% reduction in the NRMSE. The utilisation of local Deep SHAP values enables the visualisation of the influence of past input hours and individual features. By mapping temporal attention, it was possible to demonstrate the importance of the most recent time steps in a intrinsic way. The combination of explainable methods enables plant operators to gain further insights and trustworthi- ness from the purely data-driven forecast model, and to identify the importance of individual features and time steps.

关键词： Multi-step load forecasting SHAP values encoder-decoder model Attention mechanisms Feature selection

来源：评论

学校读者我要写书评

暂无评论

Multiclass Image Segmentation using Deep Residual encoder-decoder models in Highly Turbid Underwater Ambiances

INTERNATIONAL JOURNAL OF MATHEMATICAL ENGINEERING AND MANAGE...

引用

INTERNATIONAL JOURNAL OF MATHEMATICAL ENGINEERING AND MANAGEMENT SCIENCES 2024年第6期9卷 1510-1530页

作者： Haridas, T. P. Mithun Kamal, Suraj Balakrishnan, Arun A. Thomas, Rosemol Nezla, N. A. Balakrishnan, Kannan Supriya, M. H. Cochin Univ Sci & Technol Ctr Ocean Elect Lab CUCENTOL Dept Elect Kochi 682021 Kerala India Cochin Univ Sci & Technol Dept Comp Applicat Kochi 682021 Kerala India

Underwater environments, especially the coral reefs, are the habitat of many critically endangered species. Extensive monitoring of these aquatic ecosystems is essential for conserving and deep understanding of these vulnerable habitats. Monitoring by extracting details from underwater images of turbid, hazy marine environments is extremely challenging. In this work, a novel annotated dataset is created for three classes of objects in the images of coral reef environment considering fish, rock/coral and background for the Fish4Knowledge dataset, a benchmark dataset primarily for binary segmentation. This work also proposes a multiclass ResUnet based image segmentation model for the newly created multiclass annotations. Various encoder-decoder convolutional architectures were analysed and found that ResUnet exhibits better robustness. The performance of the multiclass ResUnet model is also analysed by optimizing with different cost functions. Various underwater noisy conditions are simulated in the test images to find the robustness of the model, and observed that the proposed model optimised with Jaccard loss performs better even in extremely noisy scenarios.

关键词： Underwater image encoder-decoder model Multi-class image segmentation Fish4Knowledge

来源：评论

学校读者我要写书评

暂无评论

Short-term Inland Vessel Trajectory Prediction with encoder-decoder models 25

Short-term Inland Vessel Trajectory Prediction with Encoder-...

引用

IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)

作者： Donandt, Kathrin Boettger, Karim Soeffker, Dirk Univ Duisburg Essen Inst Ship Technol Ocean Engn & Transport Syst ISM Duisburg Germany German Fed Waterway Engn & Res Inst Geesthacht Germany Univ Duisburg Essen Chair Dynam & Control SRS Duisburg Germany

ISBN: (数字)9781665468800

ISBN: (纸本)9781665468800

Accurate vessel trajectory prediction is necessary for save and efficient navigation. Deep learning-based prediction models, esp. encoder-decoders, are rarely applied to inland navigation specifically. Approaches from the maritime domain cannot directly be transferred to river navigation due to specific driving behavior influencing factors. Different encoder-decoder architectures, including a transformer encoder-decoder, are compared herein for predicting the next positions of inland vessels, given not only spatio-temporal information from AIS, but also river specific features. The results show that the reformulation of the regression task as classification problem and the inclusion of river specific features yield the lowest displacement errors. The standard LSTM encoder-decoder outperforms the transformer encoder-decoder for the data considered, but is computationally more expensive. In this study for the first time a transformer-based encoder-decoder model is applied to the problem of predicting the ship trajectory. Here, a feature vector using the river-specific context of navigation input parameters is established. Future studies can built on the proposed models, investigate the improvement of the computationally more efficient transformer, e.g. through further hyper-parameter optimization, and use additional river-specific information in the context representation to further increase prediction accuracy.

关键词： vessel trajectory prediction encoder-decoder model transformer inland navigation

来源：评论

学校读者我要写书评

暂无评论

encoder-decoder models in sequence-to-sequence learning: A survey of RNN and LSTM approaches

Encoder-decoder models in sequence-to-sequence learning: A s...

引用

作者： Yunong Zhang Civil Engineering College Xi'an University of Architecture and Technology

In today's information age, from natural language processing to audio signal processing, from time series analysis to machine translation, the application of sequence data involves various fields. encoder-decoder models, as a powerful approach to sequence modeling, have attracted extensive attention and research. This review paper aims to explore encoder-decoder models, focusing on the principles and operational steps of recurrent neural networks(RNN) and long short-term memory(LSTM), aiming to provide researchers and practitioners with a deep understanding of the fundamentals and applications of these models Condition. Through the analysis and summary of relevant literature, this study reveals the advantages of RNN and LSTM in sequence data processing;RNN structure is simple and effective, can process sequence input and output of any length, and can capture the time dependence in sequence data. But there is a problem of gradient disappearance, which makes it difficult to deal with long-term dependencies. To solve this problem, the LSTM model introduces different gating mechanisms, which effectively solve the gradient problem while better capturing long-term dependencies. Through the review of the principles and applications of the two, it provides a useful reference for further research and application.

关键词： encoder-decoder model RNN LSTM

来源：评论

学校读者我要写书评

暂无评论

Analytical study of the encoder-decoder models for ultrasound image segmentation

引用

SERVICE ORIENTED COMPUTING AND APPLICATIONS 2024年第1期18卷 81-100页

作者： Srivastava, Somya Vidyarthi, Ankit Jain, Shikha Jaypee Inst Informat Technol Dept Comp Sci Engn & Informat Technol Noida India

Accurate diagnosis and treatment planning for medical conditions rely heavily on the results of medical image segmentation. Medical images are available in many modalities like CT scans, MRI, histopathological, and ultrasound images. Among all, the real-time analysis of the ultrasound is the most complex as the internal organ's visualization requires experience from the radiologist. Diagnosing the medical conditions and unavailability of experienced radiologists during an emergency requires automated segmentation which heavily depends on computer-aided diagnostic systems. The new generation CAD systems are found to incorporate advanced deep learning algorithms to produce accurate segmentation results. While most of the segmentation models relate to the encoder-decoder model as the base architecture and thus evolve a variety of modifications in its pipeline architecture. This paper presents the analytical study of the various encoder- decoder based models like UNet, Residual UNet (Res-U-Net), Dense UNet (DenseUNet), Attention UNet, UNet + +, Double UNet, and U(2)Net (U-Squared-Net) on ultrasound image segmentation. Further, the paper presents the various trade-offs, application areas, open challenges, and performance analysis of these models on benchmark datasets, namely the HC18 Challenge dataset, CUM dataset, and B-mode Ultrasound Nerve Segmentation dataset. The performance analysis of these models is presented using the six state-of-the-art metrics like Dice coefficient, Jaccard index, sensitivity, specificity, Mean Absolute distance, and Housdorff Distance. Based on the above parameters U-2-Net (U-Squared-Net) outperformed all other neural network models for all three datasets. In terms of all four criteria (Dice Coefficient: 0.92, 0.89, 0.9, Jaccard Index: 0.81, 0.79, 0.81, Sensitivity: 0.86, 0.84, 0.86, Specificity: 0.97, 0.95, 0.96), the U2-Net (U-Squared-Net) model performed the best. Over the HC18 Challenge dataset, the CUM dataset, and the B-Mode Ultrasound

关键词： Medical image segmentation encoder-decoder model Artificial intelligence Deep neural network

来源：评论

学校读者我要写书评

暂无评论

Investigation of chemical structure recognition by encoder-decoder models in learning progress

引用

JOURNAL OF CHEMINFORMATICS 2023年第1期15卷 45-45页

作者： Nemoto, Shumpei Mizuno, Tadahaya Kusuhara, Hiroyuki Univ Tokyo Dept Pharmaceut Sci Bunkyo Tokyo Japan

Descriptor generation methods using latent representations of encoder-decoder (ED) models with SMILES as input are useful because of the continuity of descriptor and restorability to the structure. However, it is not clear how the structure is recognized in the learning progress of ED models. In this work, we created ED models of various learning progress and investigated the relationship between structural information and learning progress. We showed that compound substructures were learned early in ED models by monitoring the accuracy of downstream tasks and input- output substructure similarity using substructure-based descriptors, which suggests that existing evaluation methods based on the accuracy of downstream tasks may not be sensitive enough to evaluate the performance of ED models with SMILES as descriptor generation methods. On the other hand, we showed that structure restoration was time-consuming, and in particular, insufficient learning led to the estimation of a larger structure than the actual one. It can be inferred that determining the endpoint of the structure is a difficult task for the model. To our knowledge, this is the first study to link the learning progress of SMILES by ED model to chemical structures for a wide range of chemicals.

关键词： encoder-decoder model Descriptor

来源：评论

学校读者我要写书评

暂无评论

HandSegNet: Hand segmentation using convolutional neural network for contactless palmprint recognition

引用

IET BIOMETRICS 2022年第2期11卷 109-123页

作者： Ito, Koichi Suzuki, Yusei Kawai, Hiroya Aoki, Takafumi Fujio, Masakazu Kaga, Yosuke Takahashi, Kenta Tohoku Univ Grad Sch Informat Sci 6-6-05 Aramaki Sendai Miyagi 9808579 Japan Hitachi Ltd Yokohama Kanagawa Japan

Extracting a palm region with fixed location from an input hand image is a crucial task for palmprint recognition to realise reliable person authentication under contactless and unconstrained conditions. A palm region can be extracted from the fixed location using the gaps between fingers. An accurate and robust hand segmentation method is indispensable to extract a palm region from an image with complex background taken under various environments. In this study, HandSegNet, which is a hand segmentation method using Convolutional Neural Network (CNN) for contactless palmprint recognition, is proposed. HandSegNet employs a new CNN architecture consisting of an encoder-decoder model with a pyramid pooling module. Through performance evaluation using a set of synthesised hand images, HandSegNet exhibited the best segmentation results of 98.90% and 93.20% for accuracy and intersection over union, respectively. The effectiveness of HandSegNet in contactless palmprint recognition through experiments using a set of synthesised images of hand images is also demonstrated. Comparing the performance of palmprint recognition using three conventional methods and HandSegNet for palm region extraction, the proposed method has the lowest equal error rate of 4.995%, demonstrating its effectiveness in palm region extraction for contactless palmprint recognition.

关键词： convolutional neural network complex background synthesised hand images contactless conditions CNN pyramid pooling module palm region extraction reliable person authentication feature extraction HandSegNet palmprint recognition contactless palmprint recognition fixed location robust hand segmentation method convolutional neural nets synthesised images accurate hand segmentation method unconstrained conditions image segmentation encoder-decoder model input hand image biometrics (access control)

来源：评论

学校读者我要写书评

暂无评论

Dialogue Generation model with Hierarchical Encoding and Semantic Segmentation of Dialogue Context

引用

INTERNATIONAL JOURNAL OF SOFTWARE ENGINEERING AND KNOWLEDGE ENGINEERING 2024年第3期34卷 427-447页

作者： Wei, Xiao Lin, Yidian Hu, Qitao Shanghai Univ Sch Comp Engn & Sci Shanghai 200444 Peoples R China

Dialogue generation, as a crucial subtask of dialogue systems, is garnering increasing attention in the field of Natural Language Processing (NLP). The success of dialogue generation relies on effectively utilizing context information to ensure coherent and diverse responses. However, current approaches heavily rely on external sources rather than leveraging the inherent dialogue content. We propose a new approach to address this challenge by introducing semantic segmentation from the field of image processing into NLP. Our contribution lies in the development of a Dialogue Generation model with Hierarchical Encoding and Semantic segmentation of dialogue Context, which is called DGHESC. This model is topic and speaker-aware, capturing the flow of topic and speaker information within the dialogue context using a hierarchical transformer-based framework. Specifically, we extract semantic information at the word-level for each utterance, segment the dialogue context based on topic and speaker semantics, and employ attention mechanisms to model the context at the utterance-level. Experimental results on two open-domain datasets demonstrate the effectiveness of DGHESC. It enhances response quality and achieves state-of-the-art performances on the datasets.

关键词： Open-domain dialogue system semantic segmentation dialogue generation encoder-decoder model transformer

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Context-Aware Online Action Detection and Prediction

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2020年第8期30卷 2650-2662页

作者： Huang, Jingjia Li, Nannan Li, Thomas Liu, Shan Li, Ge Peking Univ Shenzhen Grad Sch Sch Elect & Comp Engn Shenzhen 518055 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China Peking Univ AIIT Hangzhou 310000 Peoples R China Tencent Media Lab Palo Alto CA 94301 USA

Spatial-temporal action detection in videos is a challenging problem that has attracted considerable attention in recent years. Most current approaches address action detection as an object detection problem, which utilizes successful object detection frameworks such as Faster R-CNN to operate action detection at every single frame first, and then generates action tubes by linking bounding boxes across the whole video in an offline fashion. However, unlike object detection in static images, temporal context information is vital for action detection in videos. Therefore, we propose an online action detection model that leverages the spatial-temporal context information existing in videos to perform action inference and localization. More specifically, we try to depict the spatial-temporal context pattern of actions via an encoder-decoder model that is based on a convolutional recurrent neural network. The model accepts a video snippet as input and encodes the dynamic information inside the snippet in the forward pass. During the backward pass, the decoder resolves the information for action detection with the current appearance or motion cue at each time stamp. In addition, we devise an incremental action-tube construction algorithm that enables our model to accomplish action prediction ahead of time and performs action detection in an online fashion. To evaluate the performance of our method, we conduct experiments on three popular public datasets UCF-101, UCF-Sports, and J-HMDB-21. The experimental results demonstrate that our method can achieve competitive or superior performance when compared to the state-of-the-art methods. To encourage further research, we release our project on "https://***."

关键词： Videos Electron tubes Proposals Context modeling Object detection Predictive models Computational modeling Spatial-temporal action detection encoder-decoder model online action tube generation

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：