检索结果-内蒙古大学图书馆

Triple-Stage Attention-Based Multiple Parallel Connection Hybrid Neural Network Model for Conditional Time Series Forecasting

引用

IEEE ACCESS 2021年 9卷 29165-29179页

作者： Cheng, Yepeng Morimoto, Yasuhiko Hiroshima Univ Grad Sch Engn Dept Informat Engn Higashihiroshima 7398527 Japan

The attention-based SeriesNet (A-SeriesNet) combined augmented attention residual learning module-based convolutional neural network (augmented ARLM-CNN) subnetwork with hidden state attention module-based recurrent neural network (HSAM-RNN) subnetwork for conditional time series prediction with high accuracy. The augmented ARLM-CNN subnetwork has defects in extracting latent features of the multi-condition series. The forecasting accuracy will decrease when the feature dimension of the multi-condition series becomes high. The same problem also occurs in the HSAM-RNN subnetwork of A-SeriesNet. The dual-stage attention recurrent neural network (DA-RNN) proved that the attention-based encoder-decoder framework is an effective model for dealing with the above problem. This paper applies the DA-RNN to the HSAM-RNN subnetwork of A-SeriesNet and presents the triple-stage attention-based recurrent neural network (TA-RNN) subnetworks. Furthermore, this paper considers a CNN-based encoder-decoder structure named dual attention residual learning module-based convolutional neural network (DARLM-CNN) subnetwork to improve the augmented ARLM-CNN subnetwork of A-SeriesNet. Finally, this paper presents the triple-stage attention-based SeriesNet (TA-SeriesNet), which uses a new concatenation method instead of the element-wise multiplication of A-SeriesNet to parallel connect the proposed subnetworks and reduce the dependence of forecasting results on a certain subnetwork. The experimental results show our TA-SeriesNet is superior to other deep learning models in forecasting accuracy evaluation metrics for high feature dimensional time series datasets.

关键词： Time series analysis Forecasting Recurrent neural networks Feature extraction Convolutional neural networks Logic gates Decoding encoder-decoder hybrid neural networks time series prediction triple-stage attention

来源：评论

学校读者我要写书评

暂无评论

TTPP: Temporal Transformer with Progressive Prediction for efficient action anticipation

引用

NEUROCOMPUTING 2021年 438卷 270-279页

作者： Wang, Wen Peng, Xiaojiang Su, Yanzhou Qiao, Yu Cheng, Jian Univ Elect Sci & Technol China Signal & Informat Proc Chengdu 611731 Sichuan Peoples R China Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Sichuan Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol SIAT SenseTime Joint Lab ShenZhen Key Lab Comp Vis & Pattern Recognit Shenzhen Peoples R China Shenzhen Inst Artificial Intelligence & Robot Soc SIAT Branch Shenzhen Peoples R China Shenzhen Technol Univ Shenzhen Peoples R China

Video action anticipation aims to predict future action categories from observed frames. Current state-ofthe-art approaches mainly resort to recurrent neural networks to encode history information into hidden states, and predict future actions from the hidden representations. It is well known that the recurrent pipeline is inefficient in capturing long-term information which may limit its performance in predication task. To address this problem, this paper proposes a simple yet efficient Temporal Transformer with Progressive Prediction (TTPP) framework, which repurposes a Transformer-style architecture to aggregate observed features, and then leverages a light-weight network to progressively predict future features and actions. Specifically, predicted features along with predicted probabilities are accumulated into the inputs of subsequent prediction. We evaluate our approach on three action datasets, namely TVSeries, THUMOS-14, and TV-Human-Interaction. Additionally we also conduct a comprehensive study for several popular aggregation and prediction strategies. Extensive results show that TTPP not only outperforms the state-of-the-art methods but also more efficient. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Action anticipation Transformer Progressive prediction encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

MH UNet: A Multi-Scale Hierarchical Based Architecture for Medical Image Segmentation

引用

IEEE ACCESS 2021年 9卷 148384-148408页

作者： Ahmad, Parvez Jin, Hai Alroobaea, Roobaea Qamar, Saqib Zheng, Ran Alnajjar, Fady Aboudi, Fathia Huazhong Univ Sci & Technol Natl Engn Res Ctr Big Data Technol & Syst Sch Comp Sci & Technol Serv Comp Technol & Syst LabCluster & Grid Comp Wuhan 430074 Peoples R China Taif Univ Coll Comp & Informat Technol Dept Comp Sci At Taif 21944 Saudi Arabia Madanapalle Inst Technol & Sci Dept Comp Applicat Madanapalle 517325 Andhra Pradesh India United Arab Emirates Univ Coll Informat Technol Al Ain U Arab Emirates Univ Tunis El Manar High Inst Med Technol Tunisia ISTMT LRBTM Res Lab Biophys & Med Technol Tunis 1006 Tunisia

UNet and its variations achieve state-of-the-art performances in medical image segmentation. In end-to-end learning, the training with high-resolution medical images achieves higher accuracy for medical image segmentation. However, the network depth, a massive number of parameters, and low receptive fields are issues in developing deep architecture. Moreover, the lack of multi-scale contextual information degrades the segmentation performance due to the different sizes and shapes of regions of interest. The extraction and aggregation of multi-scale features play an important role in improving medical image segmentation performance. This paper introduces the MH UNet, a multi-scale hierarchical-based architecture for medical image segmentation that addresses the challenges of heterogeneous organ segmentation. To reduce the training parameters and increase efficient gradient flow, we implement densely connected blocks. Residual-Inception blocks are used to obtain full contextual information. A hierarchical block is introduced between the encoder-decoder for acquiring and merging features to extract multi-scale information in the proposed architecture. We implement and validate our proposed architecture on four challenging MICCAI datasets. Our proposed approach achieves state-of-the-art performance on the BraTS 2018, 2019, and 2020 Magnetic Resonance Imaging (MRI) validation datasets. Our approach is 14.05 times lighter than the best method of BraTS 2018. In the meantime, our proposed approach has 2.2 times fewer training parameters than the top 3D approach on the ISLES 2018 Computed Tomographic Perfusion (CTP) testing dataset. MH UNet is available at https://***/parvezamu/MHUnet.

关键词： Image segmentation Biomedical imaging Feature extraction Training Decoding Three-dimensional displays Convolutional neural networks BraTS convolutions dense connections encoder-decoder ISLES MICCAI UNet

来源：评论

学校读者我要写书评

暂无评论

Video Question Answering: a Survey of Models and Datasets

引用

MOBILE NETWORKS & APPLICATIONS 2021年第5期26卷 1904-1937页

作者： Sun, Guanglu Liang, Lili Li, Tianlin Yu, Bo Wu, Meng Zhang, Bolun Harbin Univ Sci & Technol Sch Comp Sci & Technol Harbin 150080 Peoples R China

Video question answering (VideoQA) automatically answers natural language question according to the content of videos. It promotes the development of online education, scenario analysis, video content retrieving, etc. VideoQA is a challenging task because it requires a model to understand semantic information of the video and the question to generate the answer. Firstly, we propose a general framework of VideoQA which consists of a video feature extraction module, a text feature extraction module, an integration module, and an answer generation module. The integration module is the core module, including core processing model, recurrent neural networks (RNNs) encoder and feature fusion. These three sub-modules cooperate to generate the contextual representation, and the answer generation module generates the answer based on it. Then, we summarize the methods in core processing model, and introduce the ideas and applications of the methods in detail, such as encoder-decoder, attention model, and memory network and other methods. Additionally, we introduce the widely used datasets and evaluation criteria, as well as the analysis of experimental results on benchmark datasets. Finally, we discuss challenges in the field of VideoQA and provide some possible directions for future work.

关键词： Video question answering Feature extraction encoder-decoder Attention model Memory network Recurrent neural networks Feature fusion

来源：评论

学校读者我要写书评

暂无评论

Abstractive Summarization of Khasi Texts using Pretrained Large Language Models

引用

Procedia Computer Science 2025年 258卷 4117-4127页

作者： Aiom Minnette Mitri Goutam Saha Saralin A Lyngdoh Arnab Kumar Maji Department of Information Technology North Eastern Hill University Umshing Mawkynroh Meghalaya Shillong 793022 India Department of Linguistics North Eastern Hill University Umshing Mawkynroh Meghalaya Shillong 793022 India

An automatic abstractive summarization model for the Khasi news articles is implemented in this work by leveraging language models that have emerged at the forefront in the recent past. The emergence of language models has opened avenues for the exploration and implementation of abstractive summarization models even in low-resource languages because the approach may be applied even without the support of other linguistic tools as it mainly relies on the availability of a sizable corpus. Since the Khasi language lacks linguistic tools and resources, this is a practical and effective approach. The methodology relies on the availability of two large language models pre-trained on generic texts for natural language understanding. Thus, a RoBERTa (Robustly Optimized BERT Pretraining Approach) model pre-trained in the Khasi language on a generic corpus of 400 mb Khasi texts and a publicly available pre-trained GPT-2 (Generative pre-trained transformer) has been utilized. For implementation, an encoder-decoder network has been employed for this sequence-to-sequence task. The pre-trained RoBERTa is loaded into the encoder since RoBERTa is an encoder-only model while the decoder is loaded with a pre-trained GPT-2 as the GPT-2 is a decoder-only model. The encoder transforms the input sequence to contextualized embeddings and during decoding these contextualized outputs from the encoder are used by the decoder for calculating the cross-attention between the inputs and the target summary sequence. The decoder outputs a probability distribution of the words that form the summary. For training and finetuning the summarization model, a corresponding summarization corpus has to be constructed as there is no such corpus available publicly. Since the approach requires a sizable corpus, a relatively large dataset must be built and updated incrementally. The model achieves ROUGE-1 scores of 0.55, 0.29, and 0.37 for recall, precision, and F1 respectively, ROUGE-2 scores of 0.15, 0.11, a

关键词： abstractive summarization automatic text summarization encoder-decoder language models

来源：评论

学校读者我要写书评

暂无评论

A traffic-weather generative adversarial network for traffic flow prediction for road networks under bad weather

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年 137卷

作者： Zhang, Wensong Yao, Ronghan Yuan, Ying Du, Xiaojing Wang, Libing Sun, Feng Hebei GEO Univ Sch Urban Geol & Engn Shijiazhuang Peoples R China Minist Nat Resources Key Lab Intelligent Detect & Equipment Underground Shijiazhuang Peoples R China Hebei Technol Innovat Ctr Intelligent Dev & Contro Shijiazhuang Peoples R China Shandong Univ Technol Sch Transportat & Vehicle Engn Zibo Peoples R China Dalian Univ Technol Sch Transportat & Logist Dalian Peoples R China

Traffic flow prediction is pivotal in providing reliable information for intelligent traffic systems. Unexpected events, such as bad weather, unavoidably impact the precision of traffic flow prediction. Therefore, to achieve accurate traffic flow prediction results in road networks under bad weather, a novel Traffic-Weather Generative Adversarial Network (TWeather-GAN model) is developed. This model comprises a Generator and a Discriminator. The Generator incorporates both the traffic and weather modules to extract the spatiotemporal patterns hidden in traffic flow and weather data. In the traffic and weather modules, the gated convolutional layer, encoder-decoder architecture, and attention mechanism are established. In the Discriminator, the gated convolutional layer and bidirectional long short-term memory neural network are introduced. Traffic flow data under fog, strong wind, and heavy rain are selected to test the seven baseline models and the proposed model, and the ablation experiments are conducted to analyze the mechanism of the proposed model. The experiments demonstrate that the TWeather-GAN model outperforms the baseline models under bad weather, and makes the prediction error have an average reduction of 0.20%-34.81%, 3.21%-35.22%, and 9.46%-39.10%, respectively, under one-step prediction, three-step prediction, and six-step prediction. Furthermore, establishing the gated convolutional layer and the weather module enhances the accuracy of traffic flow prediction under bad weather. Results show that traffic flow fluctuations and distributions differ under fog and strong wind, and heavy rain affects the trend of traffic flow over one day.

关键词： Traffic flow prediction Generative adversarial network Bad weather encoder-decoder Gated convolutional layer Bidirectional long short-term memory neural network

来源：评论

学校读者我要写书评

暂无评论

Multi-scale dual-channel feature embedding decoder for biomedical image segmentation

引用

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024年 257卷 108464-108464页

作者： Agarwal, Rohit Ghosal, Palash Sadhu, Anup K. Murmu, Narayan India, Debashis Nandi Natl Inst Technol Dept Comp Sci & Engn Durgapur 713209 West Bengal India Sikkim Manipal Univ Sikkim Manipal Inst Technol Dept Informat Technol Sikkim India EKO Diagnost Ctr Med Coll Kolkata India

Background and Objective: Attaining global context along with local dependencies is of paramount importance for achieving highly accurate segmentation of objects from image frames and is challenging while developing deep learning-based biomedical image segmentation. Several transformer-based models have been proposed to handle this issue in biomedical image segmentation. Despite this, segmentation accuracy remains an ongoing challenge, as these models often fall short of the target range due to their limited capacity to capture critical local and global contexts. However, the quadratic computational complexity is the main limitation of these models. Moreover, a large dataset is required to train those models. Methods: In this paper, we propose a novel multi-scale dual-channel decoder to mitigate this issue. The complete segmentation model uses two parallel encoders and a dual-channel decoder. The encoders are based on convolutional networks, which capture the features of the input images at multiple levels and scales. The decoder comprises a hierarchy of Attention-gated Swin Transformers with a fine-tuning strategy. The hierarchical Attention-gated Swin Transformers implements a multi-scale, multi-level feature embedding strategy that captures short and long-range dependencies and leverages the necessary features without increasing computational load. At the final stage of the decoder, a fine-tuning strategy is implemented that refines the features to keep the rich features and reduce the possibility of over-segmentation. Results: The proposed model is evaluated on publicly available LiTS, 3DIRCADb, and spleen datasets obtained from Medical Segmentation Decathlon. The model is also evaluated on a private dataset from Medical College Kolkata, India. We observe that the proposed model outperforms the state-of-the-art models in liver tumor and spleen segmentation in terms of evaluation metrics at a comparative computational cost. Conclusion: The novel dual-channel deco

关键词： Attention gate Biomedical image segmentation encoder-decoder Self-attention Vision transformer

来源：评论

学校读者我要写书评

暂无评论

BGNet: Boundary-guided network for polyp segmentation

引用

INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY 2024年第1期34卷 e22959-e22959页

作者： Gao, Shanglei Zhan, Yinwei Chen, Zijun Guangdong Univ Technol Sch Comp Sci & Technol Guangzhou Peoples R China Guangdong Univ Technol Sch Comp Sci & Technol Guangzhou 510006 Peoples R China

Colonoscopy is one of the most direct and effective methods for detecting colon polyps;they are crucial for early screening and prevention of colorectal cancer (CRC). Accurate segmentation of polyp images is significant for the clinical management and treatment of CRC. However, polyp image segmentation is a challenging task because polyps vary in size, shape, and color, and have low contrast with the surrounding tissue and mucosa. To address these challenges, we propose a novel network called BGNet for polyp segmentation. BGNet consists of three modules: a boundary feature extraction module (BFEM), a mutual optimization module (MOM), and a convolutional attention module (CBAM). The BFEM extracts boundary features and predicts boundary maps, which complement and guide region features to accurately predict polyp regions and help BGNet generate precise prediction masks. The MOM optimizes the extracted features to enhance fine-grained feature representation. The CBAM performs attention operations on the feature map to focus on informative regions and suppress irrelevant information. We conduct quantitative and qualitative evaluations on five benchmark datasets, and the results show that BGNet outperforms other methods and has strong learning ability and generalization ability.

关键词： boundary-guided colorectal cancer (CRC) encoder-decoder polyp image segmentation

来源：评论

学校读者我要写书评

暂无评论

Sequence Prediction under Missing Data: An RNN Approach without Imputation 22

Sequence Prediction under Missing Data: An RNN Approach with...

引用

31st ACM International Conference on Information and Knowledge Management (CIKM)

作者： Pachal, Soumen Achar, Avinash IIT Madras Res Pk Consultancy Serv Res Chennai Tamil Nadu India

ISBN: (纸本)9781450392365

Missing data scenarios are very common in ML applications in general and time-series/sequence applications are no exceptions. This paper pertains to a novel Recurrent Neural Network (RNN) based solution for sequence prediction under missing data. Our method is distinct from all existing approaches. It tries to encode the missingness patterns in the data directly without trying to impute data either before or during model building. Our encoding is lossless and achieves compression. It can be employed for both sequence classification and forecasting. We focus on forecasting here in a general context of multi-step prediction in presence of possible exogenous inputs. In particular, we propose novel variants of encoder-decoder (Seq2Seq) RNNs for this. The encoder here adopts the above mentioned pattern encoding, while at the decoder which has a different structure, multiple variants are feasible. We demonstrate the utility of our proposed architecture via multiple experiments on both single and multiple sequence (real) data-sets. We consider both scenarios where (i)data is naturally missing and (ii)data is synthetically masked.

关键词： Recurrent Neural Networks encoder-decoder Seq2Seq time-series Missing Data

来源：评论

学校读者我要写书评

暂无评论

Explainability for Medical Image Captioning 11

Explainability for Medical Image Captioning

引用

11th International Conference on Image Processing Theory, Tools and Applications (IPTA)

作者： Beddiar, Djamila Oussalah, Mourad Tapio, Seppanen Univ Oulu CMVS Oulu Finland MIPT Fac Med Oulu Finland

ISBN: (纸本)9781665469647

Medical image captioning is the process of generating clinically significant descriptions to medical images, which has many applications among which medical report generation is the most frequent one. In general, automatic captioning of medical images is of great interest for medical experts since it offers assistance in diagnosis, disease treatment and automating the workflow of the health practitioners. Recently, many efforts have been put forward to obtain accurate descriptions but medical image captioning still provides weak and incorrect descriptions. To alleviate this issue, it is important to explain why the model produced a particular caption based on some specific features. This is performed through Artificial Intelligence Explainability (XAI), which aims to unfold the 'black-box' feature of deeplearning based models. We present in this paper an explainable module for medical image captioning that provides a sound interpretation of our attention-based encoder-decoder model by explaining the correspondence between visual features and semantic features. We exploit for that, self-attention to compute word importance of semantic features and visual attention to compute relevant regions of the image that correspond to each generated word of the caption in addition to visualization of visual features extracted at each layer of the Convolutional Neural Network (CNN) encoder. We finally evaluate our model using the ImageCLEF medical captioning dataset.

关键词： Image Captioning Medical images encoder-decoder Attention-maps Artificial Intelligence Explainability

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：