检索结果-内蒙古大学图书馆

37th IEEE International Conference on Data Engineering (IEEE ICDE)

作者： Fujita, Jumpei Sato, Masahiro Nobuhara, Hajime Univ Tsukuba Tsukuba Ibaraki Japan

ISBN: (纸本)9781665448901

It is difficult to find a recipe that uses the ingredients in a person's refrigerator within a short time. To solve this problem, we propose a recipe-generation model in the encoder-decoder framework. Models developed in the traditional encoder-decoder framework do not adequately reflect the ingredients in cooking recipes, but the proposed method introduces reinforcement learning and coverage loss. The model was experimentally evaluated on a dataset of approximately 15 K cooking recipes extracted from ***. The evaluation index was ingredient matching (IM), a new evaluation metric, showing the extent to which the recipe uses the input ingredients. Relative to the existing model, the proposed model improved the IM by approximately 21%.

关键词： reinforcement learning encoder-decoder framework coverage loss attention mechanism cooking recipe loss function evaluation metric embedding layer recipe generation computational linguistic

来源：评论

学校读者我要写书评

暂无评论

A Human-Machine Collaborative Video Summarization framework Using Pupillary Response Signals 6

A Human-Machine Collaborative Video Summarization Framework ...

引用

6th International Conference on Information Communication and Signal Processing, ICICSP 2023

作者： Ma, Haigang Yu, Wenyuan Wang, Yaoyao Zhou, Minwei Ding, Nai Zheng, Jing Zhejiang University Hangzhou China Zhejiang Lab Hangzhou China Zhejiang University Zhejiang Lab Hangzhou China

ISBN: (纸本)9798350339994

This paper proposes a novel, human-machine collaborative, pupillary response-based video summarization framework. Considering that humans are the end-users and evaluators of video content, it is natural to establish the links between video features and real-time viewers' attentive response for designing a video summarization framework. In this paper, pupil size, a pupillary response, is introduced as a real-time indicator for assessment of viewers' engagement and attention. Firstly, we augmented the TVSum dataset by replacing manual annotations with attention scores that converted from pupillary size signals to generate the perceptually driven dataset. Secondly, we developed a video summarization framework which uses cues from pupillary size signal of humans to predict frame-level attention scores, and then extracts key shots from videos. On the perception-driven dataset, the average F-measure of the proposed summarization method is 69.71%, while the precision and recall are 69.67% and 69.77%, respectively, which is a significant improvement compared to random summarization. Experimental results initially demonstrated that our modeling approach can learn the dynamic attention mechanism of viewers and apply it to video summarization. In addition, the experimental results validate the effect. © 2023 IEEE.

关键词： Attention mechanism encoder-decoder framework Gated Recurrent Unit (GRU) Pupil size Video summarization

来源：评论

学校读者我要写书评

暂无评论

Jointly Modeling Spatio-Temporal Dependencies and Daily Flow Correlations for Crowd Flow Prediction

引用

ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA 2021年第4期15卷 58-58页

作者： Zang, Tianzi Zhu, Yanmin Xu, Yanan Yu, Jiadi Shanghai Jiao Tong Univ Dept Comp Sci & Engn 800 Dongchuan Rd Shanghai 200240 Peoples R China

Crowd flow prediction is a vital problem for an intelligent transportation system construction in a smart city. It plays a crucial role in traffic management and behavioral analysis, thus it has raised great attention from many researchers. However, predicting crowd flows timely and accurately is a challenging task that is affected by many complex factors such as the dependencies of adjacent regions or recent crowd flows. Existing models mainly focus on capturing such dependencies in spatial or temporal domains and fail to model relations between crowd flows of distant regions. We notice that each region has a relatively fixed daily flow and some regions (even very far away from each other) may share similar flow patterns which show strong correlations among them. In this article, we propose a novel model named Double-encoder which follows a general encoder-decoder framework for multi-step citywide crowd flow prediction. The model consists of two encoder modules named ST-encoder and FR-encoder to model spatial-temporal dependencies and daily flow correlations, respectively. We conduct extensive experiments on two real-world datasets to evaluate the performance of the proposed model and show that our model consistently outperforms state-of-the-art methods.

关键词： Multi-step crowd flow prediction encoder-decoder framework CNN ConvLSTM latent representation

来源：评论

学校读者我要写书评

暂无评论

DKPE: Deep KeyPhrase Expansion

引用

NEUROCOMPUTING 2024年 572卷

作者： Du, Huaming Xie, Zhilong Song, Jia Yuan, Yaoxing Li, Jiacan Chen, Xingyan Chen, Huangen Zhao, Yu Zhuang, Fuzhen Li, Qing Southwestern Univ Finance & Econ SWUFE Fac Business Adm Sch Business Adm Chengdu 611130 Peoples R China SWUFE Innovat Res Inst Digital Econ & Interdisciplinary Financial Intelligence & Financial Engn Key Lab Chengdu 611130 Peoples R China Xiamen Univ Inst Artificial Intelligence Xiamen 361005 Peoples R China William & Mary Raymond A Mason Sch Business Williamsburg VA 23187 USA SWUFE Financial Intelligence & Financial Engn Key Lab Chengdu 611130 Peoples R China Beihang Univ Inst Artificial Intelligence Sch Comp Sci SKLSDE Beijing 100191 Peoples R China

Keyphrase provides accurate information of document content that is highly compact, concise, full of meanings, and widely used for discourse comprehension, organization, and text retrieval. Though previous studies have made substantial efforts for automated keyphrase extraction and generation, surprisingly, few studies have been made for KeyPhrase Expansion. This task aims to add more keyphrases for documents (e.g. scientific publications) via taking advantage of document content along with a very limited number of known keyphrases, which can widely be used to improve the keyphrases-involved NLP tasks. In this paper, we introduce a novel problem concerning KeyPhrase Expansion and propose a novel keyphrase expansion method with an encoder- decoder framework. We name it Deep KeyPhrase Expansion (DKPE) since it attempts to capture the deep semantic meaning of the document content together with known keyphrases via a deep learning framework. Specifically, the encoder and the decoder in DKPE play different roles to make full use of the known keyphrases. The former considers the keyphrase-guiding factors, which aggregates information of known keyphrases into context. On the contrary, the latter considers the keyphrase-inhibited factor to inhibit semantically repeated keyphrase generation. Extensive experiments on benchmark datasets demonstrate the efficacy of our proposed model.

关键词： Keyphrase expansion Known keyphrases encoder-decoder framework Deep learning

来源：评论

学校读者我要写书评

暂无评论

Modeling hierarchical attention interaction between contexts and triple-channel encoding networks for document-grounded dialog generation

引用

FRONTIERS IN PHYSICS 2022年 10卷

作者： Cai, Yuanyuan Zuo, Min Xiong, Haitao Beijing Technol & Business Univ Natl Engn Res Ctr Agriprod Qual Traceabil Beijing Peoples R China Beijing Technol & Business Univ Sch Ebusiness & Logist Beijing Peoples R China Beijing Technol & Business Univ Sch Int Econ & Management Beijing Peoples R China

Dialog systems have attracted attention as they are promising in many intelligent applications. Generating fluent and informative responses is of critical importance for dialog systems. Some recent studies introduce documents as extra knowledge to improve the performance of dialog generation. However, it is hard to understand the unstructured document and extract crucial information related to dialog history and current utterance. This leads to uninformative and inflexible responses in existing studies. To address this issue, we propose a generative model of a neural network with an attention mechanism for document-grounded multi-turn dialog. This model encodes the context of utterances that contains the given document, dialog history, and the last utterance into distributed representations via a triple-channel. Then, it introduces a hierarchical attention interaction between dialog contexts and previously generated utterances into the decoder for generating an appropriate response. We compare our model with various baselines on dataset CMU_DoG in terms of the evaluation criteria. The experimental results demonstrate the state-of-the-art performance of our model as compared to previous studies. Furthermore, the results of ablation experiments show the effectiveness of the hierarchical attention interaction and the triple channel for encoding. We also conduct human judgment to evaluate the informativeness of responses and the consistency of responses with dialog history.

关键词： document-grounded conversation generation hierarchical attention interaction semantic feature encoding context-aware transformer encoder-decoder framework

来源：评论

学校读者我要写书评

暂无评论

A hashtag-based sub-event detection framework for social media

引用

COMPUTERS & ELECTRICAL ENGINEERING 2021年 94卷 107317-107317页

作者： Lu, Guoming Mu, Yaqiao Gu, Jianbin Kouassi, Franck A. P. Lu, Chenxi Wang, Ruozhou Chen, Aiguo Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu Sichuan Peoples R China Trusted Cloud Comp & Big Data Key Lab Sichuan Pro Chengdu Sichuan Peoples R China Essence Secur Co Ltd 13A034018 Jintian St Shenzhen Guangdong Peoples R China

Sub-event detection for social media is getting increasingly important because social media platforms have played key roles in disseminating vital information to the public. However, conventional methods fail to achieve high-quality analysis of events evolution due to the severe sparseness and noise of tweets data. In this paper, we propose an unsupervised sub-event detection model which learns rich information from hashtags with a Text-CNN model. Furthermore, a two steps training method leveraged by KL divergence is introduced to further reduce the negative influence of incoherent semantics. The experiments show that our method achieves very good performance on datasets of different languages. On the Chinese dataset, in terms of NMI, and BCubed F1 precision, our method has a significant increase of 5.1%, and 11.9%, respectively, over the baseline methods. In most cases, our method significantly improves the performance of sub-event detection compared with state-of-the-art methods.

关键词： Sub-event detection encoder-decoder framework Text-CNN Social media mining

来源：评论

学校读者我要写书评

暂无评论

Automated audio captioning: an overview of recent progress and new challenges

引用

EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING 2022年第1期2022卷 26-26页

作者： Mei, Xinhao Liu, Xubo Plumbley, Mark D. Wang, Wenwu Univ Surrey Ctr Vision Speech & Signal Proc CVSSP Dept Elect & Elect Engn Fac Engn & Phys Sci Guildford GU2 7XH Surrey England

Automated audio captioning is a cross-modal translation task that aims to generate natural language descriptions for given audio clips. This task has received increasing attention with the release of freely available datasets in recent years. The problem has been addressed predominantly with deep learning techniques. Numerous approaches have been proposed, such as investigating different neural network architectures, exploiting auxiliary information such as keywords or sentence information to guide caption generation, and employing different training strategies, which have greatly facilitated the development of this field. In this paper, we present a comprehensive review of the published contributions in automated audio captioning, from a variety of existing approaches to evaluation metrics and datasets. We also discuss open challenges and envisage possible future research directions.

关键词： Audio captioning Deep learning Audio processing Natural language processing encoder-decoder framework

来源：评论

学校读者我要写书评

暂无评论

NumCap: A Number-controlled Multi-caption Image Captioning Network

引用

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 2023年第4期19卷 148-148页

作者： Abdussalam, Amr Ye, Zhongfu Hawbani, Ammar Al-Qatf, Majjed Khan, Rashid Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230027 Peoples R China Univ Sci & Technol China Sch Comp Sci & Technol Hefei 230027 Peoples R China

Image captioning is a promising task that attracted researchers in the last few years. Existing image captioning models are primarily trained to generate one caption per image. However, an image may contain rich contents, and one caption cannot express its full details. A better solution is to describe an image with multiple captions, with each caption focusing on a specific aspect of the image. In this regard, we introduce a new number-based image captioning model that describes an image with multiple sentences. An image is annotated with multiple ground-truth captions;thus, we assign an external number to each caption to distinguish its order. Given an image-number pair as input, we could achieve different captions for the same image under different numbers. First, a number is attached to the image features to form an image-number vector (INV). Then, this vector and the corresponding caption are embedded using the order-embedding approach. Afterward, the INV's embedding is fed to a language model to generate the caption. To show the efficiency of the numbers incorporation strategy, we conduct extensive experiments using MS-COCO, Flickr30K, and Flickr8K datasets. The proposed model attains 24.1 in METEOR on MS-COCO. The achieved results demonstrate that our method is competitive with a range of state-of-the-art models and validate its ability to produce different descriptions under different given numbers.

关键词： Numbers incorporation strategy encoder-decoder framework image captioning order-embedding

来源：评论

学校读者我要写书评

暂无评论

An extended attention mechanism for scene text recognition

引用

EXPERT SYSTEMS WITH APPLICATIONS 2022年 203卷

作者： Xiao, Zheng Nie, Zhenyu Song, Chao Chronopoulos, Anthony Theodore Hunan Univ Coll Informat Sci & Engn Changsha Peoples R China Univ Texas Dept Comp Sci San Antonio TX 78249 USA Univ Patras Comp Engn & Informat Rion 26500 Greece

Scene text recognition (STR) refers to obtaining text information from natural text images. The task is more challenging than the optical character recognition(OCR) due to the variability of scenes. Attention mechanism, which assigns different weights to each feature vector at each time step, guides the text recognition decoding process. However, when the given query and the key/value are not related, the generated attention result will contain irrelevant information, which could lead the model to give wrong results. In this paper, we propose an extended attention-based framework for STR tasks. In particular, we have integrated an extended attention mechanism named Attention on Attention (AoA), which is able to determine the relevance between attention results and queries, into both the encoder and the decoder of a common text recognition framework. By two separate linear functions, the AoA module generates an information vector and an attention gate using the attention result and the current context. Then AoA adds new attention by applying element-wise multiplication to acquire final attended information. Our method is compared with seven benchmarks over eight datasets. Experimental results show that our method outperforms all the seven benchmarks, by 6.7% and 1.4% than the worst and best works on average.

关键词： Scene text recognition Attention on attention Deep neural network encoder-decoder framework

来源：评论

学校读者我要写书评

暂无评论

An improved Wavenet network for multi-step-ahead wind energy forecasting

引用

ENERGY CONVERSION AND MANAGEMENT 2023年第1期278卷

作者： Wang, Yun Chen, Tuo Zhou, Shengchao Zhang, Fan Zou, Ruming Hu, Qinghua Cent South Univ Sch Automation Changsha Hunan Peoples R China Tianjin Univ Coll Intelligence & Comp Tianjin Peoples R China

Accurate multi-step-ahead wind speed (WS) and wind power (WP) forecasting are critical to the scheduling, planning, and maintenance of wind farms. Previous forecasting methods tend to focus on improving forecast accuracy by integrating different models and disaggregating data while neglecting the forecasting ability of basic models. In addition, traditional multi-step-ahead output strategies have limitations that constrain the forecasting capability of models. To overcome the above challenges, this study proposes a novel forecasting model called ED-Wavenet-TF. It adopts two Wavenet networks as encoder and decoder connected by the multi-head self-attention mechanism. And, teacher forcing is used as the multi-step-ahead output strategy for WS and WP forecasting. In the training phase, ED-Wavenet-TF uses a portion of the actual data to correct the errors at the intermediate forecasting steps, while in the forecasting phase, it runs through an inference loop to make forecasts. In this study, two WS datasets and two WP datasets are used to validate the performance of ED-Wavenet-TF with univariate input. The results show that compared with Wavenet, the symmetric mean absolute percentage error of ED-Wavenet-TF at four forecasting steps is lower by at least 4.8577% on average for the WS datasets and 8.9463% on average for the WP datasets. The advantages of ED-Wavenert-TF over ten comparable models are confirmed by four evaluation indicators and the Harvey, Leybourne, and Newbold statistical hypothesis test. Moreover, ED-Wavenet-TF is extended to make multi-step-ahead forecasts with multivariate inputs, whose effectiveness is demonstrated on another open WS dataset.

关键词： Multi-step-ahead wind energy forecasting Wavenet encoder-decoder framework Teacher forcing Multi-head self-attention

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：