检索结果-内蒙古大学图书馆

Chinese intelligent Systems Conference, CISC 2020

作者： Yuan, Xunpu Du, Junping Kou, Feifei Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications Beijing100876 China

ISBN: (纸本)9789811584572

With the development of the economy, more and more people on social platforms share financial-related information and hope to understand the development of financial markets through relevant financial data. Aiming at this problem, this thesis proposes a sentiment analysis algorithm of financial texts based on semantic matching. First, preliminary text vectorization is performed on financial text data. Then further training and fine-tuning are performed through pre-trained models in order to fully tap the associations between text contexts and better grasp the semantic focus, so as to better model the text content and obtain higher-level financial text semantic representation. Next, through the improved Siamese network semantic matching model, financial text vectors are trained for semantic matching, so that the distance between financial text vectors with the same emotional category is closer and the distance between different classes is farther, which further optimizes the semantic representation of financial text. Finally, support vector machines are used as classifier to perform sentiment classification of financial texts. Experimental results show that compared with other classic sentiment analysis algorithms, the proposed algorithm has the best sentiment analysis effect on financial text. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A User Portrait Construction Method for Financial Credit

A User Portrait Construction Method for Financial Credit

引用

Chinese intelligent Systems Conference, CISC 2020

作者： Liu, Chong Du, Junping Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications Beijing100876 China

ISBN: (纸本)9789811584572

Credit reporting has always been an important issue in the financial field. It is widely used to collect credits from users, portray user portraits, and determine whether to lend to users. This paper proposes a user portrait construction algorithm based on multi-model fusion. This algorithm uses stacking to fuse Word2Vec and text-CNN networks, as well as LDA topic models and BP neural networks to model the users social media information, and then obtains the users basic attributes. At the same time, the algorithm uses the stacking method to fuse SVM and KNN to predict the users credit value from the users past financial data records. Finally, in order to obtain the final user portrait, the users social relationship is used to modify the user attributes by applying the PageRank algorithm. The experimental results show that the multi-model fusion method proposed in this paper has the best effect on user portrait construction. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Finance

来源：评论

学校读者我要写书评

暂无评论

Bootstrapping-Based Automatic Acquisition of Domain Concepts for Ontology Construction

引用

Chinese Journal of Electronics 2023年第2期22卷 313-318页

作者： Yuehua Yang Junping Du Lingling Zi Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications Beijing China School of Electronic and Information Engineering Liaoning Technical University Huludao China

The domain concept is one of the key elements of ontology. In order to automatically acquire the domain concepts during the domain ontology construction, we proposed a novel Bootstrapping-based automatic acquisition algorithm of domain concepts. In our work, the compound words are extracted according to the combination conditions of the mutual information and the information entropy. The candidate domain concepts determinant conditions based on the co-occurrence sentences frequency are presented. Besides, to avoid omitting the domain concepts with the lower frequency or semantically similar to other domain concepts, the semantic factor is introduced. The experiments results have demonstrated that the compound domain concepts and the semantically similar domain concepts with the lower sentences frequency can also be extracted by using the proposed algorithm. And the proposed algorithm has obtained higher precision and recall, so it is effective and feasible.

关键词： Frequency-domain analysis Semantics Focusing Ontologies Filtering algorithms Compounds Data mining

来源：评论

学校读者我要写书评

暂无评论

MemoMusic 3.0: Considering Context at Music Recommendation and Combining Music Theory at Music Generation

MemoMusic 3.0: Considering Context at Music Recommendation a...

引用

2023 IEEE International Conference on multimedia and Expo Workshops, ICMEW 2023

作者： Mou, Luntian Sun, Yihan Tian, Yunhan Sun, Yiqi Liu, Yuhang Zhang, Zexi He, Ruichen Li, Juehui Li, Jueying Li, Zijin Gao, Feng Shi, Yemin Jain, Ramesh Beijing Institute of Artificial Intelligence Beijing University of Technology Beijing Key Laboratory of Multimedia and Intelligent Software Technology Faculty of Information Technology China University of Regensburg Germany Pandora Denmark Cornell University United States Central Conservatory of Music China School of Arts Peking University China Beijing Academy of Artificial Intelligence China University of California Irvine United States

ISBN: (纸本)9798350313154

MemoMusic 3.0 enhances personalized music recommendation by considering the music listening context, and improves music generation by introducing music theory. One observation is that the context of music listening would affect the emotional states of listeners, positively or negatively. The other is that better music can be generated by introducing some music theory knowledge. We propose a Transformer-based music generation framework, which is trained into three models for Classic, Pop, and Yanni music respectively. The dominant melody of a music with expected Valence and Arousal values is used as a sample sequence to the model, and its output is adjusted according to music theory. Experimental results demonstrate that MemoMusic 3.0 performs better at improving the emotional states of listeners and achieves better user satisfaction. © 2023 IEEE.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph Enhanced Multimodal Transformer for Image-Text Retrieval

Knowledge Graph Enhanced Multimodal Transformer for Image-Te...

引用

International Conference on Data Engineering

作者： Juncheng Zheng Meiyu Liang Yang Yu Yawen Li Zhe Xue Beijing Key Laboratory of Intelligent Communication Software and Multimedia School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China School of Economics and Management Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Image-text retrieval is a fundamental cross-modal task that aims to align the representation spaces between the image and text modalities. Existing cross-modal image-text retrieval methods independently generate embeddings for images and text, introduce interaction-based networks for cross-modal inference, and then achieve retrieval by using matching metrics. However, they overlook the semantic relationship between the coarse-grained and fine-grained representations within each modality, failing to capture the consistency of representations across different modalities, which affects the semantic learning of cross-modal representations, and makes it difficult to align modalities in semantic space. Consequently, these previous works inevitably suffer from low retrieval accuracy or high computational costs. In this paper, instead of directly fusing two cross-modal het-erogeneous spaces, we propose an multimodal knowledge enhanced multimodal transformer network framework to combine coarse-grained and fine-grained representation learning into a unified framework, capturing alignment information between targets, constructing a global semantic graph, and ultimately align multimodal representations in the semantic space. In our approach, images generate semantic and spatial graphs to represent visual information, while sentences generate text graphs based on semantic relationships between words, and they are used for intra-modal graph network inference. Subsequently, the generated global and local embeddings are fused into an enhanced multimodal transformer framework, effectively imple-menting cross-modal interaction processes by leveraging prior implicit semantic information from the multimodal knowledge graph. Furthermore, compared to simply matching words with image regions, our method proposes a bidirectional fine-grained matching method to filter the salient regions and words of images and texts, remove the interfering noise information, and realize bidirectional fine-

关键词： Representation learning Measurement Visualization Accuracy Semantics Noise Knowledge graphs

来源：评论

学校读者我要写书评

暂无评论

Detecting Photographic Cropping Based on Vanishing Points

引用

Chinese Journal of Electronics 2023年第2期22卷 369-372页

作者： Xianzhe Meng Shaozhang Niu Ru Yan Yezhou Li School of Computer Science Beijing University of Posts and Telecommunications Beijing China Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia Beijing China School of Science Beijing University of Posts and Telecommunications Beijing China

Cropping is a common form of manipulation, it is indiscernible and hard to detect, since the interception will not destroy most of the image's original features. In this paper, how to detect cropping according to a single image is described, and a new camera calibration algorithm into digital forensics is proposed, which conducts the calibration according to orthometric vanishing points. Our method can estimate the principal point according to a single image, science the vanishing points only depends on the direction of the object. Experiments show that our method can identify asymmetric cropping of the image effectively, and also can estimate the principal points precisely, besides it is robust to smoothing and noise.

关键词： Smoothing methods Digital forensics Feature extraction Cameras Calibration

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Self-Driving Attention Prediction via Uncertainty Mining and Knowledge Embedding

Unsupervised Self-Driving Attention Prediction via Uncertain...

引用

International Conference on computer Vision (ICCV)

作者： Pengfei Zhu Mengshi Qi Xia Li Weijian Li Huadong Ma Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications Beijing Key Laboratory of Artificial Intelligence Ministry of Education Shanghai Department of Computer Science University of Rochester

Predicting attention regions of interest is an important yet challenging task for self-driving systems. Existing methodologies rely on large-scale labeled traffic datasets that are labor-intensive to obtain. Besides, the huge domain gap between natural scenes and traffic scenes in current datasets also limits the potential for model training. To address these challenges, we are the first to introduce an unsupervised way to predict self-driving attention by uncertainty modeling and driving knowledge integration. Our approach’s Uncertainty Mining Branch (UMB) discovers commonalities and differences from multiple generated pseudo-labels achieved from models pre-trained on natural scenes by actively measuring the uncertainty. Meanwhile, our Knowledge Embedding Block (KEB) bridges the domain gap by incorporating driving knowledge to adaptively refine the generated pseudo-labels. Quantitative and qualitative results with equivalent or even more impressive performance compared to fully-supervised state-of-the-art approaches across all three public datasets demonstrate the effectiveness of the proposed method and the potential of this direction. The code is available at https://***/zaplm/DriverAttention.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A General Debiasing Framework with Counterfactual Reasoning for Multimodal Public Speaking Anxiety Detection

SSRN

引用

SSRN 2024年

作者： Zhang, Tingting Zhu, Yangfu Wu, Bin Zheng, Chunping Tan, Jiachen Xiong, Zihua Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science National Pilot School of Software Engineering Beijing University of Posts and Telecommunications Beijing100876 China School of Humanities Beijing University of Posts and Telecommunications Beijing100876 China

Multimodal public speaking anxiety detection (MPSAD), which aims to identify the anxiety states of learners, has attracted widespread attention. Unfortunately, the current MPSAD task inevitably suffers from the impact of latent different types of multimodal hybrid biases, such as context bias, label bias and keyword bias. Models may rely on these biases as shortcuts, preventing them from fully utilizing all three modalities to learn multimodal knowledge. Existing methods primarily focus on addressing specific types of biases, but anticipating bias types when designing these methods is challenging, as we cannot foresee all possible biases. To tackle this issue, we use causal graphs to clarify the causal relationships among variables, and propose a General Multimodal Counterfactual Reasoning debiasing framework (GMCR), which eliminates multimodal hybrid biases from a unified causal perspective. Specifically, this plug-and-play debiasing framework removes multimodal hybrid biases by disentangling causal and biased features and capturing adverse effects via a counterfactual branch. It then subtracts spurious correlations during inference for unbiased predictions. Due to the challenge of collecting speech video data, there are currently limited high-quality datasets available for the MPSAD task. To overcome this scarcity, we create a new large-scale fine-grained Multimodal English Public Speaking Anxiety (ME-PSA) dataset. Extensive experiments on our ME-PSA and two benchmarks demonstrate the superior effectiveness of our proposed framework. Furthermore, our approach improves the accuracy and F1 score of the MPSAD task by over 2.00% and 4.00%, respectively, compared to the vanilla SOTA baselines. Our dataset and code will be available at https://***/Ztt1997/GMCR\_Framework. © 2024, The Authors. All rights reserved.

关键词： Speech analysis

来源：评论

学校读者我要写书评

暂无评论

IRAM-SQL: A Language Model Integrating Relation-Aware Mechanism for Text-to-SQL

IRAM-SQL: A Language Model Integrating Relation-Aware Mechan...

引用

International Conference on computer and Communications (ICCC)

作者： Ruohan Zhang Feng Zhou Shuyuan Peng Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing China School of Computer Science Beijing University of Posts and Telecommunications Beijing China Jiu Tian Team China Mobile Research Institute Beijing China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

The task of text-to-SQL aims to convert natural language questions into executable SQL queries within relational databases. This greatly enhances the usability of relational database querying, alleviating the difficulties faced by users who are not proficient in SQL. A major challenge in text-to-SQL task is the model's ability to recognize entities accurately. This paper focuses on this issue and proposes a language model with an integrated relation-aware mechanism for text-to-SQL, named IRAM-SQL. We explore the adaptability of pretrained models for downstream text-to-SQL tasks, ultimately selecting CodeT5+ as the pretrained model, which is trained on a large dataset of source code and annotation, exploring the shared representation between natural language and code. Therefore, the model's ability to generate structured sentences would be explored during the pretraining phase. At the same time, we also integrate a relation-aware mechanism throughout the model fine-tuning process. To this end, we comprehensively models the relational information between natural language questions and database schemas, integrating these relationships effectively within the encoder and decoder of the Transformer architecture. Two denoising tasks is employed during training to help the model learn these relationships more effectively. The integration of relational information during encoding and decoding, along with the emphasis on entity awareness in the training tasks, enhances the model's entity recognition capabilities. We evaluate our proposed framework on the SPIDER dataset and three of its robustness variants: SPIDER-SYN, SPIDER-DK, and SPIDER-REALISTIC. Experimental results indicate that IRAM-SQL, with its comprehensively integrated relation-aware mechanism, demonstrates strong performance and robustness.

关键词： Training Adaptation models Structured Query Language Natural languages Noise reduction Relational databases computer architecture Transformers Robustness Decoding

来源：评论

学校读者我要写书评

暂无评论

Lite-UNet: A Lightweight and Efficent Network for Cell Localization

TechRxiv

引用

TechRxiv 2023年

作者： Bo, Li Yong, Zhang Ren, Yunhan Zhang, Chengyang Baocai, Yin Beijing Key Laboratory of Multimedia and Intelligent Software Technology Faculty of Information Technology Beijing Institute of Artificial Intelligence Beijing University of Technology Beijing100124 China Beijing-Dublin International College Beijing University of Technology Beijing100124 China

Cell localization constitutes a fundamental research domain within the realm of pathology image analysis, with its core objective being the precise identification of cell spatial coordinates. The task has always involved the challenge of large color variations among cells, uneven distribution, and overlapping borders. Furthermore, in realistic cell localization scenarios, the existing state-of-the-art methods suffer from high computational costs and slow inference times, which severely reduce the efficiency of computer-assisted. To tackle the above issues, a lightweight and efficient cell localization model named Lite-UNet is proposed. Specifically, the Lite-UNet encompasses three pivotal modules. Firstly, we introduce a gradient aggregation module grounded in difference convolution. This module effectively mitigates the challenge posed by extensive color variations among cells by adeptly leveraging gradient information. Secondly, we propose an efficient plug-and-play graph correlation attention module, which optimizes the feature representation capabilities by encoding higher-order feature associations. Finally, we design a lightweight Ghost CBAM module that alleviates the difficulty of uneven cell distribution while forming the base module of the Lite-UNet. Extensive experiments show that our Lite-UNet is capable of locating cells in images quickly and accurately, thus further improving the efficiency of computer-assisted medicine. © 2023, CC BY.

关键词： Cells

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：