检索结果-内蒙古大学图书馆

Intensity preserving technology in image restoration

Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (engineering and Technology Edition) 2013年第SUPPL.1期43卷 106-109页

作者： Guo, Xiao-Xin Xu, Zhi-Wen Che, Xiang-Jiu College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun 130012 China

A new approach of image restoration for the sequence of fluorescein angiography was proposed. First, the intensity constraint was incorporated into Miller regularization equation to obtain the ability to preserve the high intensity of pixels. Thus, the restored image would be influenced not only by the smoothness constraints, but also by the intensity constraints. Secondly, in the process of the restoration, we use an intensity template obtained from the pre-filtering procedure was used to achieve the intensity constraints. The template represented an image composed by the desired intensity value. The experiments show that the proposed scheme gains a better result in both high intensity preservation and image restoration.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Object Attribute Matters in Visual Question Answering

arXiv

引用

arXiv 2023年

作者： Li, Peize Si, Qingyi Fu, Peng Lin, Zheng Wang, Yan School of Artificial Intelligence Jilin University Changchun China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun China

Visual question answering is a multimodal task that requires the joint comprehension of visual and textual information. However, integrating visual and textual semantics solely through attention layers is insufficient to comprehensively understand and align information from both modalities. Intuitively, object attributes can naturally serve as a bridge to unify them, which has been overlooked in previous research. In this paper, we propose a novel VQA approach from the perspective of utilizing object attribute, aiming to achieve better object-level visual-language alignment and multimodal scene understanding. Specifically, we design an attribute fusion module and a contrastive knowledge distillation module. The attribute fusion module constructs a multimodal graph neural network to fuse attributes and visual features through message passing. The enhanced object-level visual features contribute to solving fine-grained problem like counting-question. The better object-level visual-language alignment aids in understanding multimodal scenes, thereby improving the model’s robustness. Furthermore, to augment scene understanding and the out-of-distribution performance, the contrastive knowledge distillation module introduces a series of implicit knowledge. We distill knowledge into attributes through contrastive loss, which further strengthens the representation learning of attribute features and facilitates visual-linguistic alignment. Intensive experiments on six datasets, COCO-QA, VQAv2, VQA-CPv2, VQA-CPv1, VQAvs and TDIUC, show the superiority of the proposed method. © 2023, CC BY.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Research on collaborative filtering recommendation based on k-means clustering

引用

ICIC Express Letters 2016年第10期10卷 2493-2498页

作者： Dong, Liyan Zhu, Gaozi Zhu, Qi Li, Yongli College of Computer Science and Technology Jilin University No. 2699 Qianjin Street Changchun130012 China Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University No. 2699 Qianjin Street Changchun130012 China School of Computer Science and Information Technology Northeast Normal University No. 2555 Jingyue Ave Changchun130117 China

In accordance with the inaccuracy of searching neighbors in traditional collaborative filtering algorithms, we narrow down the space of neighbor searching by means of partition clustering to improve the real-time performance of recommendations. Then by taking the similarity measurement into consideration, we convert the high-dimensional sparse matrix of user rating to the low-dimensional dense matrix of user interest to enhance the accuracy of recommendations. Experiments proved that combining the partition clustering based on user interests and collaborative filters could contribute to increasing real-time speed and the accuracy of recommendation effectively. © 2016 ICIC International.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

A new qualitative spatial reasoning model for natural language understanding

引用

ICIC Express Letters, Part B: Applications 2011年第5期2卷 1015-1020页

作者： Song, Xiaohua Ouyang, Dantong College of Computer Science and Technology Jilin University No. 2699 Qianjin Street Changchun 130012 China Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry Education Jilin University No. 2699 Qianjin Street Changchun 130012 China Center of Mathematics for Applications Aviation University of Air Force No. 7855 Renmin Street Changchun 130022 China

This paper introduces a qualitative spatial model based on previously developed models for representation and reasoning the spatial information described in natural language. The model is integrated with direction and topology which make it more useful than CDC and ICD to describe complex spatial information in natural language. Then, we give the reasoning method and discuss its advantage. © 2011 ISSN 2185-2766.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Classification based on Label-Specific Features

Multi-Label Classification based on Label-Specific Features

引用

2011年全国理论计算机科学学术年会

作者： QU Huaqiao ZHANG Shichao LIU Huawen ZHAO Jianmin Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun 130012 China Department of Computer Science Zhejiang Normal University Jinhua 321004 Department of Computer Science Zhejiang Normal University Jinhua 321004 China Department of Computer Science Zhejiang Normal University Jinhua 321004 China

lti-label learning aims at predicting a proper label set for each unseen *** instance in the dataset is associated with a set of predefined ***-label learning approaches frequently used choose identical feature set to...

关键词：

来源：评论

学校读者我要写书评

暂无评论

A multi-level neural network for implicit causality detection in Web texts

arXiv

引用

arXiv 2019年

作者： Liang, Shining Zuo, Wanli Shi, Zhenkun Wang, Sen Wang, Junhu Zuo, Xianglin Key Laboratory of Symbol Computation Knowledge Engineering of Ministry of Education Changchun China College of Computer Science and Technology Jilin University Jilin China Tianjin Institute of Industrial Biotechnology Chinese Academy of Sciences School of Information Technology and Electrical Engineering The University of Queensland Brisbane Australia School of Information and Communication Technology Griffith University QLD Australia

Mining causality from text is a complex and crucial natural language understanding task corresponding to the human cognition. Existing studies at its solution can be grouped into two primary categories: feature engineering based and neural model based methods. In this paper, we find that the former has incomplete coverage and inherent errors but provide prior knowledge;while the latter leverages context information but causal inference of which is insufficiency. To handle the limitations, we propose a novel causality detection model named MCDN to explicitly model causal reasoning process, and furthermore, to exploit the advantages of both methods. Specifically, we adopt multi-head self-attention to acquire semantic feature at word level and develop the SCRN to infer causality at segment level. To the best of our knowledge, with regards to the causality tasks, this is the first time that the Relation Network is applied. The experimental results show that: i) the proposed approach performs prominent performance on causality detection;ii) further analysis manifests the effectiveness and robustness of MCDN. © 2019, CC BY-NC-SA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Design of vehicle automatic braking systems considering drivers' braking characteristics

引用

International Journal of Performability engineering 2019年第9期15卷 2338-2345页

作者： Gao, Zhenhai Sun, Tianjun Hassan, MuHammad Wang, Liupu College of Automotive Engineering Jilin University Changchun130022 China College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbol Computation Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China Cancer Hospital Attached Xinjiang Medical University Urumqi830000 China Department of Computer Science and Information Technology University of Malakand KP Pakistan

With the rapid development of advanced driver assistance systems (ADAS), an automatic braking system has become increasingly important when faced with complicated traffic. The conventional decision-making method for the braking system is focused on security but lacks consideration of drivers' characteristics, which generates feelings of fear and frustration. We propose an anthropomorphic braking method based on vehicle kinematic characteristics and dynamic theories to improve the original system and eliminate the sense of jerking. Furthermore, on the basis of the traditional time to collision (TTC) algorithm, we consider the random motion of the target vehicle and develop a dynamic time to collision (DTTC) algorithm to meet different drivers' braking requirements. Therefore, in this study, the braking model is optimized by a series of driving simulator and real-vehicle braking tests. Finally, the validity and feasibility of the method are verified through the simulations of different braking modes. © 2019 Totem Publisher, Inc. All rights reserved.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Logical reinforcement learning method based on heuristic contour list

引用

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2008年第11期45卷 1824-1830页

作者： Liu, Quan Gao, Yang Chen, Daoxu Sun, Jigui Yao, Wangshu State Key Laboratory for Novel Software Technology Nanjing University Nanjing 210093 China Institute of Computer Science and Technology Soochow University Suzhou 215006 China Key Laboratory of Symbol Computation and Knowledge Engineering Jilin University Changchun 130012 China

Reinforcement learning gets optimal policy through trial-and-error and interaction with dynamic environment. Its properties of self-improving and online learning make reinforcement learning become one of most important machine learning methods. Against reinforcement learning has been 'curse of dimensionality' troubled by the problem the question, a method of heuristic contour list is proposed on the basis of relational reinforcement learning. The method can represent states, actions and Q-functions through using first-order predications with contour list. Thus advantages of Prolog list can be exerted adequately. The method is to combine logical predication rule with reinforcement learning. A new logical reinforcement learning-CCLORRL is formed and its convergence is proved. The method uses contour shape predicates to build shape state tables, drastically reducing the state space;Using heuristic rules to guide the choice of action can reduce choice blindness when the sample does not exist in the state space. The CCLORRL algorithm is used in the Tetris game. Experiments show that the method is more efficient.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Survey on Fairness in Large Language Models

arXiv

引用

arXiv 2023年

作者： Li, Yingji Du, Mengnan Song, Rui Wang, Xin Wang, Ying College of Computer Science and Technology Jilin University Changchun130012 China Department of Data Science New Jersey Institute of Technology Newark United States School of Artificial Intelligence Jilin University Changchun130012 China Key Laboratory of Symbol Computation and Knowledge Engineering Jilin University Ministry of Education Changchun130012 China

Large Language Models (LLMs) have shown powerful performance and development prospects and are widely deployed in the real world. However, LLMs can capture social biases from unprocessed training data and propagate the biases to downstream tasks. Unfair LLM systems have undesirable social impacts and potential harms. In this paper, we provide a comprehensive review of related research on fairness in LLMs. Considering the influence of parameter magnitude and training paradigm on research strategy, we divide existing fairness research into oriented to medium-sized LLMs under pre-training and fine-tuning paradigms and oriented to large-sized LLMs under prompting paradigms. First, for medium-sized LLMs, we introduce evaluation metrics and debiasing methods from the perspectives of intrinsic bias and extrinsic bias, respectively. Then, for large-sized LLMs, we introduce recent fairness research, including fairness evaluation, reasons for bias, and debiasing methods. Finally, we discuss and provide insight on the challenges and future directions for the development of fairness in LLMs. Copyright © 2023, The Authors. All rights reserved.

关键词： computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Nondestructive quantitative analysis of compound paracetamol and diphenhydramine hydrochloride powder using RBF networks

Nondestructive quantitative analysis of compound paracetamol...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Hong Zheng Li-Ming Wan Jing-Qing Jiang Yan-Chun Liang College of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun China College of Computer Science and Engineering Changchun University of Technology Changchun China Institute of General Development and Evaluation of Equipment EAAF of PLA Beijing China College of Mathematics and Computer Science Inner Mongolia University for the Nationalities Tongliao China

A method for simultaneous analysis of the two components of compound paracetamol and diphenhydramine hydrochloride powdered drugs on near-infrared (NIR) spectroscopy is developed by using a radial basis function (RBF) network. Nearest neighbor-clustering algorithm is used as the learning algorithm of RBF network. Comparisons of the results obtained from the RBF models with those from BP models show that it is feasible to use the RBF network in nondestructive quantitative analysis of the components of drugs.

关键词： Powders Radial basis function networks Clustering algorithms Educational institutions Computer science Drugs Spectroscopy Educational technology knowledge engineering Artificial neural networks

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：