检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhao Xie Tian Gao Kewei Wu Jiao Chang Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology

The causality relation modeling remains a challenging task for group activity recognition. The causality relations describe the influence on the centric actor (effect actor) from its correlative actors (cause actors). Most existing graph models focus on learning the actor relation with synchronous temporal features, which is insufficient to deal with the causality relation with asynchronous temporal features. In this paper, we propose an Actor-Centric Causality Graph Model, which learns the asynchronous temporal causality relation with three modules, i.e., an asynchronous temporal causality relation detection module, a causality feature fusion module, and a causality relation graph inference module. First, given a centric actor and its correlative actor, we analyze their influences to detect causality relation. We estimate the self influence of the centric actor with self regression. We estimate the correlative influence from the correlative actor to the centric actor with correlative regression, which uses asynchronous features at different timestamps. Second, we synchronize the two action features by estimating the temporal delay between the cause action and the effect action. The synchronized features are used to enhance the feature of the effect action with a channel-wise fusion. Third, we describe the nodes (actors) with causality features and learn the edges by fusing the causality relation with the appearance relation and distance relation. The causality relation graph inference provides crucial features of effect action, which are complementary to the base model using synchronous relation inference. Experiments show that our method achieves state-of-the-art performance on the Volleyball dataset and Collective Activity dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive data-Free Quantization

Adaptive Data-Free Quantization

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Biao Qian Yang Wang Richang Hong Meng Wang Key Laboratory of Knowledge Engineering with Big Data Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology China

data-free quantization (DFQ) recovers the performance of quantized network (Q) without the original data, but generates the fake sample via a generator (G) by learning from full-precision network (P), which, however, is totally independent of Q, overlooking the adaptability of the knowledge from generated samples, i.e., informative or not to the learning process of Q, resulting into the overflow of generalization error. Building on this, several critical questions — how to measure the sample adaptability to Q under varied bit-width scenarios? whether the largest adaptability is the best? how to generate the samples with adaptive adaptability to improve Q's generalization? To answer the above questions, in this paper, we propose an Adaptive data-Free Quantization (AdaDFQ) method, which revisits DFQ from a zero-sum game perspective upon the sample adaptability between two players — a generator and a quantized network. Following this viewpoint, we further define the disagreement and agreement samples to form two boundaries, where the margin between two boundaries is optimized to adaptively regulate the adaptability of generated samples to Q, so as to address the over-and-under fitting issues. Our AdaDFQ reveals: 1) the largest adaptability is NOT the best for sample generation to benefit Q's generalization; 2) the knowledge of the generated sample should not be informative to Q only, but also related to the category and distribution information of the training data for P. The theoretical and empirical analysis validate the advantages of AdaDFQ over the state-of-the-arts. Our code is available at https://***/hfutqian/AdaDFQ.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Minimizing XML Queries Using a Family of Constraints

Minimizing XML Queries Using a Family of Constraints

引用

International Conference on Fuzzy Systems and knowledge Discovery (FSKD)

作者： Xiping Liu Changxuan Wan School of Information Technology Jiangxi Key Laboratory of Data and Knowledge Engineering Jiangxi University of Finance and Economics Nanchang China

An effective way to optimize XML queries is to minimize XML queries. In this paper, we improve redundance elimination in XPath queries greatly by incorporating two novel kinds of constraints: parent constraint and sibling constraint, and by extending the tractable fragment to include descendant-or-self axis. The two novel kinds of constraints, together with child constraint and descendant constraint, form a family of constraints, which complicate the problem but offer possibilities for further minimization. Two techniques, tree augmentation and simulation augmentation, are employed to cope with constraints. We elaborate on the minimizing algorithms and running efficiencies both in the absence and in the presence of various kinds of constraints.

关键词： XML Polynomials Minimization methods Information technology Finance Laboratories knowledge engineering Constraint optimization Fuzzy systems System testing

来源：评论

学校读者我要写书评

暂无评论

DSOSW: A Deleting Strategy in Mining Frequent Itemsets over Sliding Window of Stream

DSOSW: A Deleting Strategy in Mining Frequent Itemsets over ...

引用

International Symposiums on Information Processing (ISIP)

作者： Haifeng Li Hong Chen Key Laboratory of Data Engineering and Knowledge Engineering MOE Renmin University of China Beijing China Renmin University of China Beijing CN

Most traditional mining approaches of frequent item sets consider mainly on databases and thus can use the second storage and need multiple scans which are not adapted to mining of stream. Some new algorithms over stream's sliding window are presented recently, which perform addition and deletion over stream independently, so the common deleting strategy which removes the earliest transaction is used when the window slides. This paper considers both operations together to reduce the computation cost, consequently, three deleting strategies are proposed to improve the performance with little precision loss. The experimental results show that these strategies over current method are effective and efficient.

关键词： data mining Itemsets Writing Laboratories data engineering knowledge engineering Transaction databases Information processing Computational efficiency Performance loss

来源：评论

学校读者我要写书评

暂无评论

The lifestyle transition of Arthrobotrys oligospora is mediated by microRNA-like RNAs

引用

Science China(Life Sciences) 2020年第4期63卷 543-551页

作者： Xinglai Ji Heng Li Weihua Zhang Jiai Wang Lianming Liang Chenggang Zou Zefen Yu Shuqun Liu Ke-Qin Zhang State Key Laboratory for Conservation and Utilization of Bio-Resources in Yunnan Yunnan UniversityKunming 650091China Smart Health Big Data Analysis and Location Services Engineering Lab of Jiangsu Province Nanjing University of Posts and TelecommunicationsNanjing 210023China Institute of Medical Biology Chinses Academy of Medical Sciences&Peking Union Medical CollegeKunming 650118China

The lifestyle transition of fungi,defined as switching from taking organic material as nutrients to pathogens,is a fundamental phenomenon in ***,the mechanisms of such transition remain largely *** we show microRNA-like RNAs(milRNAs)play a key role in fungal lifestyle transition for the first *** identified milRNAs by small RNA sequencing in Arthrobotrys oligospora,a known nematode-trapping *** them,7 highly expressed milRNAs were confirmed by northern-blot *** out two milRNAs significantly decreased ***’s ability to switch *** further identified that two of these milRNAs were associated with argonaute protein QDE-2 by RNA-immunoprecipitation(RIP)*** of the predicted target genes of milRNAs were found in immunoprecipitation(IP)products of *** of argonaute gene qde-2 also led to serious defects in lifestyle ***,knocking out individual milRNAs or qde-2 lead to diverse responses under different conditions,and qde-2 itself may be targeted by the ***,it indicates the lifestyle transition of fungi is mediated by milRNAs through RNA interference(RNAi)machinery,revealing the wide existence of miRNAs in fungi kingdom and providing new insights into understanding the adaptation of fungi from scavengers to predators and the mechanisms underlying fungal infections.

关键词： lifestyle transition Arthrobotrys oligospora,microRNA-like RNAs nematode-trapping fungi trap induction fungal adaptation

来源：评论

学校读者我要写书评

暂无评论

Stable Learning via Triplex Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5267-5276页

作者： Yang, Shuai Jiang, Tingting Dang, Qianlong Gu, Lichuan Wu, Xindong Anhui Agricultural University School of Information and Artificial Intelligence Hefei230036 China Anhui Provincial Engineering Research Center for Agricultural Information Perception and Intelligent Computing Hefei230036 China Northwest A & F University College of Science Yangling712100 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China

Stable learning aims to learn a model that generalizes well to arbitrary unseen target domain by leveraging a single source domain. Recent advances in stable learning have focused on balancing the distribution of confounders for each feature to eliminate spurious correlations. However, previous studies treat all features equally without considering the difficulties of confounder balancing associated with different features, and regard irrelevant features as confounders, deteriorating generalization performance. To tackle these issues, this article proposes a novel triplex learning (TriL) based stable learning algorithm, which performs sample reweighting, causal feature selection, and representation learning to remove spurious correlations. Specifically, first, TriL adaptively assigns weights to the confounder balancing term of each feature in accordance with the difficulties of confounder balancing, and aligns the confounder distribution of each feature by learning a group of sample weights. Second, TriL integrates the sample weights into a weighted cross-entropy model to compute causal effects of features for excluding irrelevant features from the confounder set. Finally, TriL relearns a set of sample weights and uses them to guide a new supervised dual-autoencoder containing two classifiers to learn feature representations. TriL forces the results of two classifiers to remain consistent for removing spurious correlations by using a cross-classifier consistency regularization. Extensive experiments on synthetic and two real-world datasets show the superiority of TriL compared with seven methods. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

USER: A unified information search and recommendation model based on integrated behavior sequence

arXiv

引用

arXiv 2021年

作者： Yao, Jing Dou, Zhicheng Xie, Ruobing Lu, Yanxiong Wang, Zhiping Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China WeChat Search Application Department Tencent China Beijing Key Laboratory of Big Data Management and Analysis Methods Key Laboratory of Data Engineering and Knowledge Engineering MOE

Search and recommendation are the two most common approaches used by people to obtain information. They share the same goal - satisfying the user's information need at the right time. There are already a lot of Internet platforms and Apps providing both search and recommendation services, showing us the demand and opportunity to simultaneously handle both tasks. However, most platforms consider these two tasks independently - they tend to train separate search model and recommendation model, without exploiting the relatedness and dependency between them. In this paper, we argue that jointly modeling these two tasks will benefit both of them and finally improve overall user satisfaction. We investigate the interactions between these two tasks in the specific information content service domain. We propose first integrating the user's behaviors in search and recommendation into a heterogeneous behavior sequence, then utilizing a joint model for handling both tasks based on the unified sequence. More specifically, we design the Unified Information SEarch and Recommendation model (USER), which mines user interests from the integrated sequence and accomplish the two tasks in a unified way. Experiments on a dataset from a real-world information content service platform verify that our model outperforms separate search and recommendation baselines. Copyright © 2021, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Dynamic programming based top-k aggregate queries in uncertain database

引用

Journal of Information and Computational Science 2009年第3期6卷 1589-1596页

作者： Liu, Dexi School of Information Technology Jiangxi University of Finance and Economics Nanchang 330013 China Jiangxi Key Laboratory of Data and Knowledge Engineering Nanchang 330013 China

A Top-k aggregate query ranks groups of tuples by their aggregate values, sum or average for example, and returns k groups with the highest aggregate values. We propose a dynamic programming based method to process uncertain kRanks aggregate queries in uncertain database, where the number of retrieved tuples and group states generated on these tuples are minimized. Our method has two levels, group state generation and U-x-kRanks query processing. In the former level, group states, which satisfy the properties of x-tuple [13], are generated one after the other according to their aggregate values, while in the latter level, dynamic programming based uncertain x-tuple kRanks query processing [15] are employed to return the answers. Comprehensive experiments on different data sets demonstrate the effectiveness of the proposed solutions. 1548-7741/ Copyright © 2009 Binary Information Press.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Managing data provenance in database

引用

Journal of Information and Computational Science 2009年第1期6卷 423-431页

作者： Liu, Xiping Wan, Changxuan Jiang, Tengjiao School of Information Technology Jiangxi University of Finance and Economics Nanchang 330013 China Jiangxi Key Laboratory of Data and Knowledge Engineering Nanchang 330013 China

The paper studies the management problem of data provenance. Firstly, two data models, which enhance the traditional relational model and tree model, are proposed to reveal the basic nature of data provenance. To answer the new challenges to data management posed by data provenance, DBPro, a new database with the ability of managing both data and provenance, is introduced. The storage of data provenance is a core problem in designing DBPro, which is coped with two storage schemes. The comparison between these two storage schemes is also conducted. © 2009 Binary Information Press.

关键词： database systems

来源：评论

学校读者我要写书评

暂无评论

Predictable recovery for replication real-time main memory databases using request logs

引用

Journal of Information and Computational Science 2009年第3期6卷 1607-1614页

作者： Liao, Guoqiong Li, Jing School of Information Technology Jiangxi University of Finance and Economics Nanchang 330013 China Jiangxi Key Laboratory of Data and Knowledge Engineering Nanchang 330013 China

Reliable telecommunication applications in future need the supports from replication real-time main memory databases. In order to improve recovery performance and provide predictable recovery, this paper proposes a new recovery method using request logs for the databases. Firstly, the format and correctness of request logs are discussed. Then, a recovery model based on request logs is given. Thirdly, the recovery algorithms for local recovery and resynchronization are provided in details. At last, a formula to estimate denial-of-service time (DoS) is presented for predictable recovery. 1548-7741/ Copyright © 2009 Binary Information Press.

关键词： Recovery

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：