检索结果-内蒙古大学图书馆

Cross-Domain Animal Pose Estimation with Skeleton Anomaly-Aware Learning

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Han, Le Chen, Kaixuan Zhao, Lei Jiang, Yangbo Wang, Pengfei Zheng, Nenggan Zhejiang Hangzhou310007 China Zhejiang University College of Computer Science and Technology Zhejiang Hangzhou310007 China Zhejiang University State Key Laboratory of Blockchain and Data Security Zhejiang Hangzhou310007 China Institute of Blockchain and Data Security. China Zhejiang University School of Software Technology Ningbo China Zhejiang University State Key Lab of Brain-Machine Intelligence Hangzhou310007 China Zhejiang Provincial Government ZJU Collaborative Innovation Center for Artificial Intelligence by MOE Hangzhou310007 China Bengbu University School of Computer and Information Engineering Bengbu233030 China

Animal pose estimation is often constrained by the scarcity of annotations and the diversity of scenarios and species. The pseudo-label generation based unsupervised domain adaptation paradigm, which discriminates the predicted keypoints of unlabeled data based on the skeleton position consistency, has demonstrated effectiveness for such problems. However, existing methods generate pseudo-labels with massive false positives, because they cannot effectively distinguish sample pairs with the same errors. In this study, we propose a cross-domain animal pose estimation model from a novel perspective of skeleton anomaly learning. We construct a graph contrastive learning mechanism to acquire the skeleton anomaly-aware knowledge, which enables the generation of accurate pseudo-labels for target domain and imposes graph constraint on unlabeled data. And a skeleton anomaly-feedback based domain adaptation framework is designed to facilitate implicit alignment of object-specific features and joint training of cross-domain. Besides, we propose a novel rat pose dataset named UDARP-9.4K to address the gap of small-sized animal pose datasets encompassing diverse experimental scenarios. The related datasets are reviewed and evaluated in detail. Extensive experiments are conducted on UDARP-9.4K and two public datasets to demonstrate the superiority of the proposed model in cross-scenarios and cross-species animal pose estimation tasks. Further analysis reveals the effectiveness of the proposed model for skeleton structure feature learning. The UDARP-9.4K dataset is available here. © 1991-2012 IEEE.

关键词： Invertebrates

来源：评论

学校读者我要写书评

暂无评论

A Review-Based Reputation Evaluation Approach for Web Services

引用

Journal of Computer Science & Technology 2009年第5期24卷 893-900页

作者：李海华杜小勇 Member 田萱 Key Laboratory of Data Engineering and Knowledge Engineering (Renmin University of China) MOE Beijing 100872 China School of Information Renmin University of China Beijing 100872 China School of Information Science & Technology Beijing Forestry University Beijing 100083 China

Web services are commonly perceived as an environment of both offering opportunities and threats. In this environment, one way to minimize threats is to use reputation evaluation, which can be computed, for example, through transaction feedback. However, the current feedback-based approach is inaccurate and ineffective because of its inner limitations （e.g., feedback quality problem）. As the main source of feedback, the qualities of existing on-line reviews are often varied greatly from low to high, the main reasons include：（1） they have no standard expression formats, （2） dishonest comments may exist among these reviews due to malicious attacking. Up to present, the quality problem of review has not been well solved, which greatly degrades their importance on service reputation evaluation. Therefore, we firstly present a novel evaluation approach for review quality in terms of multiple metrics. Then, we make a further improvement in service reputation evaluation based on those filtered reviews. Experimental results show the effectiveness and efficiency of our proposed approach compared with the naive feedback-based approaches.

关键词： Web services reputation evaluation review quality measurement

来源：评论

学校读者我要写书评

暂无评论

Lawyer information integration and recommendation by multi-source information validation

Lawyer information integration and recommendation by multi-s...

引用

2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011

作者： Liu, Tao Fan, Biao Hu, He Du, Xiao-Yong Key Laboratory of Data Engineering and Knowledge Engineering MOE School of Information Renmin University of China Beijing 100872 China

ISBN: (纸本)9781457703065

On the internet, all-round lawyer information is located at separated information sources, which prevent web users from effective information acquisition. In order to build a unified view of separated, heterogeneous, and often redundant lawyer information, we propose a new information integration method using multi-source information cross-validation. Based on the unified integrated data, a lawyer recommendation system is built. Several key technologies are presented and evaluated, including the multi-source information acquisition and validation. Experimental results indicate the key techniques used in the system are effective for lawyer information integration and recommendation. © 2011 IEEE.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Utility-based anonymisation for dataset with multiple sensitive attributes

Utility-based anonymisation for dataset with multiple sensit...

引用

作者： Wang, Lixia Zhu, Qing Key Laboratory for Data Engineering and Knowledge Engineering MOE School of Information Renmin University of China Beijing100872 China

Privacy-preserving data publication problem has attracted more and more attentions in recent years. A lot of related research works have been done towards dataset with single sensitive attribute. However, usually, original dataset contains more than one sensitive attribute. In this paper, we apply k-anonymity principle to solve the data publication problem for dataset with multiple sensitive attributes. We first cluster sensitive values based on a utility matrix. Then, we use a greedy strategy to partition tuples into equivalence classes. Our method can guarantee that the size of equivalence class is k except the last one, which reduces information loss. Also, we can guarantee the diversity of sensitive value in an equivalence class, which can protect privacy against the homogeneity attack. Experiments on a real dataset show that our method performs well on information loss, which indicates that we can guarantee data utility while protecting personal privacy. Copyright © 2016 Inderscience Enterprises Ltd.

关键词： Equivalence classes

来源：评论

学校读者我要写书评

暂无评论

Lightweight data mining based database system self-optimization: A case study

Lightweight data mining based database system self-optimizat...

引用

Joint International Conference on Advances in data and Web Management, APWeb/WAIM 2009

作者： Qin, Xiongpai Cao, Wei Wang, Shan Key Laboratory of Data Engineering and Knowledge Engineering School of Information Renmin University of China MOE Beijing 100872 China

ISBN: (纸本)9783642006715

With the system becoming more complex and workloads becoming more fluctuating, it is very hard for DBA to quickly analyze performance data and optimize the system, self optimization is a promising technique. A data mining based optimization scheme for the lock table in database systems is presented. After trained with performance data, a neural network become intelligent enough to predict system performance with newly provided configuration parameters and performance data. During system running, performance data is collected continuously for a rule engine, which chooses the proper parameter of the lock table for adjusting, the rule engine relies on the trained neural network to precisely provide the amount of adjustment. The selected parameter is adjusted accordingly. The scheme is implemented and tested with TPC-C workload, system throughput increases by about 16 percent. © Springer-Verlag Berlin Heidelberg 2009.

关键词： Locks (fasteners)

来源：评论

学校读者我要写书评

暂无评论

Simulation of main memory database parallel recovery 09

Simulation of main memory database parallel recovery

引用

2009 Spring Simulation Multiconference, SpringSim 2009

作者： Qin, Xiongpai Cao, Wei Wang, Shan Key Laboratory of Data Engineering and Knowledge Engineering School of Information Renmin University of China MOE Beijing100872 China

The paper describes the details of using J-SIM in main memory database parallel recovery simulation. In update intensive main memory database systems, I/O is still the dominant performance bottleneck. A proposal of parallel recovery scheme for large-scale update intensive main memory database systems is presented. Simulation provides a faster way of evaluating the new idea compared to actual system implementation. J-SIM is an open source discrete time simulation software package. The simulation implementation using J-SIM is elaborated in terms of resource modeling, transaction processing system modeling and workload modeling. Finally, with simulation results analyzed, the effectiveness of the parallel recovery scheme is verified and the feasibility of J-SIM's application in main memory database system simulation is demonstrated.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Effective density queries for moving objects in road networks

Effective density queries for moving objects in road network...

引用

9th Asia-Pacific Web Conference/8th International Conference on Web-Age Information Management (APWeb/WAIM 2007)

作者： Lai, Caifeng Wang, Ling Chen, Jidong Meng, Xiaofeng Zeitouni, Karine School of Information Renmin University of China Key Laboratory of Data Engineering and Knowledge Engineering MOE PRISM Versailles Saint-Quentin University France

ISBN: (纸本)9783540724834

Recent research has focused on density queries for moving objects in highly dynamic scenarios. An area is dense if the number of moving objects it contains is above some threshold. Monitoring dense areas has applications in traffic control systems, bandwidth management, collision probability evaluation, etc. All existing methods, however, assume the objects moving in the Euclidean space. In this paper, we study the density queries in road networks, where density computation is determined by the length of the road segment and the number of objects on it. We define an effective road-network density query guaranteeing to obtain useful answers. We then propose the cluster-based algorithm for the efficient computation of density queries for objects moving in road networks. Extensive experimental results show that our methods achieve high efficiency and accuracy for finding the dense areas in road networks. © Springer-Verlag Berlin Heidelberg 2007.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Generalized Unique Game Problem

引用

Journal of Computational Information Systems 2012年第16期8卷 6551-6557页

作者： Cui, Peng Key Laboratory of Data Engineering and Knowledge Engineering School of Information Resource Management Renmin University of China Beijing 100872 China

In this paper, the author defines Generalized Unique Game Problem (GUGP), where weights of the edges are allowed to be negative. Two special types of GUGP are illuminated, GUGP-NWA, where the weights of all edges are negative, and GUGP-PWT (ρ), where the total weight of all edges are positive and the negative-positive ratio is at most ρ. The author investigates the counterpart of the Unique Game Conjecture on GUGP-PWT (ρ). The author shows that Unique Game Conjecture on GUGP-PWT (1) holds true, and Unique Game Conjecture on GUGP-PWT (1=2) holds true, if the 2-to-1 Conjecture holds true. The author poses an open problem whether Unique Game Conjecture holds true on GUGP-PWT (ρ) with 0 < ρ < 1. © 2012 Binary Information Press.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Partial Label Learning via Conditional-Label-Aware Disambiguation

引用

Journal of Computer Science & Technology 2021年第3期36卷 590-605页

作者： Peng Ni Su-Yun Zhao Zhi-Gang Dai Hong Chen Cui-Ping Li Key Laboratory of Data Engineering and Knowledge Engineering(Renmin University of China) Ministry of Education Beijing 100087China School of Information Renmin University of ChinaBeijing 100087China

Partial label learning is a weakly supervised learning framework in which each instance is associated with multiple candidate labels,among which only one is the ground-truth *** paper proposes a unified formulation that employs proper label constraints for training models while simultaneously performing *** existing partial label learning approaches that only leverage similarities in the feature space without utilizing label constraints,our pseudo-labeling process leverages similarities and differences in the feature space using the same candidate label constraints and then disambiguates noise *** experiments on artificial and real-world partial label datasets show that our approach significantly outperforms state-of-the-art counterparts on classification prediction.

关键词： disambiguation partial label learning similarity and dissimilarity weak supervision

来源：评论

学校读者我要写书评

暂无评论

Efficient Model Store and Reuse in an OLML database System

引用

Journal of Computer Science & Technology 2021年第4期36卷 792-805页

作者： Jian-Wei Cui Wei Lu Xin Zhao Xiao-Yong Du Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education Renmin University of China Beijing 100872China School of Information Renmin University of ChinaBeijing 100872China

Deep learning has shown significant improvements on various machine learning tasks by introducing a wide spectrum of neural network ***,for these neural network models,it is necessary to label a tremendous amount of training data,which is prohibitively expensive in *** this paper,we propose OnLine Machine Learning(OLML)database which stores trained models and reuses these models in a new training task to achieve a better training effect with a small amount of training *** efficient model reuse algorithm AdaReuse is developed in the OLML ***,AdaReuse firstly estimates the reuse potential of trained models from domain relatedness and model quality,through which a group of trained models with high reuse potential for the training task could be selected ***,multi selected models will be trained iteratively to encourage diverse models,with which a better training effect could be achieved by *** evaluate AdaReuse on two types of natural language processing(NLP)tasks,and the results show AdaReuse could improve the training effect significantly compared with models training from scratch when the training data is *** on AdaReuse,we implement an OLML database prototype system which could accept a training task as an SQL-like query and automatically generate a training plan by selecting and reusing trained *** studies are conducted to illustrate the OLML database could properly store the trained models,and reuse the trained models efficiently in new training tasks.

关键词： model selection model reuse OnLine Machine Learning(OLML)database

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：