检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on artificial intelligence, AAAI 2025

作者： Du, Chenghu Wang, Junyin Yu, Feng Xiong, Shengwu School of Computer Science and Artificial Intelligence Wuhan University of Technology China Shanghai Artificial Intelligence Laboratory China Interdisciplinary Artificial Intelligence Research Institute Wuhan College China School of Computer Science and Artificial Intelligence Wuhan Textile University China

ISBN: (纸本)157735897X

Efficiently applying fully supervised learning to virtual try-on tasks is challenging due to the lack of paired ground truth in available training samples. Recent works have achieved virtual try-ons by employing self-supervised learning-based inpainting paradigms. However, this approach is heavily dependent on the constraints of inpainting masks. An incorrect mask can mislead the generated results, while overly large mask areas can lose essential original information, thereby hindering the synthesis of high-quality results. To address these problems, we propose a latent diffusion model-based virtual try-on network that achieves fully supervised learning using the concept of cycle consistency and knowledge distillation. Specifically, we divide our approach into pretext and downstream tasks. In the pretext task, we generate a pseudo-label (pseudo-person image) to form paired training samples, which enables the downstream task to achieve fully supervised learning. To prevent the unreliable pseudo-person image from introducing irresponsible prior knowledge, we propose a noise-covering strategy, which aims at fully optimizing the pseudo-label to eliminate the impact of the incorrect inpainting mask as much as possible. Additionally, we propose a skin refinement loss to further enhance the generation of details in the skin region. Extended experiments demonstrate that our proposed method is superior to state-of-the-art methods. © 2025, Association for the Advancement of artificial intelligence (***). All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

GGF:Global Geometric Feature for Rotation-Invariant Point Cloud Understanding

引用

Journal of computer science & Technology 2025年第2期40卷 572-587页

作者： Yun-Zhe Xiao Fu Li Hao-Tian Wang Shao-Wu Yang College of Computer Science and Technology National University of Defense TechnologyChangsha 410073China Intelligent Game and Decision Laboratory Beijing and Tianjin Artificial Intelligence Innovation CenterTianjin 300457 China

Most 3D vision tasks related to point cloud understanding require rotation-invariant solutions. However, existing deep learning techniques for point clouds do not always ensure rotation invariance, and achieving rotation invariance necessitates data augmentation or professional networks, which is not feasible for generic point cloud understandingtasks. To address this issue, we propose a plug-and-play feature called Global Geometric Feature (GGF), as an effectiveand efficient solution achieving rotation invariance for generic point cloud understanding networks. GGF extracts a distributed global description by capturing geometric relationships between points and projecting the point cloud into a rotation-invariant feature space. We find that GGF can be directly integrated into a variety of point cloud understandingtasks without network modification. Our experimental evaluation shows that GGF can improve the performance of generic point cloud networks for rotation-invariant understanding without data augmentation and is comparable to dedicatedrotation-invariant methods.

关键词： point cloud rotation invariance point cloud understanding

来源：评论

学校读者我要写书评

暂无评论

Robust Motion-Guided Frame Sampler with Interpretive Evaluation for Video Action Recognition

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 6197-6208页

作者： Bai, Jing Zhang, Yuxiang Wang, Yiran Xiao, Zhu Xiong, Yong Jiao, Licheng Xidian University School of Artificial Intelligence Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xi'an710071 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Hunan Lianzhi Technology Co. Ltd Changsha410200 China

Due to the presence of redundancy and interference, frame sampling is a promising but challenging solution to mitigate the expensive computation of video action recognition. Although the motion prior has shown great potential for frame selection, existing motion-based strategies suffer from limitations in terms of robustness and interpretive evaluation. In this paper, we devise a robust frame sampling strategy called positive motion guided sampler (PMGSampler). It consists of two procedures, local motion capture and global motion statistics. At the local level, we propose two concepts about inter-frame motion amplitude and motion continuity, which helps to perceive the movement of subjects and identify abnormal events that may generate negative pseudo-motion information. Then, through a global analysis of the obtained local motions, the sampler becomes more sensitive to informative frames and robust to outliers. The proposed sampler can be applied to most existing models for improving recognition accuracy. We conduct extensive experiments on four widely-used benchmarks to demonstrate the superiority of our PMGSampler over other methods of the same type. In addition, to analyse how sampled frames influence action recognition, we present a visual interpretation method for video models, termed as spatio-temporal class activation map (STCAM). By introducing spatial and temporal branches, our STCAM is able to visualise the salience of spatio-temporal features. With the help of STCAM, we can further intuitively evaluate the performance of different sampling strategies. Code is available at https://***/zyx-cv/PMGSampler. © 2002-2012 IEEE.

关键词： Motion capture

来源：评论

学校读者我要写书评

暂无评论

A Multi-Objective Particle Swarm Optimization Algorithm Based on Decomposition and Multi-Selection Strategy

引用

computers, Materials & Continua 2025年第1期82卷 997-1026页

作者： Li Ma Cai Dai Xingsi Xue Cheng Peng School of Computer Science Shaanxi Normal UniversityXi’an710119China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of TechnologyFuzhou350118China Information Construction and Management Center and Institute of Artificial Intelligence and Educational New Productivity Ningxia Normal UniversityGuyuan756099China

The multi-objective particle swarm optimization algorithm(MOPSO)is widely used to solve multi-objective optimization *** the article,amulti-objective particle swarm optimization algorithmbased on decomposition and multi-selection strategy is proposed to improve the search ***,two update strategies based on decomposition are used to update the evolving population and external archive,***,a multiselection strategy is *** first strategy is for the subspace without a non-dominated *** the neighbor particles,the particle with the smallest penalty-based boundary intersection value is selected as the global optimal solution and the particle far away fromthe search particle and the global optimal solution is selected as the personal optimal solution to enhance global *** second strategy is for the subspace with a non-dominated *** the neighbor particles,two particles are randomly selected,one as the global optimal solution and the other as the personal optimal solution,to enhance local *** third strategy is for Pareto optimal front(PF)discontinuity,which is identified by the cumulative number of iterations of the subspace without non-dominated *** the subsequent iteration,a new probability distribution is used to select from the remaining subspaces to ***,an adaptive inertia weight update strategy based on the dominated degree is designed to further improve the search ***,the proposed algorithmis compared with fivemulti-objective particle swarm optimization algorithms and five multi-objective evolutionary algorithms on 22 test *** results show that the proposed algorithm has better performance.

关键词： Multi-objective optimization multi-objective particle swarm optimization decomposition multi-selection strategy

来源：评论

学校读者我要写书评

暂无评论

Understanding Resolution of Multi-Language Bugs: An Empirical Study on Apache Projects 17

Understanding Resolution of Multi-Language Bugs: An Empirica...

引用

17th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement, ESEM 2023

作者： Li, Zengyang Wang, Wenshuo Wang, Sicheng Liang, Peng Mo, Ran School of Computer Science Central China Normal University Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning Wuhan China School of Computer Science Wuhan University Wuhan China

ISBN: (纸本)9781665452236

Background: In modern software systems, more and more systems are written in multiple programming languages (PLs). There is no comprehensive investigation on the phenomenon of multi-programming-language (MPL) bugs, which resolution involves source files written in multiple PLs. Aim: This work investigated the characteristics of bug resolution in MPL software systems and explored the reasons why bug resolution involves multiple PLs. Method: We conducted an empirical study on 54 MPL projects selected from 655 Apache OSS projects, of which 66,932 bugs were analyzed. Results: (1) the percentage of MPL bugs (MPLBs) in the selected projects ranges from 0.17% to 42.26%, and the percentage of MPLBs for all projects as a whole is 10.01%;(2) 95.0% and 4.5% of all the MPLBs involve source files written in 2 and 3 PLs, respectively;(3) the change complexity resolution characteristics of MPLBs tend to be higher than those of single-programming-language bugs (SPLBs);(4) the open time for MPLBs is 19.52% to 529.57% significantly longer than SPLBs regarding 9 PL combinations;(5) the reopen rate of bugs involving the PL combination of JavaScript and Python reaches 20.66%;(6) we found 6 causes why the bug resolution involves multiple PLs and identified 5 cross-language calling mechanisms. Conclusion: MPLBs are related to increased development difficulty. © 2023 IEEE.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Parallel Committees: High-Performance, Scalable, Secure and Fault-Tolerant Data Replication Using a Novel Sharding Technique 5

Parallel Committees: High-Performance, Scalable, Secure and ...

引用

5th International Conference on Blockchain Computing and Applications, BCCA 2023

作者： Solat, Siamak Naït-Abdesselam, Farid Université de Paris Cité France ENGIE Laboratory for Computer Science & Artificial Intelligence France University of Missouri Kansas City United States

ISBN: (纸本)9798350339239

Distributed replication systems that use consensus mechanisms to process clients' requests have major limitations and problems in scalability, throughput, and performance. Such problems are mainly due to the time and message complexity of the consensus algorithms used in such systems. Sharding has already been implemented in several blockchain-based replication systems and although it has shown remarkable potential to improve performance and scalability, yet current sharding techniques have several significant scalability and security issues. In this paper, we propose a novel sharding technique for distributed replication systems that use a consensus to process clients' requests. We modified the approach of how nodes are allocated between shards through the public key generation process. Our approach effectively reduces undesirable cross-shard transactions that are more complex and costly to process than intra-shard transactions. Also, there is no concept of Beacon chain-as a shared-ledger between shards-which imposes additional scalability limitations and security issues on the network. With our approach, a network using a classical distributed consensus algorithm can grow outstandingly in number of nodes and still remain permissionless, © 2023 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Innovation Lessons from CEF Projects’ Management

Innovation Lessons from CEF Projects’ Management

引用

International Conference on Marketing and Technologies, ICMarkTech 2023

作者： Carreira, Rui Campolargo, Margarida Gemein, Olaf-Gerd Mulquin, Michael N2i-Maia Polytechnic Institute LIACC-Artificial Intelligence and Computer Science Laboratory Porto Portugal University of Maia Maia Portugal VeroCity Kiel Germany Brussels Belgium

ISBN: (纸本)9789819736973

Multinational CEF research projects are mostly focused on technical innovations;however, they should also innovate from the project management practices’ perspective. In particular, the ODALA project has already improved technical data management in cities by developing Mobility Data Toolkit Components and an Interoperability framework for Environmental Sensing. Therefore, this paper promotes and describes a concrete mixed-methods approach (i.e., qualitative and quantitative) in which CEF project partners were involved to understand the intricate details about such projects in order to originate generic good practices which should be made available to similar projects. That way multinational projects’ management may be facilitated by promoting cross-learning and also avoiding the most common pitfalls addressed by the respective partners. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Project management

来源：评论

学校读者我要写书评

暂无评论

Training Graph Neural Networks on Growing Stochastic Graphs 48

Training Graph Neural Networks on Growing Stochastic Graphs

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Cerviño, Juan Ruiz, Luana Ribeiro, Alejandro University of Pennsylvania Department of Electrical and Systems Engineering Philadelphia United States Mit Computer Science & Artificial Intelligence Laboratory Cambridge United States

ISBN: (纸本)9781728163277

Graph Neural Networks (GNNs) rely on graph convolutions to exploit meaningful patterns in networked data. Based on matrix multiplications, convolutions incur in high computational costs leading to scalability limitations in practice. To overcome these limitations, proposed methods rely on training GNNs in smaller number of nodes, and then transferring the GNN to larger graphs. Even though these methods are able to bound the difference between the output of the GNN with different number of nodes, they do not provide guarantees against the optimal GNN on the very large graph. In this paper, we propose to learn GNNs on very large graphs by leveraging the limit object of a sequence of growing graphs, the graphon. We propose to grow the size of the graph as we train, and we show that our proposed methodology - learning by transference - converges to a neighborhood of a first order stationary point on the graphon data. A numerical experiment validates our proposed approach. © 2023 IEEE.

关键词： Graph Neural Networks Graphons

来源：评论

学校读者我要写书评

暂无评论

ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors

ShieldLM: Empowering LLMs as Aligned, Customizable and Expla...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Zhang, Zhexin Lu, Yida Ma, Jingyuan Zhang, Di Li, Rui Ke, Pei Sun, Hao Sha, Lei Sui, Zhifang Wang, Hongning Huang, Minlie Group DCST Tsinghua University China School of Computer Science Key Laboratory of Computational Linguistics Ministry of Education Peking University China Institute of Artificial Intelligence Beihang University Zhongguancun Laboratory Beijing China

ISBN: (纸本)9798891761681

The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs' responses in an aligned, customizable and explainable manner. In this paper, we propose ShieldLM, an LLM-based safety detector, which aligns with common safety standards, supports customizable detection rules, and provides explanations for its decisions. To train ShieldLM, we compile a large bilingual dataset comprising 14,387 query-response pairs, annotating the safety of responses based on various safety standards. Through extensive experiments, we demonstrate that ShieldLM surpasses strong baselines across four test sets, showcasing remarkable customizability and explainability. Besides performing well on standard detection datasets, ShieldLM has also been shown to be effective as a safety evaluator for advanced LLMs. ShieldLM is released at https://***/thu-coai/ShieldLM to support accurate and explainable safety detection under various safety standards. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Phasmatodea Population Evolution Algorithm Based on Spiral Mechanism and Its Application to Data Clustering

引用

computers, Materials & Continua 2025年第4期83卷 475-496页

作者： Jeng-Shyang Pan Mengfei Zhang Shu-Chuan Chu Xingsi Xue Václav Snášel College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao266590China School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing210044China Department of Information Management Chaoyang University of TechnologyTaichung41349TaiwanChina Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of TechnologyFuzhou350118China Faculty of Electrical Engineering and Computer Science VŠB-Technical University of OstravaOstrava70833Czech Republic

Data clustering is an essential technique for analyzing complex datasets and continues to be a central research topic in data *** clustering algorithms,such as K-means,are widely used due to their simplicity and *** paper proposes a novel Spiral Mechanism-Optimized Phasmatodea Population Evolution Algorithm(SPPE)to improve clustering *** SPPE algorithm introduces several enhancements to the standard Phasmatodea Population Evolution(PPE)***,a Variable Neighborhood Search(VNS)factor is incorporated to strengthen the local search capability and foster population ***,a position update model,incorporating a spiral mechanism,is designed to improve the algorithm’s global exploration and convergence ***,a dynamic balancing factor,guided by fitness values,adjusts the search process to balance exploration and exploitation *** performance of SPPE is first validated on CEC2013 benchmark functions,where it demonstrates excellent convergence speed and superior optimization results compared to several state-of-the-art metaheuristic *** further verify its practical applicability,SPPE is combined with the K-means algorithm for data clustering and tested on seven *** results show that SPPE-K-means improves clustering accuracy,reduces dependency on initialization,and outperforms other clustering *** study highlights SPPE’s robustness and efficiency in solving both optimization and clustering challenges,making it a promising tool for complex data analysis tasks.

关键词： Phasmatodea population evolution algorithm data clustering meta-heuristic algorithm

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：