检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Tan, Jiawei Wang, Hongxing Dang, Kang Li, Jiaxin Ou, Zhilong Key Laboratory of Dependable Service Computing Cyber Physical Society Chongqing University Ministry of Education China School of Big Data and Software Engineering Chongqing University China Xi’an Jiaotong-Liverpool University Suzhou China

Video scene detection involves assessing whether each shot and its surroundings belong to the same scene. Achieving this requires meticulously correlating multi-modal cues, e.g. visual entity and place modalities, among shots and comparing semantic changes around each shot. However, most methods treat multi-modal semantics equally and do not examine contextual differences between the two sides of a shot, leading to sub-optimal detection performance. In this paper, we propose the Modality-Aware Shot Relating and Comparing approach (MASRC), which enables relating shots per their own characteristics of visual entity and place modalities, as well as comparing multi-shots similarities to have scene changes explicitly encoded. Specifically, to fully harness the potential of visual entity and place modalities in modeling shot relations, we mine long-term shot correlations from entity semantics while simultaneously revealing short-term shot correlations from place semantics. In this way, we can learn distinctive shot features that consolidate coherence within scenes and amplify distinguishability across scenes. Once equipped with distinctive shot features, we further encode the relations between preceding and succeeding shots of each target shot by similarity convolution, aiding in the identification of scene ending shots. We validate the broad applicability of the proposed components in MASRC. Extensive experimental results on public benchmark datasets demonstrate that the proposed MASRC significantly advances video scene detection. © 2024, CC BY-NC-ND.

关键词： Footage counters

来源：评论

学校读者我要写书评

暂无评论

Projection methods with linesearch technique for pseudomonotone equilibrium problems and fixed point problems

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2021年第1期83卷 3-14页

作者： Zhu, Li-Jun Yao, Yonghong Postolache, Mihai The Key Laboratory of Intelligent Information and Big Data Processing of NingXia Province North Minzu University Yinchuan750021 China Health Big Data Research Institute of North Minzu University Yinchuan750021 China The Key Laboratory of Intelligent Information and Big Data Processing of NingXia Province North Minzu University Yinchuan750021 China Health Big Data Research Institute of North Minzu University Yinchuan750021 China School of Mathematical Sciences Tiangong Uni-versity Tianjin300387 China Center for General Education China Medical University Taichung40402 Taiwan Department of Interior Design Asia University Taichung Taiwan Romanian Academy Gh. Mihoc-C. Iacob Institute of Mathematical Statistics and Applied Mathematics Bucharest050711 Romania University "Politehnica" of Bucharest Department of Mathematics and Informatics Bucharest060042 Romania

In this paper, we discuss pseudomonotone equilibrium problems and fixed point problems in real Hilbert spaces. With the help of linesearch technique, we propose a projection algorithm without any Lipschitz-type condition for solving equilibrium problems and fixed point problems. We show that the constructed algorithm converges strongly to a common element of the investigated problems. © 2021, Politechnica University of Bucharest. All rights reserved.

关键词： Computers

来源：评论

学校读者我要写书评

暂无评论

Mining World Indicators for Analyzing and Modeling the Development of Countries

引用

ACM/IMS Transactions on data Science 2021年第4期2卷 1–27页

作者： Huang, Hong Chi, Mingyuan Song, Yu Jin, Hai The National Engineering Research Center for Big Data Technology and System Key Laboratory of Service Computing Technology and System Ministry of Education School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

The world indicators released by the World Bank or other organizations usually give the basic public knowledge about the world. However, separate and static index lacks the complex interplay among different indicators and thus cannot help us have an overall understanding of the world. To this end, we study the world indicators from a different angle. Firstly, we discover that there exist correlations between indicators either from a static view or from a dynamic view. Moreover, taking the trade and diplomatic relationships into consideration, we construct a multi-relational network to depict the interactions between different countries, and propose a Multiple Relations to Vector (MR2vec) model to study world indicators from a network perspective. The experimental results show the changes of world indicators are predictable with the proposed model, and our proposed MR2vec has wide adaptability in predicting multi-relation networks. © 2022 Copyright held by the owner/author(s).

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Deep Closest Point Method for Point Cloud Registration

Semi-supervised Deep Closest Point Method for Point Cloud Re...

引用

2021 International Conference on Robotics Automation and intelligent Control, ICRAIC 2021

作者： Wu, Yong Shen, Lingfeng Li, Ping Jiangsu Power Transmission and Transformation Co. Ltd. Nanjing211106 China College of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing210023 China

Point cloud registration is one of the key issues in fields that need 3D scenes with global vision, including 3D scene reconstruction in robot technology, high-accuracy 3D map reconstruction in automatic driving, 3D reconstruction of real-time monitoring underground tunnel. Recently, point cloud registration methods based on deep neural networks have made great progress by learning from a large amount of well-aligned point cloud pairs. However, these large-scale labelled samples are usually difficult to obtain in the real-world applications such as visual simultaneous location and mapping of mobile robots which obtains unlabelled scene images in real time. To solve this problem, we propose a deep point cloud registration method based on the semi-supervised learning. Specifically, for the problem of less supervised data, we use Iterative Closest Point (ICP) algorithm to generate pseudo labels for the point cloud samples with unknown rigid transformations, effectively increasing the number of supervised data;in order to amend the pseudo labels, we design an alternating optimization algorithm to jointly learn the pseudo labels and deep point cloud registration model. The deep point cloud registration model and ICP are used alternately to continuously improve the precision of pseudo labels and the performance of the deep model. Experimental results show that this method can still obtain a reliable point cloud registration model even when just observing a small amount of point cloud samples with ground truth labels. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： Surface measurement

来源：评论

学校读者我要写书评

暂无评论

Application of Computer Software Simulation in Building Fire Evacuation Engineering:A Case Study of a University Library in Beijing

Application of Computer Software Simulation in Building Fire...

引用

第35届中国控制与决策会议

作者： Shun Wang Hongyan Ma Shengyan Li Wei He School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture School of Electrical and Information Engineering Institute of Distributed Energy Storage Safety Big DataBeijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture

University library is an important building for teaching and *** atrium library has the characteristics of good lighting and flexible use,and the atrium structure was extensively ***,the fire in the atrium library will cause more serious *** this paper,we build a fire and evacuation model of a university atrium library and conduct a simulation *** with BIM technology,we restored the physical information of a university library and establish a fire *** was used to simulate the fire somke diffusion,and the smoke factors were analyzed to derive the available safe evacuation time(ASET).Pathfinder was used to simulate personnel evacuation,which determines the required safe evacuation time(REST).The simulation results show that the visibility of the smoke is the most important factor affecting personnel evacuation,and the personnel needs 108 s to evacuate the fire area and 291 s to enter the stairwell to *** the personnel in the library by area can shorten the evacuation time by about 74 *** study is expected to provide support for the fire simulation and personnel evacuation in atrium building.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Pruning Method Based on the Dissimilarity of Angle Among Channels and Filters

A Pruning Method Based on the Dissimilarity of Angle Among C...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Jiayi Yao Ping Li Xiatao Kang Yuzhe Wang Changsha University of Science and Technology China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transp China

Convolutional Neural Network (CNN) is more and more widely used in various fileds, and its computation and memory-demand are also increasing significantly. In order to make it applicable to limited conditions such as embedded application, network compression comes out. Among them, researchers pay more attention to network pruning. In this paper, we encode the convolution network to obtain the similarity of different encoding nodes, and evaluate the connectivity-power among convolutional kernels on the basis of the similarity. Then impose different level of penalty according to different connectivity-power. Meanwhile, we propose Channel Pruning base on the Dissimilarity of Angle (DACP). Firstly, we train a sparse model by GL penalty, and impose an angle dissimilarity (AD) constraint on the channels and filters of convolutional network to obtain a more sparse structure. Eventually, the effectiveness of our method is demonstrated in the section of experiment. On CIFAR-10, we reduce 66.86% FLOPs on VGG-16 with 93.31% accuracy after pruning, where FLOPs represents the number of floating-point operations per second of the model. Moreover, on ResNet-32, we reduce FLOPs by 58.46%, which makes the accuracy after pruning reach 91.76%.

关键词： Convolution Encoding Convolutional neural networks Kernel Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learning

arXiv

引用

arXiv 2025年

作者： Liu, Bangzhen Zheng, Chenxi Xu, Xuemiao Xu, Cheng Zhang, Huaidong He, Shengfeng South China University of Technology Guangzhou China Guangdong Engineering Center for Large Model and GenAI Technology The State Key Laboratory of Subtropical Building and Urban Science The Ministry of Education Key Laboratory of Big Data and Intelligent Robot The Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information China Singapore Management University Singapore

The vulnerability of 3D point cloud analysis to unpredictable rotations poses an open yet challenging problem: orientation-aware 3D domain generalization. Cross-domain robustness and adaptability of 3D representations are crucial but not easily achieved through rotation augmentation. Motivated by the inherent advantages of intricate orientations in enhancing generalizability, we propose an innovative rotation-adaptive domain generalization framework for 3D point cloud analysis. Our approach aims to alleviate orientational shifts by leveraging intricate samples in an iterative learning process. Specifically, we identify the most challenging rotation for each point cloud and construct an intricate orientation set by optimizing intricate orientations. Subsequently, we employ an orientation-aware contrastive learning framework that incorporates an orientation consistency loss and a margin separation loss, enabling effective learning of categorically discriminative and generalizable features with rotation consistency. Extensive experiments and ablations conducted on 3D cross-domain benchmarks firmly establish the state-of-the-art performance of our proposed approach in the context of orientation-aware 3D domain generalization. © 2025, CC BY-NC-SA.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Neighbor Importance-Aware Graph Collaborative Filtering for Item Recommendation

SSRN

引用

SSRN 2022年

作者： Wang, Qingxian Liu, Xinyu Bai, Yanan Chen, Bo Shi, Xiaoyu Chengdu610054 China Chongqing University of Technology Chongqing401135 China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China Intelligent Terminal Key Laboratory of SiChuan Province Yibin644000 China

The emerging topic of Graph Neural Network (GNN) has attracted increasing attention and achieved state-of-the-art (SOTA) performance in many recommendation problems, due to its strong ability in node representation with exploring high-order information. To learn a node’s representation, most previous methods usually linearly combine the embeddings of node features, amusing the equal importance of neighbors. However, due to the intrinsic differences (i.e., degree, create time) over neighbors, we argue that these differences carry important signals for node representation. Ignoring them will lead to a sub-optimal in node representation and thus weaken the effectiveness of the follow-up graphbased operations. To address it, we propose big-SAGE@ for item recommendation with rating prediction task, which is a neighbor importance-aware graph neural network. Specifically, its main idea is two-fold: 1) A rating-confidencebased neighborhood sampling method is introduced, making the sampling process biased to those more valuable nodes. 2) An attention network is integrated to achieve the rating prediction task, by flexibly incorporating information from user and item embedding features. Finally, we verified the effectiveness of the proposed model on six public data sets. Extensive experimental results demonstrate the superior performance of big-SAGE@ in the rating prediction task, compared to the SOTA methods. © 2022, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A pruning method based on the dissimilarity of angle among channels and filters

arXiv

引用

arXiv 2022年

作者： Yao, Jiayi Li, Ping Kang, Xiatao Wang, Yuzhe Changsha University of Science and Technology China Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transp China

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Asymmetrical Interactions Driven by Strategic Persistence Effectively Alleviates Social Dilemmas in Spatial Games

SSRN

引用

SSRN 2024年

作者： Li, Xiaopeng Wang, Zhonglin Xu, Yan Zhang, Hui Yu, Guihai College of Big Data Statistics Guizhou University of Finance and Economics Guizhou Guiyang550025 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin300384 China School of Information Guizhou University of Finance and Economics Guizhou Guiyang550025 China Guangxi Key Laboratory of Big Data in Finance and Economics Guangxi University of Finance and Ecomonics Nanning530003 China

Asymmetry is a common phenomenon in real life due to constraints such as status, age, information, reputation, and so on. Yet it is still unclear how asymmetric interactions driven by adaptive feedback affect the evolution of cooperation. To this end, we creatively propose a novel asymmetric interaction model driven by strategy persistence to unravel this mystery. In particular, players whose strategy persistence is beyond the threshold β are the pearls for being able to interact with all of the neighbors. Otherwise, they can only interact with half of their neighbors as the layfolks. As the strategy persistence is always updated, leading to the fact that the pearls and the layfolks maybe switch at any time, which adds uncertainty to the evolution of cooperation. Simulation results show that the asymmetric interaction of adaptive feedback effectively alleviates social dilemmas, thus opening up a path for cooperators to survive. Moreover, with the increase of β, there is an appropriate interval resulting in the optimal evolution of cooperation. Micro analysis further indicates that the pearl cooperators play an irreplaceable pivotal role in promoting the evolution of cooperation. At last, we verify and extend the applicability and robustness of the designed model through other social dilemmas, network topologies, and strategy update patterns © 2024, The Authors. All rights reserved.

关键词： Feedback

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：