检索结果-内蒙古大学图书馆

Web3D Learning Framework for 3D Shape Retrieval Based on Hybrid Convolutional Neural Networks

学校读者我要写书评

暂无评论

Tsinghua science and Technology 2020年第1期25卷 93-102页

作者： Wen Zhou Jinyuan Jia Chengxi Huang Yongqing Cheng School of Computer and Information Anhui Normal UniversityWuhu 241002China School of Software Engineering Tongji UniversityShanghai 201804China College of Electronics and Information Engineering Tongji UniversityShanghai 201804China School of Engineering and Computer Science University of HullHullHU6 7RXUK.

With the rapid development of Web3 D technologies, sketch-based model retrieval has become an increasingly important challenge, while the application of Virtual Reality and 3 D technologies has made shape retrieval of furniture over a web browser feasible. In this paper, we propose a learning framework for shape retrieval based on two Siamese VGG-16 Convolutional Neural Networks(CNNs), and a CNN-based hybrid learning algorithm to select the best view for a shape. In this algorithm, the AlexNet and VGG-16 CNN architectures are used to perform classification tasks and to extract features, respectively. In addition, a feature fusion method is used to measure the similarity relation of the output features from the two Siamese networks. The proposed framework can provide new alternatives for furniture retrieval in the Web3 D environment. The primary innovation is in the employment of deep learning methods to solve the challenge of obtaining the best view of 3 D furniture,and to address cross-domain feature learning problems. We conduct an experiment to verify the feasibility of the framework and the results show our approach to be superior in comparison to many mainstream state-of-the-art approaches.

关键词： Web3D sketch-based model retrieval Convolutional Neural Networks(CNNs) best view cross-domain

Chebyshev Polynomial Broad Learning System

学校读者我要写书评

暂无评论

Chebyshev Polynomial Broad Learning System

2021 International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2021

作者： Feng, Shuang Wang, Bingshu Philip Chen, C.L. Beijing Normal University School of Applied Mathematics Zhuhai China Northwestern Polytechnical University School of Software Suzhou China South China University of Technology School of Computer Science and Engineering Guangzhou China

ISBN: (纸本)9781665402453

The broad learning system (BLS) has been attracting more and more attention due to its excellent property in the field of machine learning. A great deal of variants and hybrid structures of BLS have also been designed and developed for better performance in some specialized tasks. In this paper, the Chebyshev polynomials are introduced into the BLS to take advantage of their powerful approximation capability, where the feature windows are replaced by a set of Chebyshev polynomials. This new variant, named Chebyshev polynomial BLS (CPBLS), has a light structure with a reduction in computational complexity since the sparse autoencoder is removed. Instead, the dimension of each input sample is expended by n + 1 Chebyshev polynomials, mapping the original feature into a new feature space with higher dimension, which helps to classify the patterns in training. The proposed CPBLS is evaluated by some popular datasets from UCI and KEEL repositories, and it outperforms some representative neural networks and neuro-fuzzy models in terms of classification accuracy. The CPBLS also show some advantages over the recent developed compact fuzzy BLS (CFBLS) which indicates its great potential in future research and real-world applications. © 2021 IEEE.

关键词： Classification (of information)

SceneGATE: Scene-Graph Based Co-Attention Networks for Text Visual Question Answering

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cao, Feiqi Luo, Siwen Nunez, Felipe Wen, Zean Poon, Josiah Han, Soyeon Caren School of Computer Science Faculty of Engineering University of Sydney CamperdownNSW2006 Australia Department of Computer Science and Software Engineering School of Physics Maths and Computing University of Western Australia CrawleyWA6009 Australia

Visual Question Answering (VQA) models fail catastrophically on questions related to the reading of text-carrying images. However, TextVQA aims to answer questions by understanding the scene texts in an image-question context, such as the brand name of a product or the time on a clock from an image. Most TextVQA approaches focus on objects and scene text detection, which are then integrated with the words in a question by a simple transformer encoder. The focus of these approaches is to use shared weights during the training of a multi-modal dataset, but it fails to capture the semantic relations between an image and a question. In this paper, we proposed a Scene Graph-Based Co-Attention Network (SceneGATE) for TextVQA, which reveals the semantic relations among the objects, the Optical Character Recognition (OCR) tokens and the question words. It is achieved by a TextVQA-based scene graph that discovers the underlying semantics of an image. We create a guided-attention module to capture the intra-modal interplay between the language and the vision as a guidance for inter-modal interactions. To permit explicit teaching of the relations between the two modalities, we propose and integrate two attention modules, namely a scene graph-based semantic relation-aware attention and a positional relation-aware attention. We conduct extensive experiments on two widely used benchmark datasets, Text-VQA and ST-VQA. It is shown that our SceneGATE method outperforms existing ones because of the scene graph and its attention modules. Copyright © 2022, The Authors. All rights reserved.

关键词： Neural networks

Graph Contrastive Learning with Cohesive Subgraph Awareness

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Yucheng Han, Xiao Wang, Leye Ye, Han-Jia Key Lab of High Confidence Software Technologies Peking University Ministry of Education School of Computer Science Peking University Beijing China School of Information Management and Engineering Shanghai University of Finance and Economics Shanghai China National Key Laboratory for Novel Software Technology Nanjing University School of Artificial Intelligence Nanjing University Nanjing China

Graph contrastive learning (GCL) has emerged as a state-of-the-art strategy for learning representations of diverse graphs including social and biomedical networks. GCL widely uses stochastic graph topology augmentation, such as uniform node dropping, to generate augmented graphs. However, such stochastic augmentations may severely damage the intrinsic properties of a graph and deteriorate the following representation learning process. We argue that incorporating an awareness of cohesive subgraphs during the graph augmentation and learning processes has the potential to enhance GCL performance. To this end, we propose a novel unified framework called CTAug, to seamlessly integrate cohesion awareness into various existing GCL mechanisms. In particular, CTAug comprises two specialized modules: topology augmentation enhancement and graph learning enhancement. The former module generates augmented graphs that carefully preserve cohesion properties, while the latter module bolsters the graph encoder’s ability to discern subgraph patterns. Theoretical analysis shows that CTAug can strictly improve existing GCL mechanisms. Empirical experiments verify that CTAug can achieve state-of-the-art performance for graph representation learning, especially for graphs with high degrees. The code is available at https://***/10.5281/zenodo.10594093, or https://***/wuyucheng2002/CTAug. Copyright © 2024, The Authors. All rights reserved.

关键词： Topology

Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Duan, Yue Zhao, Zhen Qi, Lei Zhou, Luping Wang, Lei Shi, Yinghuan National Key Laboratory for Novel Software Technology Nanjing University China School of Electrical and Information Engineering The University of Sydney Sydney Australia School of Computer Science and Engineering Southeast University China School of Computing and Information Technology University of Wollongong Australia

While semi-supervised learning (SSL) has yielded promising results, the more realistic SSL scenario remains to be explored, in which the unlabeled data exhibits extremely high recognition difficulty, e.g., fine-grained visual classification in the context of SSL (SS-FGVC). The increased recognition difficulty on fine-grained unlabeled data spells disaster for pseudo-labeling accuracy, resulting in poor performance of the SSL model. To tackle this challenge, we propose Soft Label Selection with Confidence-Aware Clustering based on Class Transition Tracking (SoC) by reconstructing the pseudo-label selection process by jointly optimizing Expansion Objective and Shrinkage Objective, which is based on a soft label manner. Respectively, the former objective encourages soft labels to absorb more candidate classes to ensure the attendance of ground-truth class, while the latter encourages soft labels to reject more noisy classes, which is theoretically proved to be equivalent to entropy minimization. In comparisons with various state-of-the-art methods, our approach demonstrates its superior performance in SS-FGVC. Checkpoints and source code are available at https://***/NJUyued/SoC4SS-FGVC. Copyright © 2023, The Authors. All rights reserved.

关键词： Shrinkage

Multi-task MIML learning for pre-course student performance prediction

学校读者我要写书评

暂无评论

Frontiers of computer science 2020年第5期14卷 113-121页

作者： Yuling Ma Chaoran Cui Jun Yu Jie Guo Gongping Yang Yilong Yin School of Software Shandong UniversityJinan250100China School of Information Engineering Shandong Yingcai CollegeJinan250104China School of Computer Science and Technology Shandong University of Finance and EconomicsJinan250014China

In higher education,the initial studying period of each course plays a crucial role for students,and seriously influences the subsequent learning ***,given the large size of a course’s students at universities,it has become impossible for teachers to keep track of the performance of individual *** this circumstance,an academic early warning system is desirable,which automatically detects students with difficulties in learning(i.e.,at-risk students)prior to a course ***,previous studies are not well suited to this purpose for two reasons:1)they have mainly concentrated on e-learning platforms,e.g.,massive open online courses(MOOCs),and relied on the data about students’online activities,which is hardly accessed in traditional teaching scenarios;and 2)they have only made performance prediction when a course is in progress or even close to the *** this paper,for traditional classroom-teaching scenarios,we investigate the task of pre-course student performance prediction,which refers to detecting at-risk students for each course before its *** better represent a student sample and utilize the correlations among courses,we cast the problem as a multi-instance multi-label(MIML)***,given the problem of data scarcity,we propose a novel multi-task learning method,i.e.,MIML-Circle,to predict the performance of students from different specialties in a unified *** experiments are conducted on five real-world datasets,and the results demonstrate the superiority of our approach over the state-of-the-art methods.

关键词： educational data mining academic early warning system student performance prediction multi-instance multi-label learning multi-task learning

A Heuristic-based Dynamic Scheduling and Routing Method for Industrial TSN Networks

学校读者我要写书评

暂无评论

A Heuristic-based Dynamic Scheduling and Routing Method for ...

IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)

作者： Honglong Chen Mindong Liu Jing Huang Zhiling Zheng Weihong Huang Yufeng Xiao School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan China Information Center Hunan Industry Polytechnic Changsha China

In the industrial environment, machines often need to reflect the anomaly detection results to the total control center in time, and the general industrial network can not achieve high real-time. In order to solve such challenges, a set of protocol standards developed by IEEE802.1 working group, namely Time-sensitive Networking (TSN), has been introduced into industrial networks. TSN can provide high real-time and reliability for data transmission, where the reliability is achieved by Frame duplication and Frame Elimination (FRER). In the realization process of FRER, it is necessary to determine the source node, destination node, and multiple disjoint paths to transmit redundant data. However, the transmission of these redundant traffic may result in the delay of other flows, and then affects the user experience. Therefore, it is very important to choose excellent redundant traffic paths to ensure reliability and reduce the impact on other flows. In the existing research, there are many dynamic scheduling and routing heuristics to determine the path, but they do not consider the influence of the location of the source node on the whole route scheduling. This paper proposes an improved dynamic scheduling and routing heuristic method, which takes the source node into account in the routing selection. In the flow test experiments of different magnitudes, it is found that the total delay of all flows is reduced by 1.4%-4.5% under the same magnitude of schedulability compared with Ant Colony Optimization.

关键词：

SG-GS: Topology-aware Human Avatars with Semantically-guided Gaussian Splatting

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhao, Haoyu Yang, Chen Wang, Hao Zhao, Xingyue Shen, Wei MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China School of Computer Science Wuhan University China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology China School of Software Engineering Xi’an Jiao Tong University China

Reconstructing photo-realistic and topology-aware animatable human avatars from monocular videos remains challenging in computer vision and graphics. Recently, methods using 3D Gaussians to represent the human body have emerged, offering faster optimization and real-time rendering. However, due to ignoring the crucial role of human body semantic information which represents the explicit topological and intrinsic structure within human body, they fail to achieve fine-detail reconstruction of human avatars. To address this issue, we propose SG-GS, which uses semantics-embedded 3D Gaussians, skeleton-driven rigid deformation, and non-rigid cloth dynamics deformation to create photo-realistic human avatars. We then design a Semantic Human-Body Annotator (SHA) which utilizes SMPL’s semantic prior for efficient body part semantic labeling. The generated labels are used to guide the optimization of semantic attributes of Gaussian. To capture the explicit topological structure of the human body, we employ a 3D network that integrates both topological and geometric associations for human avatar deformation. We further implement three key strategies to enhance the semantic accuracy of 3D Gaussians and rendering quality: semantic projection with 2D regularization, semantic-guided density regularization and semantic-aware regularization with neighborhood consistency. Extensive experiments demonstrate that SG-GS achieves state-of-the-art geometry and appearance reconstruction performance. Our project is at https://***/. Copyright © 2024, The Authors. All rights reserved.

关键词： Topology

An efficient face recognition attack method based on generative adversarial networks and cosine metrics 5

学校读者我要写书评

暂无评论

An efficient face recognition attack method based on generat...

5th Asian Conference on Artificial Intelligence Technology, ACAIT 2021

作者： Ding, Hu He, Shumeng Wu, Yanwen Jin, Yongli Gan, Lin Xu, Gaodi Yang, Houqun Hainan University School of Computer Science and Technology Hainan Haikou China Chongqing University School of Big Data and Software Engineering Chongqing China Anhui University School of Computer Science and Technology Anhui Hefei China Purdue University Elmore Family School of Computer and Electrical Engineering West Lafayette United States Hainan Association for Artificial Intelligence Hainan Haikou China

ISBN: (纸本)9781665426305

Deep neural networks are vulnerable to attacks on adversarial samples. These attacks are caused by adding small magnitude perturbations to the input samples, which may lead to misclassification of the deep neural network. Based on the study of the adversarial sample attack network model, we propose an attack sample based on the generative adversarial network HNUGAN, incorporating the cosine metric of disparity recognition, for the features of the face dataset, to construct an attack sample to attack the face recognition system. Using these adversarial samples can reduce the recognition accuracy of models such as GoogleNet and ResNet to a very low level, and thus complete the attack on the target model. Interestingly, we can obtain a batch of adversarial samples through adversarial training to expand the dataset and retrain the target model to improve its robustness and resistance to attacks. © 2021 IEEE.

关键词： Face recognition