检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第7期5卷 3393-3407页

作者： Gu, Jing Sun, Xinkai Feng, Jie Yang, Shuyuan Liu, Fang Jiao, Licheng Xidian University Key Lab of Intelligent Perception and Image Understanding of Ministry of Education Xi'an710071 China

Real-time image semantic segmentation (ISS) draws the attentions of more and more researchers as a basis of scene understanding, and it has been applied in many fields that need fast interaction and response, such as autonomous driving and robot control. Considering the loss of low-level spatial information with the deepening network layer, we propose a multiple resolutions detail enhancement network (MRDENet) in this article, which adequately extracts and utilizes accurate low-level detail information from original images with different resolutions. MRDENet consists of three light-weight branch subnetworks, and designs dense oblique connections between adjacent branches to preserve the different level effective features of previous branch. Furthermore, a new multilevel information aggregation (MIA) module is presented to effectively fuse the low-level detail features and the high-level semantic features of different branches by employing group convolution (group conv) and channel shuffle with low computation cost, thus ensuring that MRDENet could achieve a favorable tradeoff between segmentation precision with inference speed. The experimental results show that MRDENet achieves 73.1% mean intersection over union (mIoU) with 93 frames per second (FPS) on Cityscapes dataset, and 68.5% mIoU with 112 FPS on CamVid dataset, which indicates the performance of MRDENet is competitive with the state-of-art methods. © 2020 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Graph Representation Learning Meets Computer Vision: A Survey

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第1期4卷 2-22页

作者： Jiao, Licheng Chen, Jie Liu, Fang Yang, Shuyuan You, Chao Liu, Xu Li, Lingling Hou, Biao Key Lab. of Intelligent Perception and Image Understanding of the Ministry of Education of China International Research Center of Intelligent Perception and Computation School of Artificial Intelligence Xidian University Xi'an710071 China

A graph structure is a powerful mathematical abstraction, which can not only represent information about individuals but also capture the interactions between individuals for reasoning. Geometric modeling and relational inference based on graph data is a long-standing topic of interest in the computer vision community. In this article, we provide a systematic review of graph representation learning and its applications in computer vision. First, we sort out the evolution of representation learning on graphs, categorizing them into the nonneural network and neural network methods based on the way the nodes are encoded. Specifically, nonneural network methods, such as graph embedding and probabilistic graphical models, are introduced, and neural network methods, such as graph recurrent neural networks, graph convolutional networks, and variants of graph neural networks, are also presented. Then, we organize the applications of graph representation algorithms in various vision tasks (such as image classification, semantic segmentation, object detection, and tracking) for review and reference, and the typical graph construction approaches in computer vision are also summarized. Finally, on the background of biology and brain inspiration, we discuss the existing challenges and future directions of graph representation learning and computer vision. © 2022 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Cascaded Sliding-Window-Based Relativistic GAN Fusion for Perceptual and Consistent Video Super-Resolution 6th

Cascaded Sliding-Window-Based Relativistic GAN Fusion for P...

引用

6th IFIP TC 12 International Conference on Intelligence Science, ICIS 2024

作者： Li, Dingyi PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

ISBN: (纸本)9783031712524

Perceptual video super-resolution aims at converting low-resolution videos to visually appealing high-resolution ones. It may lead to temporal inconsistency due to the drastically changing outputs. In this paper, we propose cascaded sliding-window-based relativistic GAN (Generative Adversarial Network) fusion for perceptual and consistent video super-resolution (PC-VSR). Firstly, cascaded sliding-window-based relativistic GAN is designed to extract more useful information. It enlarges the temporal receptive field of sliding-window-based model in each step. It is able to enhance perceptual quality and compensate temporal consistency progressively and sufficiently. The trained separate refinement generator networks are fused into a final refinement generator. The final refinement generator can be calculated recursively at the testing stage. With our generator fusion, the parameter number is reduced and good quality is maintained. Extensive experimental results demonstrate that our approach outperforms state-of-the-art super-resolution methods in terms of perceptual quality. Our method also achieves good temporal consistency and per-pixel accuracy, compared with other perceptual approaches. © IFIP International Federation for Information Processing 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Global Spatio-Temporal Fusion-based Traffic Prediction Algorithm with Anomaly Aware

Global Spatio-Temporal Fusion-based Traffic Prediction Algor...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Liu, Chaoqun Li, Xuanpeng Gong, Chen Li, Guangyu Nanjing University of Science and Technology Pca Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security China Southeast University Nanjing210094 China

ISBN: (纸本)9798350351255

Traffic prediction is an indispensable component of urban planning and traffic management. Achieving accurate traffic prediction hinges on the ability to capture the potential spatio-temporal relationships among road sensors. However, the majority of existing works focus on local short-term spatiotemporal correlations, failing to fully consider the interactions of different sensors in the long-term state. In addition, these works do not analyze the influences of anomalous factors, or have insufficient ability to extract personalized features of anomalous factors, which make them ineffectively capture their spatiotemporal influences on traffic prediction. To address the aforementioned issues, We propose a global spatio-temporal fusionbased traffic prediction algorithm that incorporates anomaly awareness. Initially, based on the designed anomaly detection network, we construct an efficient anomalous factors impacting module (AFIM), to evaluate the spatio-temporal impact of unexpected external events on traffic prediction. Furthermore, we propose a multi-scale spatio-temporal feature fusion module (MTSFFL) based on the transformer architecture, to obtain all possible both long and short term correlations among different sensors in a wide-area traffic environment for accurate prediction of traffic flow. Finally, experiments are implemented based on real-scenario public transportation datasets (PEMS04 and PEMS08) to demonstrate that our approach can achieve stateof-the-art performance. © 2024 IEEE.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Robust and Faster Zeroth-Order Minimax Optimization: Complexity and Applications 38

Robust and Faster Zeroth-Order Minimax Optimization: Complex...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： An, Weixin Liu, Yuanyuan Shang, Fanhua Liu, Hongying Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University China College of Intelligence and Computing Tianjin University China Medical School Tianjin University China Peng Cheng Lab Shenzhen China

Many zeroth-order (ZO) optimization algorithms have been developed to solve nonconvex minimax problems in machine learning and computer vision areas. However, existing ZO minimax algorithms have high complexity and rely on some strict restrictive conditions for ZO estimations. To address these issues, we design a new unified ZO gradient descent extragradient ascent (ZO-GDEGA) algorithm, which reduces the overall complexity to O(dϵ-6) to find an ϵ-stationary point of the function ψ for nonconvex-concave (NC-C) problems, where d is the variable dimension. To the best of our knowledge, ZO-GDEGA is the first ZO algorithm with complexity guarantees to solve stochastic NC-C problems. Moreover, ZO-GDEGA requires weaker conditions on the ZO estimations and achieves more robust theoretical results. As a by-product, ZO-GDEGA has advantages on the condition number for the NC-strongly concave case. Experimentally, ZO-GDEGA can generate more effective poisoning attack data with an average accuracy reduction of 5%. The improved AUC performance also verifies the robustness of gradient estimations. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multitasking Evolutionary Algorithm Based on Adaptive Seed Transfer for Combinatorial Problem

arXiv

引用

arXiv 2023年

作者： Lv, Haoyuan Liu, Ruochen Key Lab of Intelligent Perception and Image Understanding Ministry of Education International Center of Intelligent Perception and Computation Xidian University Xi’an710071 China

Evolutionary computing (EC) is widely used in dealing with combinatorial optimization problems (COP). Traditional EC methods can only solve a single task in a single run, while real-life scenarios often need to solve multiple COPs simultaneously. In recent years, evolutionary multitasking optimization (EMTO) has become an emerging topic in the EC community. And many methods have been designed to deal with multiple COPs concurrently through exchanging knowledge. However, many-task optimization, cross-domain knowledge transfer, and negative transfer are still significant challenges in this field. A new evolutionary multitasking algorithm based on adaptive seed transfer (MTEA-AST) is developed for multitasking COPs in this work. First, a dimension unification strategy is proposed to unify the dimensions of different tasks. And then, an adaptive task selection strategy is designed to capture the similarity between the target task and other online optimization tasks. The calculated similarity is exploited to select suitable source tasks for the target one and determine the transfer strength. Next, a task transfer strategy is established to select seeds from source tasks and correct unsuitable knowledge in seeds to suppress negative transfer. Finally, the experimental results indicate that MTEA-AST can adaptively transfer knowledge in both same-domain and cross-domain many-task environments. And the proposed method shows competitive performance compared to other state-of-the-art EMTOs in experiments consisting of four COPs. Copyright © 2023, The Authors. All rights reserved.

关键词： Multitasking

来源：评论

学校读者我要写书评

暂无评论

A novel clinical artificial intelligence model for disease detection via retinal imaging

引用

The Innovation 2024年第2期5卷 11-12页

作者： Yidian Fu Liang Ma Sheng Wan Shengfang Ge Zhi Yang Department of Ophthalmology Ninth People’s HospitalShanghai JiaoTong University School of MedicineShanghai 200011China Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology Shanghai 200011China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of EducationNanjing 210000China Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and EngineeringNanjing University of Science and TechnologyNanjing 210000China

Artificial intelligence(AI)is an emerging field in which computerized systems are used to carry out complex tasks in place of *** AI algorithms have been developed for disease diagnosis and prediction and treatment recommendation across various clinical data types,e.g.,chest X-rays,electrocardiograms,and other radiological images.1 In ophthalmology,particularly,great progress has been made in AI systems over the past *** fundus photography(CFP)and optical coherence tomography(OCT),which are readily available in routine clinical practice,are both mainstream and useful retinal imaging modalities in *** September 2023,the 2023 Lasker-Debakey Clinical Medical Research Award was awarded to three scientists for their work on OCT for accurate retinal disease detection.

关键词： clinical routine diagnosis

来源：评论

学校读者我要写书评

暂无评论

A Special Point and Transfer Component Analysis Based Dynamic Multi-objective Optimization Algorithm 11th

A Special Point and Transfer Component Analysis Based Dynami...

引用

11th International Conference on Evolutionary Multi-Criterion Optimization, EMO 2021

作者： Liu, Ruochen Li, Nanxi Peng, Luyao Wu, Kai Key Lab of Intelligent Perception and Image Understanding of Ministry of Education International Center of Intelligent Perception and Computation Xidian University Xi’an710071 China

ISBN: (纸本)9783030720612

To solve a dynamic multi-objective optimization problem better, algorithms need to quickly adapt to environmental changes and track its changing Pareto fronts fast. In this paper, an algorithm (SPTr-RMMEDA) based on special point and transfer component analysis is presented, in which, by using some special points and their neighborhoods solutions, the prediction strategy are used to generated the transfer learning prediction model, together with part new initial solutions to generate next population when change occurs. In order to better adapt to environmental changes, in addition to reusing some important historical information by transfer component analysis, the algorithm also introduces the adaptive diversity introduction strategy. The algorithm performs on 12 groups test problems. And the experimental results show that the proposed algorithm is superior to other four algorithms, such as Tr-NSGA-II, Tr-RMMEDA, DNSGA-II-A and DNSGA-II-B on most test problems in term of convergence and computation complexity. © 2021, Springer Nature Switzerland AG.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Clothed Human Model Estimation from Unseen Partial Point Clouds with Meta-learning 1st

Clothed Human Model Estimation from Unseen Partial Point Cl...

引用

1st International Artificial Intelligence Conference, IAIC 2023

作者： Fang, Chenghao Wang, Kangkan Yin, Shihao Li, Shaoyuan Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing China Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9789819712793

This work aims to address the problems of clothed human reconstruction from unseen partial point clouds. Existing methods focus on estimating vertex offsets on top of parametric models for clothing details but with the limitation of the fixed topology, or reconstructing non-parametric shapes using implicit functions which are lack of semantic information. Moreover, due to limited training data, large variations in clothing details, and domain gaps between training data and real data, these methods often have poor generalization ability on real data. In this paper, we propose a generalizable approach for estimating dressed human models from single-frame partial point clouds based on meta-learning. Specifically, we first learn a meta-model that can efficiently estimate the parameters of unclothed human models from unseen data by a fast fine-tuning. Based on the unclothed human models, we further meta-learn the point-based human models in clothing with local geometric features, which is topologically flexible and rich in human details. Our approach outperforms previous work in terms of reconstruction accuracy, as evidenced by qualitative and quantitative results obtained from a variety of datasets. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Clothed Human Performance Capture with a Double-layer Neural Radiance Fields

Clothed Human Performance Capture with a Double-layer Neural...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023

作者： Wang, Kangkan Zhang, Guofeng Cong, Suxu Yang, Jian Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China State Key Laboratory of CAD&CG Zhejiang University China

This paper addresses the challenge of capturing performance for the clothed humans from sparse-view or monocular videos. Previous methods capture the performance of full humans with a personalized template or recover the garments from a single frame with static human poses. However, it is inconvenient to extract cloth semantics and capture clothing motion with one-piece template, while single frame-based methods may suffer from instable tracking across videos. To address these problems, we propose a novel method for human performance capture by tracking clothing and human body motion separately with a double-layer neural radiance fields (NeRFs). Specifically, we propose a double-layer NeRFs for the body and garments, and track the densely deforming template of the clothing and body by jointly optimizing the deformation fields and the canonical double-layer NeRFs. In the optimization, we introduce a physics-aware cloth simulation network which can help generate physically plausible cloth dynamics and body-cloth interactions. Compared with existing methods, our method is fully differentiable and can capture both the body and clothing motion robustly from dynamic videos. Also, our method represents the clothing with an independent NeRFs, allowing us to model implicit fields of general clothes feasibly. The experimental evaluations validate its effectiveness on real multi-view or monocular videos. ©2023 IEEE.

关键词： Multilayer neural networks

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：