检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Kong, Lin Sun, Wei Shang, Fanhua Liu, Yuanyuan Liu, Hongying Key Lab. of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University China Peng Cheng Laboratory Shenzhen China

Recently, the study on learned iterative shrinkage thresholding algorithm (LISTA) has attracted increasing attentions. A large number of experiments as well as some theories have proved the high efficiency of LISTA for solving sparse coding problems. However, existing LISTA methods are all serial connection. To address this issue, we propose a novel extragradient based LISTA (ELISTA), which has a residual structure and theoretical guarantees. In particular, our algorithm can also provide the interpretability for Res-Net to a certain extent. From a theoretical perspective, we prove that our method attains linear convergence. In practice, extensive empirical results verify the advantages of our method. © 2021, CC BY.

关键词： Iterative methods

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

Data gathering of WSNs based on sequential compressed sensing and sparse sensing

引用

International Review on Computers and Software 2012年第1期7卷 397-402页

作者： Song, Xiaoxia Shi, Guangming Key Lab of Intelligent Perception and Image Understanding Ministry of Education Xidian University Xi'an 710071 Shaanxi China School of Physical and Electronics Shanxi Datong University Datong 037009 Shanxi China

In order to solve the problem of sensor nodes with limited energy supply in wireless sensor networks (WSNs), this paper proposes a method to collect the data of sensor nodes based on sequential compressed sensing (SCS) and sparse sensing. In the proposed method, the measurement matrix is generated according to sparse random projection which may save communication costs, and the data of sensor nodes are collected in the way of SCS which can reduce communication data. The proposed method can save the energy consumption of sensor nodes and achieve more reliable reconstruction results by adding the computations at the sink node. Experimental results also show that the proposed method can reduce the energy consumption of sensor nodes and achieve more reliable reconstruction results without almost reducing reconstruction quality of the signal, compared with other CS methods. © 2012 Praise Worthy Prize S.r.l. - All right reserved.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

An efficient solution to the relative pose estimation with a common direction

An efficient solution to the relative pose estimation with a...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Yaqing Ding Jian Yang Hui Kong 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 Nanjing University of Science and Technology

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

In this paper, we propose an efficient solution to the calibrated camera motion estimation with a common direction. This case is relevant to smart phones, tablets, and other camera-IMU (Inertial measurement unit) systems, which have accelerometers to measure the gravity direction. We can align one of the axes of the camera with this common direction so that the relative rotation between the views reduces to only 1DOF (degree of freedom). This allows us to use only three point correspondences for relative pose estimation. Unlike previous work, we derive new constraints on the simplified essential matrix using an elimination strategy based on Gröbner basis. In this case, computing the coefficients of these constraints require less computation and we only need to solve a polynomial eigenvalue problem. We show detailed analyses and comparisons against the existing 3-point algorithms, with satisfactory results obtained.

关键词： Cameras Eigenvalues and eigenfunctions Gravity Pose estimation Transmission line matrix methods Symmetric matrices Motion estimation

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

Study of high-resolution range profile for monostatic MIMO radar based on SIAR

引用

Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics 2010年第4期32卷 734-739+763页

作者： Zhao, Guang-Hui Chen, Bai-Xiao Gao, Zhao-Zhao Intelligent Perception and Image Understanding Key Lab of Ministry of Education of China Xidian Univ. Xi'an 710071 China National Key Lab for Radar Signal Processing Xidian Univ. Xi'an 710071 China National Information Control Laboratory Chengdu 610036 China

Conventional pulse compression use a periodical echo of single receive antenna, which is modulated by a certain carrier-frequency, in other words, single spectrum is exploited. But for MIMO radar, as the multi-carrier-frequency signals are transmitted simultaneously, if the spectrum of the target echo after channel separation can be combined to form the whole band spectrum echo, the corresponding range resolution can improve several times as compared with the conventional method, and it will be more convenient for follow-up detection and tracking. Considering the difference between the frequency modulation band and the interval between the adjacent frequencies, the spectrum joint after channel separation will be overlapped or spaced. The methods of spectrum moving of each echo and the spectrum extrapolation with Root-MUSIC algorithm are proposed, by which high-resolution range profile of the target is obtained. Simulation results verify the validity of these methods.

关键词： Multiple signal classification

来源：评论

学校读者我要写书评

暂无评论

Inference guided feature generation for generalized zero-shot learning

引用

Neurocomputing 2021年 430卷 150-158页

作者： Zongyan Han Zhenyong Fu Guangyu Li Jian Yang 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 Jiangsu 210094 China

Generalized zero-shot learning suffers from an extreme data imbalance problem, that is, the training data only come from seen classes while no unseen class data are available. Recently, a number of feature generation methods based on generative adversarial networks (GAN) have been proposed to address this problem. Existing feature generation methods, however, have never considered the under-constrained problem, and thus could generate an unrestricted visual feature corresponding to no meaningful object class. In this paper, we propose to equip the feature generation framework with a parallel inference network that projects visual feature to the semantic descriptor space, constraining to avoid the generation of unrestricted visual features. The two-parallel-stream framework (1) enables our method, termed inference guided feature generation (Inf-FG), to mitigate the under-constrained problem and (2) makes our Inf-FG applicable to transductive ZSL. Our Inf-FG learns the feature generator and the inference network simultaneously by aligning the joint distribution of visual features and semantic descriptors from the feature generator and the joint distribution from the inference network. We evaluate our approach on four benchmark ZSL datasets, including AWA, CUB, SUN, and FLO, on which our method improves our baselines on generalized zero-shot learning.

关键词： Feature generation Generalized zero-shot learning image classification Transfer learning

来源：评论

学校读者我要写书评

暂无评论

A novel feature combination methods for saliency-based visual attention

A novel feature combination methods for saliency-based visua...

引用

5th International Conference on Natural Computation, ICNC 2009

作者： Han, Bing Tcheang, Lili Walsh, Vincent Gao, Xinbo VIPS Lab. School of Electronic Engineering Xidian Univ. Xi'an 710071 China Key Laboratory of Intelligent Perception Image Understanding of Ministry of Education of China Xidian University Xi'an 710071 China Institute of Cognitive Neuroscience University College London London WC1N 3AR United Kingdom

ISBN: (纸本)9780769537368

In the field of visual attention, bottom-up or saliency-based visual attention allows primates to detect non-specific conspicuous objects or targets in cluttered scenes. Simple multi-scale "feature maps" detect local spatial discontinuities in intensity, color, orientation, and are combined into a "saliency" map. In this paper, we propose a Saliency Map based on feature weighted, in which the Rough Sets is used to assign the weighting for every feature. This method measures the contribution of each conspicuity map obtained from the feature maps to saliency map. And it also carries out a dynamic weighting of individual conspicuity maps. We obtain results, which enrich the theory of Saliency detection. We use the real data of natural scenes to demonstrate the effectiveness of the algorithm. © 2009 IEEE.

关键词： Mammals

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

Design of M-channel uniform linear-phase filter banks with near-perfect-reconstruction property

Design of M-channel uniform linear-phase filter banks with n...

引用

International Conference on Audio, Language and image Processing, ICALIP

作者： Wei Zhong Xuemei Xie Guangming Shi Bin Peng Qin Zhang Key Lab of Media Audio & Video of Ministry of Education Commuication University of China Beijing China Key Lab of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi 'an China

ISBN: (纸本)9781467301732

In this paper, we propose a simple but effective method for the design of M-channel uniform linear-phase (LP) filter banks. We are mainly concerned with the significant aliasing caused by the two adjacent filters, leading to a near-perfect-reconstruction (NPR) system. With some assumptions, a matching condition is drived for efficient aliasing cancellation. By using the proposed design criteria to construct each filter, the requirements imposed on the entire filter bank become those on individual filters. It greatly simplifies the design of NPR uniform LP filter banks and no objective function in the optimization is explicitly required. In addition, the proposed method is more general with no limitation on the channel number and filter length. As illustrated by examples, the proposed method can provide a simple and efficient alternative for designing NPR uniform filter banks with the expected LP property.

关键词： Filter banks Finite impulse response filter Matched filters Filtering theory Filtering algorithms

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：