检索结果-内蒙古大学图书馆

International Conference on computer Vision (ICCV)

作者： Xing Zhang Zuxuan Wu Zejia Weng Huazhu Fu Jingjing Chen Yu-Gang Jiang Larry Davis Academy for Engineering and Technology Fudan University Shanghai Key Lab of Intel. Info. Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center on Intelligent Visual Computing Inception Institute of Artificial Intelligence University of Maryland

ISBN: (纸本)9781665428132

Label distributions in real-world are oftentimes long-tailed and imbalanced, resulting in biased models towards dominant labels. While long-tailed recognition has been extensively studied for image classification tasks, limited effort has been made for the video domain. In this paper, we introduce VideoLT, a large-scale long-tailed video recognition dataset, as a step toward real-world video recognition. VideoLT contains 256,218 untrimmed videos, annotated into 1,004 classes with a long-tailed distribution. Through extensive studies, we demonstrate that state-of-the-art methods used for long-tailed image recognition do not perform well in the video domain due to the additional temporal dimension in videos. This motivates us to propose FrameStack, a simple yet effective method for long-tailed video recognition. In particular, FrameStack performs sampling at the frame-level in order to balance class distributions, and the sampling ratio is dynamically determined using knowledge derived from the network during training. Experimental results demonstrate that FrameStack can improve classification performance without sacrificing the overall accuracy. Code and dataset are available at: https://***/17Skye17/VideoLT.

关键词： Training Knowledge engineering computer vision Adaptation models Image recognition Codes Computational modeling

来源：评论

学校读者我要写书评

暂无评论

A Non-Asymptotic Analysis for Stein Variational Gradient Descent

arXiv

引用

arXiv 2020年

作者： Korba, Anna Arbel, Michael Salim, Adil Luise, Giulia Gretton, Arthur Gatsby Computational Neuroscience Unit University College London Visual Computing Center KAUST Computer Science Department University College London

We study the Stein Variational Gradient Descent (SVGD) algorithm, which optimises a set of particles to approximate a target probability distribution π ∝ e−V on Rd. In the population limit, SVGD performs gradient descent in the space of probability distributions on the KL divergence with respect to π, where the gradient is smoothed through a kernel integral operator. In this paper, we provide a novel finite time analysis for the SVGD algorithm. We obtain a descent lemma establishing that the algorithm decreases the objective at each iteration, and provably converges, with less restrictive assumptions on the step size than required in earlier analyses. We further provide a guarantee on the convergence rate in Kullback-Leibler divergence, assuming π satisfies a Stein log-Sobolev inequality as in (Duncan et al., 2019), which takes into account the geometry induced by the smoothed KL gradient. Copyright © 2020, The Authors. All rights reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

The wasserstein proximal gradient algorithm 20

The wasserstein proximal gradient algorithm

引用

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Adil Salim Anna Korba Giulia Luise Visual Computing Center KAUST Gatsby Computational Neuroscience Unit University College London Computer Science Department University College London

ISBN: (纸本)9781713829546

Wasserstein gradient flows are continuous time dynamics that define curves of steepest descent to minimize an objective function over the space of probability measures (i.e., the Wasserstein space). This objective is typically a divergence w.r.t. a fixed target distribution. In recent years, these continuous time dynamics have been used to study the convergence of machine learning algorithms aiming at approximating a probability distribution. However, the discrete-time behavior of these algorithms might differ from the continuous time dynamics. Besides, although discretized gradient flows have been proposed in the literature, little is known about their minimization power. In this work, we propose a Forward Backward (FB) discretization scheme that can tackle the case where the objective function is the sum of a smooth and a nonsmooth geodesically convex terms. Using techniques from convex optimization and optimal transport, we analyze the FB scheme as a minimization algorithm on the Wasserstein space. More precisely, we show under mild assumptions that the FB scheme has convergence guarantees similar to the proximal gradient algorithm in Euclidean spaces.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A non-asymptotic analysis for stein variational gradient descent 20

A non-asymptotic analysis for stein variational gradient des...

引用

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Anna Korba Adil Salim Michael Arbel Giulia Luise Arthur Gretton Gatsby Computational Neuroscience Unit University College London Visual Computing Center KAUST Computer Science Department University College London

ISBN: (纸本)9781713829546

We study the Stein Variational Gradient Descent (SVGD) algorithm, which optimises a set of particles to approximate a target probability distribution π ∝ e-V on ℝd. In the population limit, SVGD performs gradient descent in the space of probability distributions on the KL divergence with respect to π, where the gradient is smoothed through a kernel integral operator. In this paper, we provide a novel finite time analysis for the SVGD algorithm. We provide a descent lemma establishing that the algorithm decreases the objective at each iteration, and rates of convergence for the averaged Stein Fisher divergence (also referred to as Kernel Stein Discrepancy). We also provide a convergence result of the finite particle system corresponding to the practical implementation of SVGD to its population version.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Smartphone Recommendation System Using Ensemble Machine Learning

A Novel Smartphone Recommendation System Using Ensemble Mach...

引用

computer science and Data Engineering (CSDE), IEEE Asia-Pacific Conference on

作者： Ahmad Almadhor Sidra Abbas Gabriel Avelino Sampedro Mideth Abisado Thippa Reddy Gadekallu College of Computer and Information Sciences Jouf University Sakaka Saudi Arabia Department of Computer Science COMSATS University Islamabad Islamabad Pakistan Faculty of Information and Communication Studies University of the Philippines Open University Los Baños Philippines Center for Computational Imaging and Visual Innovations De La Salle University Manila Philippines College of Computing and Information Technologies National University Manila Philippines Zhongda Group Jiaxing City Zhejiang Province China Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon School of Information Technology and Engineering Vellore Institute of Technology Tamil Nadu India College of Information Science and Engineering Jiaxing University Jiaxing China Division of Research and Development Lovely Professional University Phagwara India

Due to the proliferation of internet evaluations brought on by the rising demand for smartphones, consumers find it challenging to make accurate selections when purchasing. In this paper, we offer ensemble voting methods based on TF-IDF (Term Frequency-Inverse Document Frequency) features for clas-sifying mobile phone ratings. We use a recently assembled dataset comprising over 13,000 smartphone reviews from the Flipkart website. The suggested approach includes feature extraction using the TF-IDF, data cleaning, balancing, and voting-based model prediction. To identify the recently created Flipkart dataset, the suggested method created an ensemble voting mechanism based on machine learning techniques. According to the experimental findings, the suggested method performs more accurately and efficiently than conventional machine learning techniques. At 98.0 %, the model achieved the greatest accuracy. The suggested method can be expanded to additional e-commerce platforms with sizable datasets of online evaluations and assist customers in making updated purchase preferences.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The core decomposition of networks: theory, algorithms and applications

The core decomposition of networks: theory, algorithms and a...

引用

作者： Malliaros, Fragkiskos D. Giatsidis, Christos Papadopoulos, Apostolos N. Vazirgiannis, Michalis Center for Visual Computing CentraleSupélec University of Paris-Saclay and Inria Saclay Gif-Sur-Yvette France Computer Science Laboratory École Polytechnique Palaiseau France School of Informatics Aristotle University of Thessaloniki Thessaloniki Greece Department of Informatics Athens University of Economics and Business Athens Greece

The core decomposition of networks has attracted significant attention due to its numerous applications in real-life problems. Simply stated, the core decomposition of a network (graph) assigns to each graph node v, an integer number c(v) (the core number), capturing how well v is connected with respect to its neighbors. This concept is strongly related to the concept of graph degeneracy, which has a long history in graph theory. Although the core decomposition concept is extremely simple, there is an enormous interest in the topic from diverse application domains, mainly because it can be used to analyze a network in a simple and concise manner by quantifying the significance of graph nodes. Therefore, there exists a respectable number of research works that either propose efficient algorithmic techniques under different settings and graph types or apply the concept to another problem or scientific area. Based on this large interest in the topic, in this survey, we perform an in-depth discussion of core decomposition, focusing mainly on: (i) the basic theory and fundamental concepts, (ii) the algorithmic techniques proposed for computing it efficiently under different settings, and (iii) the applications that can benefit significantly from it. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Efficient Pyramid Channel Attention Network for Pathological Myopia Recognition

arXiv

引用

arXiv 2023年

作者： Zhang, Xiaoqing Zhao, Jilu Li, Yan Wu, Hao Zhou, Xiangtian Liu, Jiang Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Center for High Performance Computing Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China National Clinical Research Center for Ocular Diseases Eye Hospital Wenzhou Medical University Wenzhou325027 China State Key Laboratory of Ophthalmology Optometry and Visual Science Eye Hospital Wenzhou Medical University Wenzhou325027 China Research Unit of Myopia Basic Research and Clinical Prevention and Control Chinese Academy of Medical Sciences Wenzhou325027 China Singapore Eye Research Institute 169856 Singapore

Pathological myopia (PM) is the leading ocular disease for impaired vision worldwide. Clinically, the characteristic of pathology distribution in PM is global-local on the fundus image, which plays a significant role in assisting clinicians in diagnosing PM. However, most existing deep neural networks focused on designing complex architectures but rarely explored the pathology distribution prior of PM. To tackle this issue, we propose an efficient pyramid channel attention (EPCA) module, which fully leverages the potential of the clinical pathology prior of PM with pyramid pooling and multi-scale context fusion. Then, we construct EPCA-Net for automatic PM recognition based on fundus images by stacking a sequence of EPCA modules. Moreover, motivated by the recent pretraining-and-finetuning paradigm, we attempt to adapt pre-trained natural image models for PM recognition by freezing them and treating the EPCA and other attention modules as adapters. In addition, we construct a PM recognition benchmark termed PM-fundus by collecting fundus images of PM from publicly available datasets. The comprehensive experiments demonstrate the superiority of EPCA-Net over state-of-the-art methods in the PM recognition task. For example, EPCA-Net achieves 97.56% accuracy and outperforms ViT by 2.85% accuracy on the PM-fundus dataset. The results also show that our method based on the pretraining-and-finetuning paradigm achieves competitive performance through comparisons to part of previous methods based on traditional fine-tuning paradigm with fewer tunable parameters, which has the potential to leverage more natural image foundation models to address the PM recognition task in limited medical data regime. Copyright © 2023, The Authors. All rights reserved.

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

Camg: Context-Aware Moment Graph Network for Multimodal Temporal Activity Localization Via Language

SSRN

引用

SSRN 2022年

作者： Hu, Yuelin Xu, Yuanwu Zhang, Yuejie Feng, Rui Zhang, Tao Lu, Xuequan Gao, Shang School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University Shanghai200433 China School of Information Management and Engineering Shanghai Key Laboratory of Financial Information Technology Shanghai University of Finance and Economics Shanghai200433 China School of Information Technology Deakin University Waurn Ponds VIC3216 Australia

Temporal Activity Localization via Language (TALL) is a challenging task for language based video understanding, especially when a video contains multiple moments of interest and the language query has words describing complex context dependencies between the moments. Latest studies have proposed various ways to exploit the temporal context of adjacent moments, but two apparent limitations remained. First, only limited context information was encoded based on RNNs or 2-D convolutions, which highly depended on the pre-sorting of proposals and lacked flexibility. Second, semantically correlated content in different moments was ignored, i.e., semantic context. To address these limitations, we propose a novel GCN-based framework, i.e., Context-Aware Moment Graph (CAMG) network, to jointly model the temporal context and semantic context. GCNs enable the CAMG to capture long-range dependencies with high flexibility. Also, we design a multi-step fusion scheme to aggregate object, motion and textual © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

CDIMC-net: Cognitive deep incomplete multi-view clustering network 29

CDIMC-net: Cognitive deep incomplete multi-view clustering n...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Wen, Jie Zhang, Zheng Xu, Yong Zhang, Bob Fei, Lunke Xie, Guo-Sen Bio-Computing Research Center Harbin Institute of Technology Shenzhen Shenzhen China Shenzhen Key Laboratory of Visual Object Detection and Recognition Shenzhen China Pengcheng Laboratory Shenzhen China Department of Computer and Information Science University of Macau Taipa China School of Computer Science and Technology Guangdong University of Technology Guangzhou China Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates

ISBN: (纸本)9780999241165

In recent years, incomplete multi-view clustering, which studies the challenging multi-view clustering problem on missing views, has received growing research interests. Although a series of methods have been proposed to address this issue, the following problems still exist: 1) Almost all of the existing methods are based on shallow models, which is difficult to obtain discriminative common representations. 2) These methods are generally sensitive to noise or outliers since the negative samples are treated equally as the important samples. In this paper, we propose a novel incomplete multi-view clustering network, called Cognitive Deep Incomplete Multi-view Clustering Network (CDIMC-net), to address these issues. Specifically, it captures the high-level features and local structure of each view by incorporating the view-specific deep encoders and graph embedding strategy into a framework. Moreover, based on the human cognition, i.e., learning from easy to hard, it introduces a self-paced strategy to select the most confident samples for model training, which can reduce the negative influence of outliers. Experimental results on several incomplete datasets show that CDIMC-net outperforms the state-of-the-art incomplete multi-view clustering methods. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

Autonomous outdoor scanning via online topological and geometric path optimization

arXiv

引用

arXiv 2020年

作者： Huang, Pengdi Lin, Liqiang Xu, Kai Huang, Hui Visual Computing Research Center Shenzhen University Shenzhen518060 China School of Computer Science National University of Defense Technology Changsha410000 China

Autonomous 3D acquisition of outdoor environments poses special challenges. Different from indoor scenes, where the room space is delineated by clear boundaries and separations (e.g., walls and furniture), an outdoor environment is spacious and unbounded (thinking of a campus). Therefore, unlike for indoor scenes where the scanning effort is mainly devoted to the discovery of boundary surfaces, scanning an open and unbounded area requires actively delimiting the extent of scanning region and dynamically planning a traverse path within that region. Thus, for outdoor scenes, we formulate the planning of an energy-efficient autonomous scanning through a discrete-continuous optimization of robot scanning paths. The discrete optimization computes a topological map, through solving an online traveling sales problem (Online TSP), which determines the scanning goals and paths on-the-fly. The dynamic goals are determined as a collection of visit sites with high reward of visibility-to-unknown. A visit graph is constructed via connecting the visit sites with edges weighted by traversing cost. This topological map evolves as the robot scans via deleting outdated sites that are either visited or become rewardless and inserting newly discovered ones. The continuous part optimizes the traverse paths geometrically between two neighboring visit sites via maximizing the information gain of scanning along the paths. The discrete and continuous processes alternate until the traverse cost of the current graph exceeds the remaining energy capacity of the robot. Our approach is evaluated with both synthetic and field tests, demonstrating its effectiveness and advantages over alternatives. The project is at http://***/research/2020/Husky, and the codes are available at https://***/alualu628628/AutonomousOutdoor-Scanning-via-Online-Topological-and-Geometric-Path-Optimization. Copyright © 2020, The Authors. All rights reserved.

关键词： Motion planning

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：