检索结果-内蒙古大学图书馆

TechRxiv 2023年

作者： Li, Yingsong Huang, Xinqi Zakharov, Yuriy Miao, Yongchun Huang, Zhixiang Li, Liping The College of Information and Communication Engineering Harbin Engineering University Harbin150001 China The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230601 China The School of Physics Engineering and Technology University of York YorkYO10 5DD United Kingdom

We presents a squared sine functioned adaptive (SSA) algorithm for acoustic-echo-cancellation (AEC) applications in-presence-of impulsive noise. In the development of the SSA algorithm, a novel cost function is constructed by exerting a sliding window type squared sine function on the estimation error vector, which provides robustness in the impulsive-noise environments and speed-ups convergence when the input is colored signals. Theoretical models for predicting the mean-weight-behavior, transient excess-mean-square-error (EMSE) behavior, and tracking behavior are presented. Moreover, the optimal step size and minimum EMSE of the tracking performance are provided. The computation complexity of SSA algorithm has also been investigated. Numerical experiments demonstrate that the theoretical results match well with simulation results and show the superiority of the proposed SSA algorithm against known algorithms in AEC applications. © 2023, CC BY.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

Unified-modal Salient Object Detection via Adaptive Prompt Learning

arXiv

引用

arXiv 2023年

作者： Wang, Kunpeng Li, Chenglong Tu, Zhengzheng Liu, Zhengyi Luo, Bin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China The Institute of Physical Science and Information Technology Anhui University Hefei230601 China

Existing single-modal and multi-modal salient object detection (SOD) methods focus on designing specific architectures tailored for their respective tasks. However, developing completely different models for different tasks leads to labor and time consumption, as well as high computational and practical deployment costs. In this paper, we attempt to address both single-modal and multi-modal SOD in a unified framework called UniSOD, which fully exploits the overlapping prior knowledge between different tasks. Nevertheless, assigning appropriate strategies to modality variable inputs is challenging. To this end, UniSOD learns modality-aware prompts with task-specific hints through adaptive prompt learning, which are plugged into the proposed pre-trained baseline SOD model to handle corresponding tasks, while only requiring few learnable parameters compared to training the entire model. Each modality-aware prompt is generated from a switchable prompt generation block, which adaptively performs structural switching based on single-modal and multi-modal inputs without human intervention. Through end-to-end joint training, UniSOD achieves overall performance improvement on 14 benchmark datasets for RGB, RGB-D, and RGB-T SOD, which demonstrates that our method effectively and efficiently unifies single-modal and multi-modal SOD tasks. The code and results are available at https://***/Angknpng/UniSOD. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection 41

Size-Invariance Matters: Rethinking Metrics and Losses for I...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright 2024 by the author(s)

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Distributed Storage Middleware Based on HBase and Redis 15th

A Distributed Storage Middleware Based on HBase and Redis

引用

15th CCF Conference on Computer Supported Cooperative Work and Social computing, Chinese CSCW 2020

作者： Xu, Lingling Chen, Yuzhong Guo, Kun College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China

ISBN: (纸本)9789811625398

In the era of big data, traditional relational databases face challenges in massive data storage. HBase is a non-relational database based on column storage which is used widely for big data storage. The writing performance of HBase is high, but the unbalanced load caused by its uneven data storage strategy is the bottleneck of its reading performance. HBase needs to access disks to get query results. Therefore, the efficiency of disk access has a great impact on the query performance of HBase. In view of the above problems, this paper proposes a storage middleware which utilizes HBase for load balancing and Redis for memory caching. Specifically, we improve HBase’s original load balancing algorithm for Regions and RegionServers and customize a Redis cache eviction algorithm according to the data’s query and update frequency. Furthermore, the coprocessor of HBase is used to synchronize data between HBase and Redis. Experiments on synthetic datasets show that the proposed storage middleware achieves better writing and reading performance than HBase. The load balancing algorithm employed in the middleware is better than HBase's original algorithm. The hit rate of the customized cache eviction algorithm is also higher than that of the LRU algorithm. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

An Overlapping Local Community Detection Algorithm Based on Node Transitivity and Modularity Density 15th

An Overlapping Local Community Detection Algorithm Based on ...

引用

15th CCF Conference on Computer Supported Cooperative Work and Social computing, Chinese CSCW 2020

作者： Huang, Xintong Wu, Ling Guo, Kun College of Mathematics and Computer Sciences Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350116 China

ISBN: (纸本)9789811625398

The local community detection (LCD) method can discover the local community structure in which the seed node is located. Compared with global community detection, local community detection is characterized by its low cost and high efficiency. However, most existing LCD methods only return a non-overlapping community. Individuals in the real world may participate in multiple communities, which can only be discovered by using overlapping local community detection methods. In this study, an overlapping local community detection algorithm based on modularity and node transitivity. First, the scope and structure information of the overlapping communities are obtained according to the node transitivity. Second, NMF is used to obtain the number of overlapping communities. Finally, the local modularity density based on edge weights is used to refine the detected local communities. The experimental results validate the high performance of our method to the other method in comparison. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Improving Molecular Graph Generation with Flow Matching and Optimal Transport

arXiv

引用

arXiv 2024年

作者： Hou, Xiaoyang Zhu, Tian Ren, Milong Bu, Dongbo Gao, Xin Zhang, Chunming Sun, Shiwei Key Laboratory of Intelligent Information Processing Institute of Computing Technology School of Computer Science and Technology University of Chinese Academy of Sciences China Central China Research Institute for Artificial Intelligence Technologies China Western Institute of Computing Technology Phil Rivers Technology King Abdullah University of Science and Technology Saudi Arabia

Generating molecular graphs is crucial in drug design and discovery but remains challenging due to the complex interdependencies between nodes and edges. While diffusion models have demonstrated their potentiality in molecular graph design, they often suffer from unstable training and inefficient sampling. To enhance generation performance and training stability, we propose GGFlow, a discrete flow matching generative model incorporating optimal transport for molecular graphs and it incorporates an edge-augmented graph transformer to enable the direct communications among chemical bounds. Additionally, GGFlow introduces a novel goal-guided generation framework to control the generative trajectory of our model, aiming to design novel molecular structures with the desired properties. GGFlow demonstrates superior performance on both unconditional and conditional molecule generation tasks, outperforming existing baselines and underscoring its effectiveness and potential for wider application. © 2024, CC BY.

关键词： Molecular docking

来源：评论

学校读者我要写书评

暂无评论

No-Reference Stereoscopic Image Quality Assessment Based on Binocular Collaboration

SSRN

引用

SSRN 2024年

作者： Guo, Wenzhong Wang, Hanling Ke, Xiao Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fujian Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou University Fuzhou350116 China

Stereoscopic images usually consist of a left view, a right view, and depth information. Stereoscopic/3D image quality assessment (SIQA) is often more challenging compared to 2D-IQA due to the usual scene differences between left and right views and the complexity of the binocular vision fusion process. To address the problem of quality prediction bias of multi-distortion images, we investigated the visual physiology and the processing of visual information by the primary visual cortex of the human brain and proposed a no-reference stereoscopic image quality evaluation method. The method mainly includes an innovative end-to-end NR-SIQA neural network with a picture patch generation algorithm. The algorithm generates a saliency map by fusing the left and right views and then guides the image cropping in the database based on the saliency map. The proposed models are validated and compared based on publicly available databases. The results show that the model and algorithm together outperform the state-of-the-art NR-SIQA metric in the LIVE 3D database and the WIVC 3D database, and have excellent results in the specific noise metric. The model generalization experiments demonstrate a certain degree of generality of our proposed model. © 2024, The Authors. All rights reserved.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Structure-Guided Graph Generation for Multi-View Semi-Supervised Classification

SSRN

引用

SSRN 2024年

作者： Wu, Yilin Chen, Zhaoliang Zou, Ying Wang, Shiping Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China Department of Computer Science Hong Kong Baptist University Hong Kong

Graph convolutional network has emerged as a focal point in machine learning because of its robust graph processing capability. Most existing graph convolutional network-based approaches are designed for single-view data, yet in many practical scenarios, data is represented through multiple views. Although the ability of graph convolutional network is undeniable, the quality of graph directly affects its performance. Moreover, the process of graph generation with traditional nearest neighbor in traditional multi-view learning actually amplifies the influence of different information on performance across these views. To tackle the aforementioned challenges, this paper proposes a multi-scale graph generation deep learning framework, called multi-scale semi-supervised graph generation based multi-view classification, consisting of two modules: edge sampling and path sampling. The former aims to generate an adjacency graph by selecting edges based on the maximum likelihood among graphs from different views. Meanwhile, the latter seeks to construct adjacency graphs according to the characteristics of paths within the graphs. Extensive experimental results robustly demonstrate the superior performance of our proposed framework, compared to other state-of-the-art multi-view semi-supervised approaches. © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

The Design and Implementation of KMeans Based on Unified Batch and Streaming processing 15th

The Design and Implementation of KMeans Based on Unified Bat...

引用

15th CCF Conference on Computer Supported Cooperative Work and Social computing, Chinese CSCW 2020

作者： Chen, Hao Guo, Kun Chen, Yuzhong Guo, Hong College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China

ISBN: (纸本)9789811625398

Clustering algorithms aim at gathering similar data points from a dataset in an unsupervised manner. Although the batch clustering algorithms have relatively high accuracy, they cannot make use of the dynamic clustering results efficiently. The requirement of using the whole dataset in calculation results in the problems of resource waste and high time cost. On the contrary, incremental clustering only needs to update the varied part of a model upon the arrival of new data, which makes it unnecessary to recluster the whole data all the time. The feature is very suitable for the streaming data process, but it decreases the accuracy of the algorithms and cannot satisfy the low latency requirement of real-time data processing. In response to this problem, the paper proposes a novel unified batch and streaming clustering model (UBSCM) based on streaming computation, which includes a streaming cluster feature updating mechanism (SCFUM). The Flink framework is used to implement a new streaming KMeans algorithm based on UBSCM (KMeansUBSP). The experiments on the real-world datasets validate that the new streaming KMeans algorithm is effective in clustering the batch and streaming data in a unified manner. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

LP-Gaussians: Learnable Parametric Gaussian Splatting for Efficient Dynamic Reconstruction of Single-View Scenes

LP-Gaussians: Learnable Parametric Gaussian Splatting for Ef...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Shaoqi Wu Weixing Xie Youhong Peng Jinwen Li Jiawei Yao Junfeng Yao Center for Digital Media Computing School of Film School of Informatics Xiamen University China National Institute for Data Science in Health and Medicine Xiamen University China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

With the popularity of short video platforms, the number of single-view videos has increased significantly. Existing NeRF-based methods can reconstruct dynamic scenes in a single-view setting, but slow rendering speed and low rendering quality limit their practical applications. To address these challenges, we propose a fast single-view scenes reconstruction framework based on 3D Gaussian Splatting. Our method uses point clouds obtained with depth priors as the Gaussian initialization and introduces learnable parametric functions to model the time-dependent deformation of Gaussians. The explicit deformation modeling for Gaussians significantly reduces training and rendering time. Furthermore, to improve the rendering quality of challenging areas, we adopt an adaptive sampling strategy to densify Gaussians. For occlusion problems from single-view videos, we design a smooth loss function to restore the color of the occluded areas. Experimental results demonstrate that our method significantly reduces training time, enhances rendering quality, and accelerates rendering speed. Project page: https://***/LPGaussians.

关键词： Training Point cloud compression Deformable models Adaptation models Three-dimensional displays Deformation Streaming media signal processing Rendering (computer graphics) Speech processing

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：