检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xinyan Liu Guorong Li Yuankai Qi Ziheng Yan Zhenjun Han Anton van den Hengel Ming-Hsuan Yang Qingming Huang University of Chinese Academy of Science Key Lab of Big Data Mining and Knowledge Management UCAS China Macquarie University Australian Institute for Machine Learning The University of Adelaide University of California at Merced Key Lab of Intell. Info. Process. Inst. of Comput. Tech. CAS

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Video Individual Counting (VIC) aims to predict the number of unique individuals in a single video. Existing methods learn representations based on trajectory labels for individuals, which are annotation-expensive. To provide a more realistic reflection of the underlying practical challenge, we introduce a weakly supervised VIC task, wherein trajectory labels are not provided. Instead, two types of labels are provided to indicate traffic entering the field of view (inflow) and leaving the field view (outflow). We also propose the first solution as a baseline that formulates the task as a weakly supervised contrastive learning problem under group-level matching. In doing so, we devise an end-to-end trainable soft contrastive loss to drive the network to distin-guish inflow, outflow, and the remaining. To facilitate future study in this direction, we generate annotations from the existing VIC datasets Sense Crowd and CroHD and also build a new dataset, UAVVIC. Extensive results show that our baseline weakly supervised method outperforms supervised methods, and thus, little information is lost in the transition to the more practically relevant weakly supervised task. The code and trained model can be found at CGNet.

关键词： Computer vision Costs Codes Annotations Contrastive learning Drives Reflection

来源：评论

学校读者我要写书评

暂无评论

WHEN TO TRUST AGGREGATED GRADIENTS: ADDRESSING NEGATIVE CLIENT SAMPLING IN FEDERATED LEARNING

arXiv

引用

arXiv 2023年

作者： Yang, Wenkai Lin, Yankai Zhao, Guangxiang Li, Peng Zhou, Jie Sun, Xu Center for Data Science Peking University China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Shanghai AI Lab China Tsinghua University Beijing China Pattern Recognition Center WeChat AI Tencent Inc. China MOE Key Lab of Computational Linguistics School of Computer Science Peking University China

Federated Learning has become a widely-used framework which allows learning a global model on decentralized local datasets under the condition of protecting local data privacy. However, federated learning faces severe optimization difficulty when training samples are not independently and identically distributed (non-i.i.d.). In this paper, we point out that the client sampling practice plays a decisive role in the aforementioned optimization difficulty. We find that the negative client sampling will cause the merged data distribution of currently sampled clients heavily inconsistent with that of all available clients, and further make the aggregated gradient unreliable. To address this issue, we propose a novel learning rate adaptation mechanism to adaptively adjust the server learning rate for the aggregated gradient in each round, according to the consistency between the merged data distribution of currently sampled clients and that of all available clients. Specifically, we make theoretical deductions to find a meaningful and robust indicator that is positively related to the optimal server learning rate and can effectively reflect the merged data distribution of sampled clients, and we utilize it for the server learning rate adaptation. Extensive experiments on multiple image and text classification tasks validate the great effectiveness of our method. © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

EABC: Energy-aware Centrality-based Caching for Named data Networking in the IoT

EABC: Energy-aware Centrality-based Caching for Named Data N...

引用

IEEE International Symposium on World of Wireless Mobile and Multimedia Networks (WoWMoM)

作者： Xingyun He Hu Liu Wuyungerile Li Alvin Valera Winston K.G. Seah Inner Mongolia Key Lab. of Wireless Networking & Mobile Computing Engineering Research Center of Ecological Big Data Ministry of Education School of Computer Science Inner Mongolia University Hohhot China Wireless Networks Research Group School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand

ISBN: (数字)9798350394665

ISBN: (纸本)9798350394672

Named data Networking (NDN) is an information-centric internet architecture that delivers packets based on the name of the content in the packet. A key component of NDN is the caching strategy designed to reduce total network latency and load on content producers. To improve the speed and reliability of web content delivery, existing caching strategies typically cache content on a large number of intermediate nodes, which incur significant energy consumption and memory overhead. However, in Internet of Things (IoT) scenarios, memory and energy of nodes are scarce resources. Therefore, in NDN-based IoT applications, traditional caching strategies can cause node failures due to energy depletion, which can significantly reduce the network operational lifetime as well as create problems that caching is supposed to solve. In this paper, a caching strategy based on node centrality and energy availability, called Energy-aware Approximate Betweenness Centrality (EABC) is proposed for NDN-based IoT. EABC uses a topology-based heuristic to cache data content on nodes with high centrality and makes caching decisions based on the remaining energy of the nodes. We evaluate EABC using simulations based on ndnSIM in different topologies and compare it with several existing NDN caching strategies. The results show that EABC performs better in different types of network topologies, reduces the average transmission delay of data and balances the energy consumption of highly central nodes, thus extending the network lifetime.

关键词： Wireless communication Energy consumption Network topology Memory management Topology Delays Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Towards high-throughput and low-latency billion-scale vector search via CPU/GPU collaborative filtering and re-ranking 25

Towards high-throughput and low-latency billion-scale vector...

引用

Proceedings of the 23rd USENIX Conference on File and Storage Technologies

作者： Bing Tian Haikun Liu Yuhang Tang Shihai Xiao Zhuohui Duan Xiaofei Liao Hai Jin Xuecang Zhang Junhua Zhu Yu Zhang National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Huawei Technologies Co. Ltd Towards high-throughput and low-latency billion-scale vector search via CPU/GPU collaborative filtering and re-ranking

ISBN: (纸本)9781939133458

Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure. Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services. None of modern ANNS systems can address these issues simultaneously. In this paper, we present Fusion-ANNS, a high-throughput, low-latency, cost-efficient, and high-accuracy ANNS system for billion-scale datasets using SSDs and only one entry-level GPU. The key idea of Fusion-ANNS lies in CPU/GPU collaborative filtering and reranking mechanisms, which significantly reduce I/O operations across CPUs, GPU, and SSDs to break through the I/O performance bottleneck. Specifically, we propose three novel designs: (1) multi-tiered indexing to avoid data swapping between CPUs and GPU, (2) heuristic re-ranking to eliminate unnecessary I/Os and computations while guaranteeing high accuracy, and (3) redundant-aware I/O deduplication to further improve I/O efficiency. We implement FusionANNS and compare it with the state-of-the-art SSD-based ANNS system-SPANN and GPU-accelerated in-memory ANNS system-RUMMY. Experimental results show that FusionANNS achieves 1) 9.4-13.1× higher query per second (QPS) and 5.7-8.8× higher cost efficiency compared with SPANN; 2) and 2-4.9× higher QPS and 2.3-6.8× higher cost efficiency compared with RUMMY, while guaranteeing low latency and high accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting the Risk of Incident Cardiovascular Disease Using Retinal Vessel Caliber Measured by Artificial Intelligence in a Chinese Community-Based Population

SSRN

引用

SSRN 2025年

作者： Luo, Xingyu Yang, Guangzhengao Fan, Fangfang Jiang, Yimeng Jia, Jia Zhao, Jie Chen, Zifan Yan, Shenshen She, Haicheng Zheng, Bo Zhang, Li Zhang, Yan Department of Cardiology Peking University First Hospital Beijing China Institute of Cardiovascular Disease Peking University First Hospital Beijing China Center for Data Science Peking University Beijing China National Engineering Laboratory for Big Data Analysis and Applications Peking University Beijing China Peking University Changsha Institute for Computing and Digital Economy Beijing China Beijing Tongren Eye Center Beijing Tongren Hospital Capital Medical University Beijing Ophthalmology and Visual Science Key Lab Beijing China

Background: The predictive value of retinal vessel caliber, measured through artificial intelligence (AI), for incident cardiovascular disease (CVD) risk remains to be explored. Our study aimed to investigate the association between AI-measured retinal vessel caliber and the risk of incident CVD in a Chinese community-based population. Methods: We conducted a prospective cohort study on subjects from a Beijing community in China who were free of prevalent stroke or myocardial infarction and underwent retinal photography at baseline. By deep-learning algorithm, retinal vessel caliber measurements, including central retinal arteriolar equivalent (CRAE), central retinal venular equivalent (CRVE), and arteriolar-to-venular ratio (AVR), were obtained from 0.5 to 1 disc diameter from the optic disc margin. The primary endpoint was an incident major adverse cardiovascular event (MACE), defined as a composite of first non-fatal stroke, first non-fatal acute myocardial infarction (AMI), and cardiovascular death. The secondary endpoints included first stroke, first AMI, and cardiovascular death. Findings: A total of 3,585 participants were included. The mean age was 56.49 ± 8.94 years, and 2335 (65.1%) were female. Prevalence of prior hypertension and diabetes was 1594 (44.5%) and 676 (18.9%), respectively. The mean values for CRAE, CRVE, and AVR were 190.83 ± 29.92 μm, 278.26 ± 36.34 μm, and 0.69 ± 0.08, respectively. During the follow-up (median, 7.53 years), there were 293 cases of incident MACE (8.2%), 226 strokes (6.3%), 57 AMIs (1.6%), and 44 cardiovascular deaths (1.2%). The Kaplan–Meier curves showed significant differences in cumulative hazards of the primary endpoint among tertiles of CRAE, CRVE, and AVR. In Cox proportional-hazards models adjusting for covariates, CRAE was negatively associated with the risk of incident MACE (per 10 μm increase, hazard ratio [HR] = 0.95, 95% confidence interval [CI]: 0.92-0.99, P = 0.009) and the risk of incident stroke (per 10 μm

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

A multimodal hybrid deep learning approach for pest forecasting using time series and satellite images

引用

Information Fusion 2025年 124卷

作者： A.M. Chacón-Maldonado G. Asencio-Cortés A. Troncoso Data Science and Big Data Lab Pablo de Olavide University Ctra. de Utrera km. 1 Seville 41013 Spain

Accurate forecasting of agricultural pests is essential for optimizing crop protection and mitigating economic losses. This work introduces a multimodal hybrid methodology to forecast the population of the olive fruit fly, enabling one-week-ahead outbreak predictions. The methodology consists of integrating an embedding model based on a deep convolutional neural network and other machine learning models with the aim of processing data from satellite images and time series. Different machine learning algorithms such as random forest, extreme gradient boosting and a fully connected deep neural network have been evaluated to be used in the proposed multimodal hybrid methodology. Firstly, the deep convolutional neural network extracts spatial features from Sentinel-2 L2A satellite imagery, specifically vegetation indexes, and then these extracted features are fused with meteorological data to improve the accuracy of the predictions obtained by a machine learning model. Results using images and time series from four plots of olive groves in Andalusia (Spain) are reported and compared with a convolutional neural network, random forest, extreme gradient boosting and a fully connected deep learning model when used separately and without data fusion. Experimental results show that the multimodal hybrid approach outperforms standalone machine learning models, improving predictive capabilities and facilitating timely and informed decision-making in agricultural pest management. Additionally, our findings highlight the relevance of multi-source data fusion in forecasting tasks, reinforcing the potential of deep learning for real-world agricultural applications.

关键词： Information fusion Multimodal data Deep learning Agricultural pest forecasting

来源：评论

学校读者我要写书评

暂无评论

SMOG: Accelerating Subgraph Matching on GPUs

SMOG: Accelerating Subgraph Matching on GPUs

引用

IEEE Conference on High Performance Extreme Computing (HPEC)

作者： Zhibin Wang Ziheng Meng Xue Li Xi Lin Long Zheng Chen Tian Sheng Zhong State Key Laboratory for Novel Software Technology Nanjing University Alibaba Group“ National Engineering Research Center for Big Data Technology and System/ Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory Huazhong University of Science and Technology Zhejiang Lab

Subgraph matching is a crucial problem in graph theory with diverse applications in fields, such as bioinformatics, social networks and recommendation systems. Accelerating subgraph matching can be greatly facilitated by GPUs, which offer exceptional parallelism and high memory bandwidth. By leveraging the power of multiple GPU cards, subgraph matching can be scaled to achieve unprecedented levels of performance. In this paper, we propose SMOG, an abbreviation for. Subgraph Matching On Multi-Card GPUs. It is a general, high-performance and scalable sub graph matching system that utilizes multi-card GPUs. To address the issue of duplication resulting from subgraph automorphism, SMOG introduces a two-step approach. Firstly, it analyzes the symmetry within the subgraph. Then, it adaptively adjusts the graph preprocessing and generates subgraph-aware GPU codes tailored to the given subgraph. Furthermore, SMOG leverages multi-level parallelism by designing the specific strategy for each level, enabling it to scale from 1 to 1,024 GPU cards, resulting in an extraordinary $553\times$ speedup. We evaluate SMOG on various subgraph queries and datasets. The experimental results demonstrate that SMOG outperforms the triangle-specific system TRUST with an average speedup of $2.94\times$ . And it performs significantly better than the subgraph matching system RPS by $203.55\times$ and the graph processing system Gunrock by 35, $455.52\times$ on average.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-task Learning for Multi-turn Dialogue Generation with Topic Drift Modeling 12

Multi-task Learning for Multi-turn Dialogue Generation with ...

引用

12th IEEE International Conference on big Knowledge, ICBK 2021

作者： Zeng, Hongwei Hong, Zhenjie Liu, Jun Wei, Bifan Xi'An Jiaotong University School of Computer Science and Technology Xi'an China Xi'An Jiaotong University National Engineering Lab For Big Data Analytics Xi'an China Xi'An Jiaotong University School of Continuing Education Xi'an China

ISBN: (纸本)9781665438582

Multi-turn dialogue generation aims to generate natural and fluent responses that should be consistent with multiple consecutive utterances history. It is a more challenging task compared to its single-turn counterpart since it requires the model to capture the topic drift along with the multi-turn dialogue history. In this paper, we propose a multi-turn dialogue generation model which incorporates topic drift aware information into a hierarchical encoder-decoder framework to generate coherent responses. This model first utilizes a Convolutional Neural Network (CNN) based topic model to obtain the topic representation of each utterance. Then a topic drift model is employed to encode the sequential topics of multi-turn dialogue history to infer the topic of response. During the response generation, a specially designed topic drift aware generator is proposed to dynamically balance the impact of the inferred topic of response and local word structure. Fur-thermore, we employ multi-task learning to optimize the topic drift model and dialogue generation simultaneously. Extensive experimental results on two benchmark datasets (i.e. Cornell Movie Dialog Corpus and Ubuntu Dialogue dataset) indicate that our proposed model can generate more coherent responses, and significantly outperform other dialogue generation models. © 2021 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Lesion-aware Dynamic Kernel for Polyp Segmentation

arXiv

引用

arXiv 2023年

作者： Zhang, Ruifei Lai, Peiwen Wan, Xiang Fan, De-Jun Gao, Feng Wu, Xiao-Jian Li, Guanbin School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Shenzhen Research Institute of Big Data Shenzhen China The Sixth Affiliated Hospital Sun Yat-sen University Guangzhou China Pazhou Lab Guangzhou China

Automatic and accurate polyp segmentation plays an essential role in early colorectal cancer diagnosis. However, it has always been a challenging task due to 1) the diverse shape, size, brightness and other appearance characteristics of polyps, 2) the tiny contrast between concealed polyps and their surrounding regions. To address these problems, we propose a lesion-aware dynamic network (LDNet) for polyp segmentation, which is a traditional u-shape encoder-decoder structure incorporated with a dynamic kernel generation and updating scheme. Specifically, the designed segmentation head is conditioned on the global context features of the input image and iteratively updated by the extracted lesion features according to polyp segmentation predictions. This simple but effective scheme endows our model with powerful segmentation performance and generalization capability. Besides, we utilize the extracted lesion representation to enhance the feature contrast between the polyp and background regions by a tailored lesion-aware cross-attention module (LCA), and design an efficient self-attention module (ESA) to capture long-range context relations, further improving the segmentation accuracy. Extensive experiments on four public polyp benchmarks and our collected large-scale polyp dataset demonstrate the superior performance of our method compared with other state-of-the-art approaches. The source code is available at https://***/ReaFly/LDNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

GeckoDAG: Towards a Lightweight DAG-Based Blockchain via Reducing data Redundancy

GeckoDAG: Towards a Lightweight DAG-Based Blockchain via Red...

引用

International Conference on Distributed Computing Systems

作者： Xiaohai Dai Yifan Zhou Jiang Xiao Feng Cheng Xia Xie Hai Jin Bo Li National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China School of Computer Science and Technology Hainan University China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

To overcome the scaling and performance limitations, the Directed Acyclic Graph (DAG) is utilized as the underlying storage model of blockchain systems, which enables concurrent transaction processing and confirmation. However, accompanied by high performance, DAG-based blockchains still suffer from the severe challenge of constrained storage scalability, i.e., expensive storage overhead. Based on an in-depth analysis of the data, we discover that the root cause of storage overhead stems from the considerable data redundancy in the DAG-based blockchains. In this paper, we propose GeckoDAG, a lightweight DAG-based blockchain, whose design consists of two steps. First, we abstract a storage model named Basic from the existing DAG-based blockchain systems, which offers both high performance and security. On top of Basic, we then devise GeckoDAG, which merges previous transactions into Transaction Union (TU) and reduces the data redundancy in TU, thus lowering the storage overhead. To evaluate our design, we implement a prototype of GeckoDAG and conduct various experiments on it. The experimental results demonstrate that GeckoDAG can offer storage scalability while maintaining the security and efficiency of DAG-based blockchains.

关键词：

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：