检索结果-内蒙古大学图书馆

ViGT: proposal-free video grounding with a learnable token in the transformer

science China(Information sciences) 2023年第10期66卷 196-212页

作者： Kun LI Dan GUO Meng WANG School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province Institute of Artificial Intelligence Hefei Comprehensive National Science Center

The video grounding(VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in the complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely video grounding transformer(ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows.(1) The token is unrelated to the video or the query and avoids data bias toward the original video and query.(2) The token simultaneously performs global context aggregation from video and query ***, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention(i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets:ANet-Captions, TACoS, and YouCookⅡ. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT.

关键词： video grounding temporal sentence grounding boundary regression token learning proposal-free

来源：评论

学校读者我要写书评

暂无评论

A survey on dynamic graph processing on GPUs: concepts, terminologies and systems

引用

Frontiers of computer science 2024年第4期18卷 1-23页

作者： Hongru GAO Xiaofei LIAO Zhiyuan SHAO Kexin LI Jiajie CHEN Hai JIN 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 TechnologyHuazhong University of Science and TechnologyWuhan 430074China Zhejiang Lab Hangzhou 311121China

Graphs that are used to model real-world entities with vertices and relationships among entities with edges,have proven to be a powerful tool for describing real-world problems in *** most real-world scenarios,entities and their relationships are subject to constant *** that record such changes are called dynamic *** recent years,the widespread application scenarios of dynamic graphs have stimulated extensive research on dynamic graph processing systems that continuously ingest graph updates and produce up-to-date graph analytics *** the scale of dynamic graphs becomes larger,higher performance requirements are demanded to dynamic graph processing *** the massive parallel processing power and high memory bandwidth,GPUs become mainstream vehicles to accelerate dynamic graph processing ***-based dynamic graph processing systems mainly address two challenges:maintaining the graph data when updates occur(i.e.,graph updating)and producing analytics results in time(i.e.,graph computing).In this paper,we survey GPU-based dynamic graph processing systems and review their methods on addressing both graph updating and graph *** comprehensively discuss existing dynamic graph processing systems on GPUs,we first introduce the terminologies of dynamic graph processing and then develop a taxonomy to describe the methods employed for graph updating and graph *** addition,we discuss the challenges and future research directions of dynamic graph processing on GPUs.

关键词： dynamic graphs graph processing graph algorithms GPUs

来源：评论

学校读者我要写书评

暂无评论

ControlVideo: conditional control for one-shot text-driven video editing and beyond

引用

science China(Information sciences) 2025年第3期68卷 150-162页

作者： Min ZHAO Rongzhen WANG Fan BAO Chongxuan LI Jun ZHU Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML CenterTsinghua Laboratory of Brain and Intelligence Lab Tsinghua University ShengShu Technology Gaoling School of Artificial Intelligence Renmin University of China Beijing Key Laboratory of Big Data Management and Analysis Methods Pazhou Laboratory (Huangpu)

This paper presents ControlVideo for text-driven video editing — generating a video that aligns with a given text while preserving the structure of the source video. Building on a pre-trained text-to-image diffusion model, ControlVideo enhances the fidelity and temporal consistency by incorporating additional conditions(such as edge maps), and fine-tuning the key-frame and temporal attention on the source video-text pair via an in-depth exploration of the design space. Extensive experimental results demonstrate that ControlVideo outperforms various competitive baselines by delivering videos that exhibit high fidelity w.r.t. the source content, and temporal consistency, all while aligning with the text. By incorporating low-rank adaptation layers into the model before training, ControlVideo is further empowered to generate videos that align seamlessly with reference images. More importantly, ControlVideo can be readily extended to the more challenging task of long video editing(e.g., with hundreds of frames), where maintaining long-range temporal consistency is crucial. To achieve this, we propose to construct a fused ControlVideo by applying basic ControlVideo to overlapping short video segments and key frame videos and then merging them by pre-defined weight functions. Empirical results validate its capability to create videos across 140 frames, which is approximately 5.83 to 17.5 times more than what previous studies achieved. The code is available at https://***/thu-ml/controlvideo.

关键词： diffusion models controllable generation text-driven editing video editing long video editing

来源：评论

学校读者我要写书评

暂无评论

SAND: semi-automated adaptive network defense via programmable rule generation and deployment

引用

science China(Information sciences) 2022年第7期65卷 121-138页

作者： Haoyu CHEN Deqing ZOU Hai JIN Shouhuai XU Bin YUAN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing Lab School of Computer Science and TechnologyHuazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabHubei Engineering Research Center on Big Data Security School of Cyber Science and EngineeringHuazhong University of Science and Technology Department of Computer Science University of Colorado at Colorado Springs

Cyber security is dynamic as defenders often need to adapt their defense postures. The state-ofthe-art is that the adaptation of network defense is done manually(i.e., tedious and error-prone). The ideal solution is to automate adaptive network defense, which is however a difficult problem. As a first step towards automation, we propose investigating how to attain semi-automated adaptive network defense(SAND). We propose an approach extending the architecture of software-defined networking, which is centered on providing defenders with the capability to program the generation and deployment of dynamic defense rules enforced by network defense tools. We present the design and implementation of SAND, as well as the evaluation of the prototype implementation. Experimental results show that SAND can achieve agile and effective dynamic adaptations of defense rules(less than 15 ms on average for each operation), while only incurring a small performance overhead.

关键词： network defense adaptive defense automated defense programmable defense security services software-defined networking security management

来源：评论

学校读者我要写书评

暂无评论

ReCSA:a dedicated sort accelerator using ReRAM-based content addressable memory

引用

Frontiers of computer science 2023年第2期17卷 1-13页

作者： Huize LI Hai JIN Long ZHENG Yu HUANG Xiaofei LIAO National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabClusters and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China

With the increasing amount of data,there is an urgent need for efficient sorting algorithms to process large data *** sorting algorithms have attracted much attention because they can take advantage of different hardware's *** the traditional hardware sort accelerators suffer“memory wall”problems since their multiple rounds of data transmission between the memory and the *** this paper,we utilize the in-situ processing ability of the ReRAM crossbar to design a new ReCAM array that can process the matrix-vector multiplication operation and the vector-scalar comparison in the same array *** this designed ReCAM array,we present ReCSA,which is the first dedicated ReCAM-based sort *** hardware designs,we also develop algorithms to maximize memory utilization and minimize memory exchanges to improve sorting *** sorting algorithm in ReCSA can process various data types,such as integer,float,double,and *** also present experiments to evaluate the performance and energy efficiency against the state-of-the-art sort *** experimental results show that ReCSA has 90.92×,46.13×,27.38×,84.57×,and 3.36×speedups against CPU-,GPU-,FPGA-,NDP-,and PIM-based platforms when processing numeric data *** also has 24.82×,32.94×,and 18.22×performance improvement when processing string data sets compared with CPU-,GPU-,and FPGA-based platforms.

关键词： ReCAM parallel sorting architecture design processing-in-memory

来源：评论

学校读者我要写书评

暂无评论

Grassland Mouse Hole Recognition Model Based on UAV Remote Sensing and Improved YOLOv7

Grassland Mouse Hole Recognition Model Based on UAV Remote S...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Han, Yu Bai, Xiangyu Gao, Xiaochen Cheng, Haoran Zhou, Kexin College of Computer Science Inner Mongolia University Engineering Research Center of Ecological Big Data Ministry of Education Hohhot China School of Computer Science Inner Mongolia University Engineering Research Center of Ecological Big Data Ministry of Education Hohhot China

ISBN: (纸本)9781665410205

As the most widely distributed vegetation type on Earth, grasslands are the second largest ecosystem after forests, and are known as the 'skin of the earth'. However, the frequency of rodent infestation has been increasing year by year in recent years due to climate change, loose soil and other factors. As the current traditional monitoring methods are time-consuming and laborious, while the deep learning method has the advantages of low cost, high efficiency and high accuracy. Therefore, this paper proposes a combination of UAV remote sensing and deep learning methods to monitor grassland mouse hole. First, because there is no publicly available grassland mouse hole dataset, this study used a UAV to capture images to create a grassland mouse hole dataset. Second, an improved YOLOv7 model, YOLOAPM, is proposed with the goal of improving the accuracy of small target recognition. Through ablation and comparison experiments, the validity of the improved model as well as the method of this paper are verified to be improved compared to other models. Finally, in order to facilitate the monitoring task of the researchers, a monitoring system is established and the mouse hole identification of this paper is embedded into the system. © 2024 IEEE.

关键词： Abiotic

来源：评论

学校读者我要写书评

暂无评论

Using analytic hierarchy process to evaluate deep learning for infrared target recognition

引用

Multimedia Tools and Applications 2024年第38期83卷 86229-86245页

作者： Xu, Laixiang Cao, Bingxu Wei, Xinhong Li, Bei Su, Jingfeng Ning, Shiyuan Zhao, Junmin School of Computer and Data Science Henan University of Urban Construction Pingdingshan467036 China School of Information Engineering Luohe Vocational Technology College Henan University of Technology Luohe Institute of Technology Luohe462000 China School of Computer and Data Science Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Pingdingshan467036 China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Henan University of Urban Construction Pingdingshan467036 China Department of Software Information China Electronics Technology Group Corporation 36-th Research Institute Jiaxing314033 China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Research Center of Intelligent Campus Application Engineering of Henan Province Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Henan University of Urban Construction Pingdingshan467036 China

In order to promote the evaluation performance of deep learning infrared automatic target recognition (ATR) algorithms in the complex environment of air-to-air missile research, we proposed an analytic hierarchy process (AHP) evaluation system consisting of the target recognition ability, the generalization recognition ability, the anti-interference ability, the background suppression ability, and the cost metrics ability. According to detailed quantitative analysis and experimental results, we establish probability evaluation models and get their probability values. Compared with traditional evaluation systems, our proposed method implementation is showing high reliability. Similar superior performances are also achieved, such as quick, comprehensive, and scientific. Through the above research, the key technology of deep learning performance evaluation in automatic target recognition has been broken through, which provides some basis and guidance for the analysis of infrared imaging-guided weapon systems. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

P3DC:Reducing DRAM Cache Hit Latency by Hybrid Mappings

引用

Journal of computer science & Technology 2024年第6期39卷 1341-1360页

作者： Ye Chi Ren-Tong Guo Xiao-Fei Liao Hai-Kun Liu Jianhui Yue National Engineering Research Center for Big Data Technology and System Wuhan 430074China Services Computing Technology and System Laboratory Wuhan 430074China Cluster and Grid Computing Laboratory Wuhan 430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China School of Big Data and Internet Shenzhen Technology UniversityShenzhen 518118China Department of Computer Science Michigan Technological UniversityHoughton 49931-1295U.S.A.

Die-stacked dynamic random access memory(DRAM)caches are increasingly advocated to bridge the performance gap between the on-chip cache and the main *** fully realize their potential,it is essential to improve DRAM cache hit rate and lower its cache hit *** order to take advantage of the high hit-rate of set-association and the low hit latency of direct-mapping at the same time,we propose a partial direct-mapped die-stacked DRAM cache called *** design is motivated by a key observation,i.e.,applying a unified mapping policy to different types of blocks cannot achieve a high cache hit rate and low hit latency *** address this problem,P3DC classifies data blocks into leading blocks and following blocks,and places them at static positions and dynamic positions,respectively,in a unified set-associative *** also propose a replacement policy to balance the miss penalty and the temporal locality of different *** addition,P3DC provides a policy to mitigate cache thrashing due to block type *** results demonstrate that P3DC can reduce the cache hit latency by 20.5%while achieving a similar cache hit rate compared with typical set-associative caches.P3DC improves the instructions per cycle(IPC)by up to 66%(12%on average)compared with the state-of-the-art direct-mapped cache—BEAR,and by up to 19%(6%on average)compared with the tag-data decoupled set-associative cache—DEC-A8.

关键词： die-stacked dynamic random access memory(DRAM) cache set-associative direct-mapped hit latency

来源：评论

学校读者我要写书评

暂无评论

Distributed Truss Computation in Dynamic Graphs

引用

Tsinghua science and Technology 2023年第5期28卷 873-887页

作者： Ziwei Mo Qi Luo Dongxiao Yu Hao Sheng Jiguo Yu Xiuzhen Cheng School of Computer Science and Technology Shandong UniversityQingdao 266200China State Key Laboratory of Software Development Environment School of Computer Science and Engineering and the Beijing Advanced Innovation Center for Big Data and Brain ComputingBeihang UniversityBeijing 100191China Big Data Institute Qilu University of Technology(Shandong Academy of Sciences)Jinan 250353China

Large-scale graphs usually exhibit global sparsity with local cohesiveness,and mining the representative cohesive subgraphs is a fundamental problem in graph *** k-truss is one of the most commonly studied cohesive subgraphs,in which each edge is formed in at least k 2 triangles.A critical issue in mining a k-truss lies in the computation of the trussness of each edge,which is the maximum value of k that an edge can be in a *** works mostly focus on truss computation in static graphs by sequential ***,the graphs are constantly changing dynamically in the real *** study distributed truss computation in dynamic graphs in this *** particular,we compute the trussness of edges based on the local nature of the k-truss in a synchronized node-centric distributed *** decomposing the trussness of edges by relying only on local topological information is possible with the proposed distributed decomposition ***,the distributed maintenance algorithm only needs to update a small amount of dynamic information to complete the *** experiments have been conducted to show the scalability and efficiency of the proposed algorithm.

关键词： distributed algorithm dynamic graph graph mining cohesive subgraph k-truss

来源：评论

学校读者我要写书评

暂无评论

DeepKet- Quantum Space-Efficient Word Embedding Layer for Steganalysis 3

DeepKet- Quantum Space-Efficient Word Embedding Layer for St...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, aiIoT 2024

作者： Roshan Ahmed, N. Shridevi, S. Vellore Institute of Technology School of Computer Science and Engineering Chennai India Vellore Institute of Technology Center for Advanced Data Science Chennai India

ISBN: (纸本)9798350372120

Text-based Statistical steganography is one of the most non-human detectable methods of embedding hidden messages in plain text format which is useful in concealing information. Steganalysis is its counter, the process of detecting if a text has any encrypted data in it. This paper applies quantum computing to create DeepKet Embedding, which optimizes the space requirements for word embeddings similar to Word2Vec. DeepKet is benchmarked against existing embedding layers and a significant size reduction is achieved while maintaining accuracy for steganalysis. © 2024 IEEE.

关键词： Embeddings

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：