检索结果-内蒙古大学图书馆

Zero-Shot Video Event Detection With High-Order Semantic Concept Discovery and Matching

ieee TRANSACTIONS ON MULTIMEDIA 2022年 24卷 1896-1908页

作者： Jin, Yang Jiang, Wenhao Yang, Yi Mu, Yadong Peking Univ Ctr Big Data Res Beijing 100871 Peoples R China Tencent AI Lab Shenzhen 518001 Peoples R China Univ Technol Sydney UTS Fac Engn & Informat Technol Ultimo NSW 2007 Australia Peking Univ Wangxuan Inst Comp Technol Beijing 100871 Peoples R China

Multimedia event detection aims to precisely retrieve videos that contain complex semantic events from a large pool. This work addresses this task under a zero-shot setting, where only brief event-specific textural information (such as event names, a few descriptive sentences, etc.) is known yet none positive video example is provided. Mainstream approaches to tackling this task are middle-level semantic concept-based, where meticulously-crafted concept banks (e.g., LSCOM) are adopted. We argue that these concept banks are still inadequate facing video semantic complexity. Existing semantic concepts are essentially first-order, mainly designed for atomic objects, scenes or human actions, etc. This work advocates the utilization of high-order concepts (such as subject-predicate-object triplets or adjective-object). The main contributions are two-fold. First, we harvest a comprehensive albeit compact high-order concept library through distilling information from three large public datasets (MS-COCO, Visual Genome, and Kinetics-600), mainly related to visual relations and human-object interactions. Secondly, zero-shot events are often only briefly and partially described via textual input. The resultant semantic ambiguity makes the pursuit of the most indicative high-order concepts challenging. We thus design a novel query-expanding scheme that enriches ambiguous event-specific keywords by searching over either large common knowledge bases (e.g., WikiHow) or top-ranked webpages retrieved from modern search engines. This way sets up a more faithful connection between zero-shot events and high-order concepts. To our best knowledge, this is the first work that strives for concept-based video search beyond first-order concepts. Extensive experiments have been conducted on several large video benchmarks (TRECVID 2013, TRECVID 2014, and ActivityNet-1.3). The evaluations clearly demonstrate the superiority of our constructed high-order concept library and its complementarines

关键词： Semantics Event detection visualization Libraries Streaming media Task analysis Feature extraction Multimedia event detection zero-shot learning high-order concept

来源：评论

学校读者我要写书评

暂无评论

ECNR: Efficient Compressive Neural Representation of Time-Varying Volumetric datasets

ECNR: Efficient Compressive Neural Representation of Time-Va...

引用

Pacific (formerly Asia-Pacific APVIS) visualization symposium

作者： Kaiyuan Tang Chaoli Wang University of Notre Dame

ISBN: (数字)9798350393804

ISBN: (纸本)9798350393811

Due to its conceptual simplicity and generality, compressive neural representation has emerged as a promising alternative to traditional compression methods for managing massive volumetric datasets. The current practice of neural compression utilizes a single large multilayer perceptron (MLP) to encode the global volume, incurring slow training and inference. This paper presents an efficient compressive neural representation (ECNR) solution for time-varying data compression, utilizing the Laplacian pyramid for adaptive signal fitting. Following a multiscale structure, we leverage multiple small MLPs at each scale for fitting local content or residual blocks. By assigning similar blocks to the same MLP via size uniformization, we enable balanced parallelization among MLPs to significantly speed up training and inference. Working in concert with the multiscale structure, we tailor a deep compression strategy to compact the resulting model. We show the effectiveness of ECNR with multiple datasets and compare it with state-of-the-art compression methods (mainly SZ3, TTHRESH, and neurcomp). The results position ECNR as a promising solution for volumetric data compression.

关键词： Training Laplace equations Fitting data compression data visualization Multilayer perceptrons

来源：评论

学校读者我要写书评

暂无评论

Analytical system based on Big data for digital transformation in Higher Education 2

Analytical system based on Big Data for digital transformati...

引用

2nd ieee International Conference on Advanced Learning Technologies on Education and Research, ICALTER 2022

作者： Alarcon, Roger Bravo, Jessie Valdivia, Carlos Aquino, Janet Pedro Ruiz Gallo National University Computing and Electronics Department Lambayeque Peru

ISBN: (数字)9781665456968

ISBN: (纸本)9781665456968

Currently higher education institutions are generating a lot of data as a result of their internal processes, but the limiting human capacities for the processing and analysis of large volumes of data cause these institutions to make hasty decisions and without real support, so it is necessary to use computational tools such as analytical systems that allow to speed up decision making based on data. The type of study is mixed and applied with a quasi-experimental design. An analytical system based on eight stages was built, which are: user characterization, business requirements, storage, technological infrastructure, feature engineering, computational processing, visualization and decision making. The analytical system was validated with data from the SQL Server management system of the academic services office and fifteen Excel files from the admission office oriented to academic data in a higher educational institution. The use of various algorithms such as support vector machine, random forest, k nearest neighbours, and neural networks, among others, was applied. The evaluation of the results generated by these algorithms allowed us to identify the support vector machine algorithm with 94.21% accuracy. © 2022 ieee.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

FlashWalker: An In-Storage Accelerator for Graph Random Walks 36

FlashWalker: An In-Storage Accelerator for Graph Random Walk...

引用

36th ieee International Parallel and Distributed Processing symposium (ieee IPDPS)

作者： Niu, Fuping Yue, Jianhui Shen, Jiangqiu Liao, Xiaofei Liu, Haikun Jin, Hai Huazhong Univ Sci & Technol Natl Engn Res Ctr Big Data Technol & Syst Sch Comp Sci & Technol Serv Comp Technol & Syst LabCluster & Grid Comp Wuhan 430074 Peoples R China Michigan Technol Univ Dept Comp Sci Houghton MI 49931 USA

ISBN: (纸本)9781665481069

Graph random walk is widely used in the graph processing as it is a fundamental component in graph analysis, ranging from vertices ranking to the graph embedding. Different from traditional graph processing workload, random walk features massive processing parallelisms and poor graph data reuse, being limited by low I/O efficiency. Prior designs for random walk mitigate slow I/O operations. However, the state-of-the-art random walk processing systems are bounded by slow disk I/O bandwidth, which is confirmed by our experiments with real-world graphs. To address this issue, we propose FlashWalker, an in-storage accelerator for random walk that moves walk updating close to graph data stored in flash memory, by exploiting significant parallelisms inside SSD. Featuring a heterogeneous and parallel processing system, FlashWalker includes a board-level accelerator, channel-level accelerators, and chip-level accelerators. To address challenges posed by the tight resource constraints for processing large-scale graphs, we propose novel designs: storing a few popular subgraphs in accelerators, the pre-walking for dense walks, two optimizations to search the subgraph mapping table, and a subgraph scheduling algorithm. We implement FlashWalker in RTL, showing small circuit area overhead. Our evaluation shows FlashWalker reduces the execution time of random walk algorithms by up to 660.50x, compared with GraphWalker, which is the state-of-the-art system for random walk algorithms.

关键词： random walk graph computing in-storage processing accelerator

来源：评论

学校读者我要写书评

暂无评论

LinkQ: An LLM-Assisted Visual Interface for Knowledge Graph Question-Answering

LinkQ: An LLM-Assisted Visual Interface for Knowledge Graph ...

引用

International Conference on Visualisation, VIS

作者： Harry Li Gabriel Appleby Ashley Suh MIT Lincoln Laboratory Tufts University

ISBN: (数字)9798350354850

ISBN: (纸本)9798350354867

We present LinkQ, a system that leverages a large language model (LLM) to facilitate knowledge graph (KG) query construction through natural language question-answering. Traditional approaches often require detailed knowledge of a graph querying language, limiting the ability for users – even experts – to acquire valuable insights from KGs. LinkQ simplifies this process by implementing a multistep protocol in which the LLM interprets a user’s question, then systematically converts it into a well-formed query. LinkQ helps users iteratively refine any open-ended questions into precise ones, supporting both targeted and exploratory analysis. Further, LinkQ guards against the LLM hallucinating outputs by ensuring users’ questions are only ever answered from ground truth KG data. We demonstrate the efficacy of LinkQ through a qualitative study with five KG practitioners. Our results indicate that practitioners find LinkQ effective for KG question-answering, and desire future LLM-assisted exploratory data analysis systems.

关键词： Analytical models Protocols Limiting data analysis Visual analytics large language models data visualization Knowledge graphs Writing data models

来源：评论

学校读者我要写书评

暂无评论

Dimensionality Reduction for visualization of Hydrogeophysical and Metereological Recordings on a Landslide Zone

Dimensionality Reduction for Visualization of Hydrogeophysic...

引用

ieee International symposium on Geoscience and Remote Sensing (IGARSS)

作者： Apostolos Parasyris Lina Stankovic Vladimir Stankovic Electronic and Electrical Engineering University of Strathclyde Glasgow UK

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

The frequency and intensity of devastating landslides have been increasing worldwide. Timely prediction of slope failure can save lives and protect property. Slope movement is a result of several meteorological and hydrogeophysical variables, such as temperature and moisture content, but this complex relationship is still not well understood. To predict and characterise a slope failure, multiple measurands are usually collected. Since these numerous variables in the predictor set may cause significant increase in complexity, it becomes necessary to use methods that determine the relative importance of measurands that contribute directly to slope failure. To this end, we investigate three methods of visualisation of the feature space and dimensionality reduction, namely Principal Component analysis (PCA), t-distributed Stochastic Neighbor Embedding (t-SNE) and Linear Discriminant analysis (LDA), to analyse a range of surface and subsurface measurements from multiple sensors focusing on five stages of slope movement and then make failure predictions using XGBoost regression by setting as predictors two most important components from the extracted features. The results clearly show that LDA better clusters the data points and distinguishes the five different stages of slope movement, including two failures during the period of study encompassing eight years.

关键词： Dimensionality reduction Temperature measurement Landslides visualization Time series analysis Feature extraction Explosives

来源：评论

学校读者我要写书评

暂无评论

Geomagnetic data Processing

Geomagnetic Data Processing

引用

Progress in Electromagnetic Research symposium (PIERS)

作者： Sheng He Gang Zhang Southwest University of Science and Technology China

ISBN: (数字)9798350375909

ISBN: (纸本)9798350375916

Geodetic electromagnetic methods have wide applications in geophysical exploration, but there are still some challenges for large-scale and complex geodetic electromagnetic data processing and interpretation. This paper introduces a Python-based open-source software library, resistics, which achieves significant optimization of the data processing effect through its application in geodetic electromagnetic data processing. There are many limitations in the traditional methods of geodetic electromagnetic data processing, including problems of data import, correction, noise suppression and model matching. The main functions and features of the resistics library, i.e., multi-threaded processing, efficient data import and pre-processing, and automated parameter optimization, can optimize data processing. These features make the resistics library perform well in large-scale geodetic electromagnetic data processing, and can significantly improve data processing efficiency and accuracy. In order to verify the advantages of the resistics library in geodetic electromagnetic data processing, we selected the geodetic electromagnetic data from the Xian Shui River area for experiments, and processed the data using the resistics library. The results show that, compared with the traditional method, the resistics library can process the data and model matching more quickly and accurately, and improve the accuracy of the data and obtain more reliable results. Not only that, in the process of using the resistics library to process data, it also realizes the visualization of data processing, and can be adjusted and optimized for the measured bad data to get more reliable data. In the processing of the Xian Shui river data, the use of the resistics library can effectively suppress the noise, extract the effective signals, and accurately restore the underground structure.

关键词： visualization Time-frequency analysis Accuracy data processing Libraries Rivers Reliability

来源：评论

学校读者我要写书评

暂无评论

Small or Far Away? Exploiting Deep Super-Resolution and Altitude data for Aerial Animal Surveillance

Small or Far Away? Exploiting Deep Super-Resolution and Alti...

引用

22nd ieee/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Xue, Mowen Greenslade, Theo Mirmehdi, Majid Burghardt, Tilo Univ Bristol Dept Comp Sci Bristol BS8 1UB Avon England

ISBN: (纸本)9781665458245

Visuals captured by high-flying aerial drones are increasingly used to assess biodiversity and animal population dynamics around the globe. Yet, challenging acquisition scenarios and tiny animal depictions in airborne imagery, despite ultra-high resolution cameras, have so far been limiting factors for applying computer vision detectors successfully with high confidence. In this paper, we address the problem for the first time by combining deep object detectors with super-resolution techniques and altitude data. In particular, we show that the integration of a holistic attention network based super-resolution approach and a custom-built altitude data exploitation network into standard recognition pipelines can considerably increase the detection efficacy in real-world settings. We evaluate the system on two public, large aerial-capture animal datasets, SAVMAP and AED. We find that the proposed approach can consistently improve over ablated baselines and the state-of-the-art performance for both datasets. In addition, we provide a systematic analysis of the relationship between animal resolution and detection performance. We conclude that super-resolution and altitude knowledge exploitation techniques can significantly increase benchmarks across settings and, thus, should be used routinely when detecting minutely resolved animals in aerial imagery.

关键词： Computer vision visualization Systematics Animals Surveillance Superresolution Pipelines

来源：评论

学校读者我要写书评

暂无评论

Transparent visualization with Dynamic Shading for 3D Scanned Point Clouds of Cultural Heritage Objects

Transparent Visualization with Dynamic Shading for 3D Scanne...

引用

Pacific (formerly Asia-Pacific APVIS) visualization symposium

作者： Hatsuki Nojiri Satoshi Takatori Kyoko Hasegawa Liang Li R. Michael Feener Keiji Yano Satoshi Tanaka College of Information Science and Engineering Ritsumeikan University School of Information and Telecommunication Engineering Tokai University Center for Southeast Asian Studies Kyoto University College of Letters Area Studies Program Ritsumeikan University

ISBN: (数字)9798331505813

ISBN: (纸本)9798331505820

Three dimensional (3D) scanned point clouds offer an invaluable tool for the digital preservation of cultural heritage, capturing intricate and complex 3D structures. Transparent visualization, i.e., see-through visualization, is essential for effectively understanding these data. However, since 3D scanned point clouds do not include normal vector information, applying shading effects to reveal complex shapes is challenging. In this paper, we present a method for assigning normal vectors to 3D scanned points using a statistical approach based on principal component analysis. To resolve the ambiguity of normal vector orientations, specifically the front or back of local surfaces, we exploit the characteristics of transparent visualization. Each normal vector is oriented toward the viewpoint, enabling consistent shading across all visible points. We then apply dynamic shading by varying the light source position sequentially, which highlights different regions of the visualized object. This approach allows for a shift in focus between surface features and deeper internal structures, enhancing the understanding of the overall structure of complex 3D cultural heritage objects. We demonstrate the effectiveness of dynamic shading through its application to real 3D scanned data of cultural heritage objects with intricate internal structures.

关键词： Point cloud compression Three-dimensional displays Shape data visualization Vectors Cultural differences Digital preservation Principal component analysis Light sources

来源：评论

学校读者我要写书评

暂无评论

Determining Distribution of a Seven-Dimensional Point Cluster with a Novel Hypersphere Method 12

Determining Distribution of a Seven-Dimensional Point Cluste...

引用

12th IFAC symposium on Biological and Medical Systems (BMS)

作者： Davey, Nicolas A. C. Chase, J. Geoffrey Zhou, Cong Murphy, Liam Univ Canterbury Dept Mech Engn Christchurch New Zealand

This paper introduces a novel method for analysing high-dimensional data points called the Most-Distant Uncovered Point (MDUP) hypersphere method. The MDUP method is a binary classification technique that defines equidistant N-dimensional points as unions of hyperspheres. The method iteratively creates hyperspheres at the most distant point within the region of interest until the entire region is covered. Tested on a 7-dimensional space representing feasible and infeasible model parameters for a cardiovascular system model, the MDUP hypersphere method tends to generate a few large spheres away from the boundary and numerous small spheres around the boundary to fill the space. The MDUP method can scale to any dimension, needing only centre points and radii, providing easily interpretable results. It can also identify large continuous regions and capture the general structure with few hyperspheres. Additionally, the method has potential to generate optimising algorithm starting conditions within predefined feasible regions, potentially enhancing model identifiability and optimisation results. Copyright (C) 2024 The Authors. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0/)

关键词： Cardiovascular Hypersphere Dimensionality Parameter Space analysis Visualisation

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：