arXiv subjects

Ali Karami

Publications and source records attributed to Ali Karami.

5 recordsLinked to original sources

arXiv2024

Graph-Jigsaw Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection

Skeleton-based video anomaly detection (SVAD) is a crucial task in computer vision. Accurately identifying abnormal patterns or events enables operators to promptly detect suspicious activities, thereby enhancing safety. Achieving this demands a comprehensive understanding of human motions, both at body and region levels, while also accounting for the wide variations of performing a single action. However, existing studies fail to simultaneously address these crucial properties. This paper introduces a novel, practical and lightweight framework, namely Graph-Jigsaw Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection (GiCiSAD) to overcome the challenges associated with SVAD. GiCiSAD consists of three novel modules: the Graph Attention-based Forecasting module to capture the spatio-temporal dependencies inherent in the data, the Graph-level Jigsaw Puzzle Maker module to distinguish subtle region-level discrepancies between normal and abnormal motions, and the Graph-based Conditional Diffusion model to generate a wide spectrum of human motions. Extensive experiments on four widely used skeleton-based video datasets show that GiCiSAD outperforms existing methods with significantly fewer training parameters, establishing it as the new state-of-the-art.

cs.CV↗

arXiv2023

NERFBK: A High-Quality Benchmark for NERF-Based 3D Reconstruction

This paper introduces a new real and synthetic dataset called NeRFBK specifically designed for testing and comparing NeRF-based 3D reconstruction algorithms. High-quality 3D reconstruction has significant potential in various fields, and advancements in image-based algorithms make it essential to evaluate new advanced techniques. However, gathering diverse data with precise ground truth is challenging and may not encompass all relevant applications. The NeRFBK dataset addresses this issue by providing multi-scale, indoor and outdoor datasets with high-resolution images and videos and camera parameters for testing and comparing NeRF-based algorithms. This paper presents the design and creation of the NeRFBK benchmark, various examples and application scenarios, and highlights its potential for advancing the field of 3D reconstruction.

cs.CV↗

arXiv2023

Graph Anomaly Detection in Time Series: A Survey

With the recent advances in technology, a wide range of systems continue to collect a large amount of data over time and thus generate time series. Time-Series Anomaly Detection (TSAD) is an important task in various time-series applications such as e-commerce, cybersecurity, vehicle maintenance, and healthcare monitoring. However, this task is very challenging as it requires considering both the intra-variable dependency (relationships within a variable over time) and the inter-variable dependency (relationships between multiple variables) existing in time-series data. Recent graph-based approaches have made impressive progress in tackling the challenges of this field. In this survey, we conduct a comprehensive and up-to-date review of TSAD using graphs, referred to as G-TSAD. First, we explore the significant potential of graph representation for time-series data and and its contributions to facilitating anomaly detection. Then, we review state-of-the-art graph anomaly detection techniques, mostly leveraging deep learning architectures, in the context of time series. For each method, we discuss its strengths, limitations, and the specific applications where it excels. Finally, we address both the technical and application challenges currently facing the field, and suggest potential future directions for advancing research and improving practical outcomes.

cs.LG↗

arXiv2018

All nearest neighbor calculation based on Delaunay graphs

When we have two data sets and want to find the nearest neighbour of each point in the first dataset among points in the second one, we need the all nearest neighbour operator. This is an operator in spatial databases that has many application in different fields such as GIS and VLSI circuit design. Existing algorithms for calculating this operator assume that there is no pre computation on these data sets. These algorithms has o(n*m*d) time complexity where n and m are the number of points in two data sets and d is the dimension of data points. With assumption of some pre computation on data sets algorithms with lower time complexity can be obtained. One of the most common pre computation on spatial data is Delaunay graphs. In the Delaunay graph of a data set each point is linked to its nearest neighbours. In this paper, we introduce an algorithm for computing the all nearest neighbour operator on spatial data sets based on their Delaunay graphs. The performance of this algorithm is compared with one of the best existing algorithms for computing ANN operator in terms of CPU time and the number of IOs. The experimental results show that this algorithm has better performance than the other.

cs.DB↗

arXiv2011

A Concurrency Control Method Based on Commitment Ordering in Mobile Databases

Disconnection of mobile clients from server, in an unclear time and for an unknown duration, due to mobility of mobile clients, is the most important challenges for concurrency control in mobile database with client-server model. Applying pessimistic common classic methods of concurrency control (like 2pl) in mobile database leads to long duration blocking and increasing waiting time of transactions. Because of high rate of aborting transactions, optimistic methods aren`t appropriate in mobile database. In this article, OPCOT concurrency control algorithm is introduced based on optimistic concurrency control method. Reducing communications between mobile client and server, decreasing blocking rate and deadlock of transactions, and increasing concurrency degree are the most important motivation of using optimistic method as the basis method of OPCOT algorithm. To reduce abortion rate of transactions, in execution time of transactions` operators a timestamp is assigned to them. In other to checking commitment ordering property of scheduler, the assigned timestamp is used in server on time of commitment. In this article, serializability of OPCOT algorithm scheduler has been proved by using serializability graph. Results of evaluating simulation show that OPCOT algorithm decreases abortion rate and waiting time of transactions in compare to 2pl and optimistic algorithms.

cs.DB↗