作者:
Ismail, LeilaWaseem, Muhammad DanishLab
School of Computing and Information Systems Faculty of Engineering and Information Technology The University of Melbourne Australia Research Laboratory
Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates National Water and Energy Center
United Arab Emirates University United Arab Emirates
The outbreak of the COVID-19 pandemic revealed the criticality of timely intervention in a situation exacerbated by a shortage in medical staff and equipment. Pain-level screening is the initial step toward identifyin...
详细信息
With advancements in AI infrastructure and Trusted Execution Environment (TEE) technology, Federated Learning as a Service (FLaaS) through Jointcloudcomputing (JCC) is promising to break through the resource constrai...
详细信息
GPS trajectories are the essential foundations for many trajectory-based applications. Most applications require a large number of high sample rate trajectories to achieve a good performance. However, many real-life t...
GPS trajectories are the essential foundations for many trajectory-based applications. Most applications require a large number of high sample rate trajectories to achieve a good performance. However, many real-life trajectories are collected with low sample rate due to energy concern or other constraints. We study the task of trajectory recovery in this paper as a means to increase the sample rate of low sample trajectories. Most existing works on trajectory recovery follow a sequence-to-sequence diagram, with an encoder to encode a trajectory and a decoder to recover real GPS points in the trajectory. However, these works ignore the topology of road network and only use grid information or raw GPS points as input. Therefore, the encoder model is not able to capture rich spatial information of the GPS points along the trajectory, making the prediction less accurate and less spatial consistent. In this paper, we propose a road network enhanced transformer-based framework, namely RNTrajRec, for trajectory recovery. RNTrajRec first uses a graph model, namely GridGNN, to learn the embedding features of each road segment. It next develops a spatial-temporal transformer model, namely GPSFormer, to learn rich spatial and temporal features along with a Sub-Graph Generation module to capture the spatial features for each GPS point in the trajectory. It finally forwards the outputs of encoder model to a multi-task decoder model to recover the missing GPS points. Extensive experiments based on three large-scale real-life trajectory datasets confirm the effectiveness of our approach.
Current sketch extraction methods either require extensive training or fail to capture a wide range of artistic styles, limiting their practical applicability and versatility. We introduce Mixture-of-Self-Attention (M...
详细信息
The paper describes the design and implementation of a heuristic fuzzy controller for traffic management in urban areas. The controller uses expert knowledge for the derivation of its fuzzy rules. The proposed control...
详细信息
In complex industrial process monitoring, prevalent challenges include high dimensionality, extensive redundancies, and dynamic characteristics. In this paper, we propose an Improved Dynamic Latent Variable-Neighborho...
详细信息
ISBN:
(数字)9798350368604
ISBN:
(纸本)9798350368611
In complex industrial process monitoring, prevalent challenges include high dimensionality, extensive redundancies, and dynamic characteristics. In this paper, we propose an Improved Dynamic Latent Variable-Neighborhood Preserving Embedding (DLV -NPE) algorithm specifically designed to tackle these issues. The methodology begins with the implementation of a variance-covariance feature selection method to minimize redundancies among monitoring variables. This is followed using a dynamic latent variable algorithm to extract dynamic regression properties from the selected variables. Subsequently, the NPE algorithm is employed to preserve the residuals of high-dimensional dynamic latent variables and the high-dimensional residuals of selected variables, thereby preserving the integrity of the low-dimensional manifold structure. Finally, Bayesian inference is applied to develop comprehensive monitoring indicators. The efficacy of the DL V -NPE algorithm is validated through its application to the Tennessee Eastman (TE) process, where it demonstrates superior fault detection capabilities compared to other algorithms.
GAN inversion is indispensable for applying the powerful editability of GAN to real images. However, existing methods invert video frames individually often leading to undesired inconsistent results over time. In this...
GAN inversion is indispensable for applying the powerful editability of GAN to real images. However, existing methods invert video frames individually often leading to undesired inconsistent results over time. In this paper, we propose a unified recurrent framework, named Recurrent vIdeo GAN Inversion and eDiting (RIGID), to explicitly and simultaneously enforce temporally coherent GAN inversion and facial editing of real videos. Our approach models the temporal relations between current and previous frames from three aspects. To enable a faithful real video reconstruction, we first maximize the inversion fidelity and consistency by learning a temporal compensated latent code. Second, we observe incoherent noises lie in the high-frequency domain that can be disentangled from the latent space. Third, to remove the inconsistency after attribute manipulation, we propose an in-between frame composition constraint such that the arbitrary frame must be a direct composite of its neighboring frames. Our unified framework learns the inherent coherence between input frames in an end-to-end manner, and therefore it is agnostic to a specific attribute and can be applied to arbitrary editing of the same video without re-training. Extensive experiments demonstrate that RIGID outperforms state-of-the-art methods qualitatively and quantitatively in both inversion and editing tasks. The deliverables can be found in https://***/RIGID.
Relevance search is to find a list of entities in a knowledge graph (KG), which are associative to a query entity. However, many entities are not linked in KG but are actually associated by user interactions. To this ...
Relevance search is to find a list of entities in a knowledge graph (KG), which are associative to a query entity. However, many entities are not linked in KG but are actually associated by user interactions. To this end, we propose a joint weighting function to evaluate the entity associations from both KG and user-entity interaction data simultaneously. Upon the subgraph extracted from KG w.r.t the query entity, we obtain the associative entities by calculating their association degrees. Experimental results show that the effectiveness of our method outperforms other competitors.
Node classification is to predict the labels of the unlabeled nodes in a graph, which is useful for various applications of social network and biological information analysis. To measure the uncertainty of structural ...
Node classification is to predict the labels of the unlabeled nodes in a graph, which is useful for various applications of social network and biological information analysis. To measure the uncertainty of structural information, we propose the structural entropy theory based method for graph node classification. First, we calculate the structural entropy of different graph structures, since the smaller the structural entropy, the less the uncertainty of the structural relationship in the graph. Then, we use the minimal structural entropy to determine the uncertainty of graphical structures. Finally, the nodes with similar structural relationships in the graph are classified. Experimental results show that our method outperforms some state-of-the-art competitors.
The computational inefficiency of spiking neural networks (SNNs) is primarily due to the sequential updates of membrane potential, which becomes more pronounced during extended encoding periods compared to artificial ...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
The computational inefficiency of spiking neural networks (SNNs) is primarily due to the sequential updates of membrane potential, which becomes more pronounced during extended encoding periods compared to artificial neural networks (ANNs). This highlights the need to parallelize SNN computations effectively to leverage available hardware parallelism. To address this, we propose Membrane Potential Estimation Parallel Spiking Neurons (MPE-PSN), a parallel computation method for spiking neurons that enhances computational efficiency by enabling parallel processing while preserving the intrinsic dynamic characteristics of SNNs. Our approach exhibits promise for enhancing computational efficiency, particularly under conditions of elevated neuron density. Empirical experiments demonstrate that our method achieves state-of-the-art (SOTA) accuracy and efficiency on neuromorphic datasets. Codes are available at https://***/chrazqee/MPE-PSN.
暂无评论