Robust graph regularization nonnegative matrix factorization for link prediction in attributed networks

Nasiri, Elahe; Berahmand, Kamal; Li, Yuefeng

doi:10.1007/s11042-022-12943-8

Cited by 70 publications

(20 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, this work can be extended to the various fuzzy numbers such as hexagonal, pentagonal and type-2 fuzzy set, q -rung orthopair fuzzy set to examine the suitable ventilators for COVID patients, where this world faced a shortage of ventilators during the COVID pandemic and also in various disciplines that are impacted by the COVID pandemic. Moreover, the bio-inspired algorithms [44] , [45] and clustering [46] , [47] , [48] , [49] concepts will be incorporated in the fuzzy MCDM methods.…”

Section: Discussionmentioning

confidence: 99%

Intuitionistic fuzzy MAUT-BW Delphi method for medication service robot selection during COVID-19

Devi

Felix

Narayanamoorthy

et al. 2022

Operations Research Perspectives

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Intuitionistic fuzzy MAUT-BW Delphi method for medication service robot selection during COVID-19

Devi

Felix

Narayanamoorthy

et al. 2022

Operations Research Perspectives

View full text Add to dashboard Cite

“…SCNN Shou et al (2016) adopts the C3D network as a binary classifier for anchor evaluation. RGNMF- AN Nasiri et al (2022) make a use of a combination of attributed and topological information in tandem to solve Link prediction. TURN Gao et al (2017) divide the video into equal length elements and do temporal regression to adjust the action boundaries.…”

Section: Related Workmentioning

confidence: 99%

Faster Learning of Temporal Action Proposal via Sparse Multilevel Boundary Generator

Song¹,

Zhang²,

Hu³

et al. 2023

Preprint

View full text Add to dashboard Cite

Temporal action localization in videos presents significant challenges in the field of computer vision. While the boundary-sensitive method has been widely adopted, its limitations include incomplete use of intermediate and global information, as well as an inefficient proposal feature generator. To address these challenges, we propose a novel framework, Sparse Multilevel Boundary Generator (SMBG), which enhances the boundary-sensitive method with boundary classification and action completeness regression. SMBG features a multi-level boundary module that enables faster processing by gathering boundary information at different lengths. Additionally, we introduce a sparse extraction confidence head that distinguishes information inside and outside the action, further optimizing the proposal feature generator. To improve the synergy between multiple branches and balance positive and negative samples, we propose a global guidance loss. Our method is evaluated on two popular benchmarks, ActivityNet-1.3 and THUMOS14, and is shown to achieve state-of-the-art performance, with a better inference speed (2.47xBSN++, 2.12xDBG). These results demonstrate that SMBG provides a more efficient and simple solution for generating temporal action proposals. Our proposed framework has the potential to advance the field of computer vision and enhance the accuracy and speed of temporal action localization in video analysis.The code and models are made available at https: //github.com/zhouyang-001/SMBG-for-temporal-action-proposal.

show abstract

“…Linearization approaches can be also regarded as shape-preserving dimensionality-reducing methods [ 23 ]. In such methods, the inverse sensor characteristic is mapped into a polygonal shape, by using either distance minimizing embedding technique, or, whenever permissible, by range and accuracy requirements—a non-negative matrix factorization technique, as suggested in [ 24 ].…”

Section: Introduction (And Motivation)mentioning

confidence: 99%

Linear Interval Approximation of Sensor Characteristics with Inflection Points

Marinov

Nikolov

Dimitrov

et al. 2023

Sensors

View full text Add to dashboard Cite

The popularity of smart sensors and the Internet of Things (IoT) is growing in various fields and applications. Both collect and transfer data to networks. However, due to limited resources, deploying IoT in real-world applications can be challenging. Most of the algorithmic solutions proposed so far to address these challenges were based on linear interval approximations and were developed for resource-constrained microcontroller architectures, i.e., they need buffering of the sensor data and either have a runtime dependency on the segment length or require the sensor inverse response to be analytically known in advance. Our present work proposed a new algorithm for the piecewise-linear approximation of differentiable sensor characteristics with varying algebraic curvature, maintaining the low fixed computational complexity as well as reduced memory requirements, as demonstrated in a test concerning the linearization of the inverse sensor characteristic of type K thermocouple. As before, our error-minimization approach solved the two problems of finding the inverse sensor characteristic and its linearization simultaneously while minimizing the number of points needed to support the characteristic.

show abstract

Robust graph regularization nonnegative matrix factorization for link prediction in attributed networks

Cited by 70 publications

References 62 publications

Intuitionistic fuzzy MAUT-BW Delphi method for medication service robot selection during COVID-19

Intuitionistic fuzzy MAUT-BW Delphi method for medication service robot selection during COVID-19

Faster Learning of Temporal Action Proposal via Sparse Multilevel Boundary Generator

Linear Interval Approximation of Sensor Characteristics with Inflection Points

Contact Info

Product

Resources

About