Representation for action recognition with motion vector termed as: SDQIO

Islam, M. Shujah; Bakhat, Khush; Iqbal, Mansoor; Khan, Rahmatullah; Ye, Zhongfu; Islam, Muhammad

doi:10.1016/j.eswa.2022.118406

Cited by 12 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We presume that the greater a node's influence on its neighbour, the greater its likelihood of being visited by that neighbour. According to the quantitative definition of influence between two entities provided in [26], which is the following:…”

Section: Mutual Influence Featurementioning

confidence: 99%

“…The parameters maximise the probability that is calculated by link prediction algorithms using data that has been actually observed. Several state-of-the-art methods for dimension reduction in feature extraction and selection for feature detection are presented in [24][25][26][27]. For instance, authors [28] established a non-asymptotic risk bound for the maximum likelihood estimator of network connection probabilities.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Link prediction grounded upon complex networks based model, based on MJMI-RW

Bakhat¹,

Kifayat²,

Islam

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Link prediction is the process of predicting the connection probability between two nodes based on observable network data, such as network structural topology and node properties. Despite the fact that traditional similarity-based methods are basic and effective, their generalisation performance varies greatly across networks. In this paper, we propose a novel link prediction approach, MJMI-RW, based on the Maxwell Jüttner distribution endowed by the Mutual Information, which recovers the probability of a node's connection by applying node characteristics to a system with less computation. Initially, the method investigates a comprehensive node feature representation by combining diverse structural topology information with node importance properties through feature construction and selection. The selected node features are then fed into a supervised learning task that solves the features matrix using the node features as input. The enhancements of MJMI-RW in terms of the average area under the curve and the precision of state-of-the-art algorithms compared to the finest baseline networks when compared to baseline methods. The limitation of MJMI-RW is its minimal computational complexity feature construction and substitution of complex features with semantic node attributes. Moreover, since inductive matrix completion is a supervised learning task in which the underlying low-rank matrix can be solved by representative nodes instead of all their nodes, it offers a potential link prediction solution for large-scale networks.

show abstract

Section: Mutual Influence Featurementioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Link prediction grounded upon complex networks based model, based on MJMI-RW

Bakhat¹,

Kifayat²,

Islam

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Knowing the amount of uniquely human behavior in each frame is a major highlight, and the data gleaned is a boon to detecting dangerous or falling actions [1]. It's useful for (a) variety of things, including (but not limited to) (b) ambient assisted living [2], (c) medical activities [3], and many more [4]. Due to its value and adaptability in the field of health care, human pose estimation in particular has grown increasingly popular because of the availability of modern activity recognition sensors.…”

Section: Introductionmentioning

confidence: 99%

Employing FGP-3D, a Fully Gated and Anchored Methodology, to Identify Skeleton-Based Action Recognition

et al. 2023

Self Cite

View full text Add to dashboard Cite

Recent years have seen an explosion in interest in and development of action recognition based on skeletal data. Contemporary methods using fully gated units can successfully extract characteristics from human skeletons by relying on the human topology that has been predefined. Despite advancements, fully gated unit-based techniques have trouble generalizing to other domains, particularly when dealing with various human topological structures. In this context, we introduce FGP-3D, a novel skeleton-based action recognition technique that can generalize across datasets while being effective at learning spatiotemporal features from human skeleton sequences. This is accomplished via a multi-head attention technique to learn an ideal dependence feature matrix from the uniform distribution. We next re-evaluate state-of-the-art techniques as well as the suggested novel descriptor FGP-3D in order to examine the cross-domain generalizability of skeleton-based action recognition in real-world video skeleton statistics. After being applied to commonly used action categorization datasets, experimental results demonstrate that the proposed FGP-3D, with pre-training, generalizes well and outperforms the state-of-the-art.

show abstract