Mining human movement evolution for complex action recognition

Yi, Yang; Yang, Cheng; Xu, Chuping

doi:10.1016/j.eswa.2017.02.020

Cited by 16 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the obtained results, it is observed that the proposed approach is more accurate compared to El Ouadrhiri et al [33] and Zhang et al [72]. While the results reported in Yi et al [73] remain better. Results shown in Fig.…”

Section: Resultsmentioning

confidence: 68%

“…where k is the rank in the sequence of retrieved videos, n is the number of retrieved videos, P(k) is the precision at cut-off k in the list, rel(k) is an indicator function equaling 1, if the video at rank k is a relevant video, zero otherwise. Using this dataset, our approach is compared to different state-of-the-art methods, notably El Ouadrhiri et al [33], Zhang et al [72] and Yi et al [73]. The MAP achieved on this dataset is shown in Table 2, the detailed precision by class is presented in Fig.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A distributed Content-Based Video Retrieval system for large datasets

Saoudi

Andaloussi

2021

J Big Data

View full text Add to dashboard Cite

With the rapid growth in the amount of video data, efficient video indexing and retrieval methods have become one of the most critical challenges in multimedia management. For this purpose, Content-Based Video Retrieval (CBVR) is nowadays an active area of research. In this article, a CBVR system providing similar videos from a large multimedia dataset based on query video has been proposed. This approach uses vector motion-based signatures to describe the visual content and uses machine learning techniques to extract key frames for rapid browsing and efficient video indexing. The proposed method has been implemented on both single machine and real-time distributed cluster to evaluate the real-time performance aspect, especially when the number and size of videos are large. Experiments were performed using various benchmark action and activity recognition datasets and the results reveal the effectiveness of the proposed method in both accuracy and processing time compared to previous studies.

show abstract

Section: Resultsmentioning

confidence: 68%

Section: Resultsmentioning

confidence: 99%

A distributed Content-Based Video Retrieval system for large datasets

Saoudi

Andaloussi

2021

J Big Data

View full text Add to dashboard Cite

show abstract

“…The recognition accuracy of the ARSR was contrasted with that of other spare representation -based recognition methods for human activities, namely L2-regularization [4], Laplacianregularization [6], Hessian-regularization [9], L1regularization [2] and adaptive L1-regularization [8]. The overall recognition rate of the 8 types of activities in the dataset reached 91.88%.…”

Section: Resultsmentioning

confidence: 99%

“…Much research has been done on human activity recognition from both single-and hierarchical-layer approaches [8,9]. The single-layer methods directly classify human activities from video data by representing activities as space-time features (e.g.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Lp-Norm Regularized Sparse Representation for Human Activity Recognition in Coal Mines

Wang¹,

Geng²

2020

JESA

View full text Add to dashboard Cite

This paper aims to overcome the lack of in-depth exploration into the intrinsic geometry of human activities. For this purpose, a generalized adaptive Lp-norm regularized sparse representation (ARSR) approach was proposed for human activity recognition, which preserves the model adaptability through the adaptive Lp-norm regularization. In essence, the proposed method applies sparse representation to human activity recognition, turning it into a new optimization problem. In addition, the problem was solved by the iterative-shrinkage-thresholding algorithm. Specifically, the sparse representation learned by the ARSR algorithm was introduced into the support vector machine (SVM) classifier. Then, several experiments were conducted on coal-mining datasets for human activity identification. The experimental results revealed that the proposed algorithm is superior to the current sparse representation algorithms like the standard L1-norm regularized sparse representation algorithm. The research findings shed new light on the human activity recognition in coal mines.

show abstract

“…E reflects the dependent relation between BS, which is related with human mobility between areas. Considering the realistic complex environment of urban areas, we assume the BS dependence is symmetric as in [25]. We define the link of the graph as: If a user can reach one BS from the other during limited time Δ t, then we say there is a link between the two BSs.…”

Section: Problem Formulationmentioning

confidence: 99%

Edge Oriented Urban Hotspot Prediction for Human-Centric Internet of Things

Zeng

Xiang

2021

IEEE Access

View full text Add to dashboard Cite

Mobile edge computing works well with the rapid growth of human-centric IoT applications by providing timely and in-situ data caching and processing. Edge oriented urban hotspot prediction is to predict the high traffic regions in case to provide basis for further deployment and replenishment of edge servers. Most of the existing hotspot analysis work is not well suited for human-centric IoT application scenarios especially for large-scale urban city areas. Instead, in this paper we propose edge-oriented hotspot prediction scheme based on information Interactive Graph Attention Networks (I-GAN) for urban city within the human-centric IoT and MEC application scenarios. I-GAN makes reasoning on the user service needs by learning the interactive relations of multifaceted human-centric factors: including online human behavior and offline crowd flow through graph attention networks. On the other hand, I-GAN makes representation of urban-scale edge service capability by graph embeddings through inductive learning with distributed multi-layer graph convolutions. Based on it, I-GAN makes matching between them and then predicts the edge-oriented hotspots with time variance. The performance evaluations are based on realistic dataset of a southern city of China provided by China Unicom. I-GAN is compared with the other related hotspot analysis schemes. The results show that I-GAN is with much better prediction accuracy with multiple time dimensions.

show abstract

Mining human movement evolution for complex action recognition

Cited by 16 publications

References 26 publications

A distributed Content-Based Video Retrieval system for large datasets

A distributed Content-Based Video Retrieval system for large datasets

Adaptive Lp-Norm Regularized Sparse Representation for Human Activity Recognition in Coal Mines

Edge Oriented Urban Hotspot Prediction for Human-Centric Internet of Things

Contact Info

Product

Resources

About