2019
DOI: 10.1016/j.image.2019.02.012
|View full text |Cite
|
Sign up to set email alerts
|

Spatio-temporal attention mechanisms based model for collective activity recognition

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
33
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 22 publications
(33 citation statements)
references
References 4 publications
0
33
0
Order By: Relevance
“…Lu et al [91] proposed a two-level attention mechanism for group activity recognition. The first individual-level attention is guided by pose features to control the hidden state at each time step.…”
Section: Attention Modelingmentioning
confidence: 99%
“…Lu et al [91] proposed a two-level attention mechanism for group activity recognition. The first individual-level attention is guided by pose features to control the hidden state at each time step.…”
Section: Attention Modelingmentioning
confidence: 99%
“…Group/Collective Activity Recognition: Before the advent of powerful deep learning methods, devising effective hand-crafted features for group activity recognition has been extensively studied, which commonly represent the sequence images with a number of predefined descriptors [6,7,8,9,10,11,12,53]. Lan et al [6] proposed a latent variable framework to jointly model the contextual information of group-person and person-person interaction.…”
Section: Related Workmentioning
confidence: 99%
“…[1]. In the literature of activity recognition, most of the works build activity model based on the temporal spatio characters [2,3], which faces the miscalculation with the similar activities because of the few features. Another research bottleneck is the poor robustness of the activity model which is difficult to handle the data missing, noisy data, habit changing, and so on [4,5].…”
Section: Introductionmentioning
confidence: 99%