2022
DOI: 10.1016/j.neucom.2022.04.043
|View full text |Cite
|
Sign up to set email alerts
|

TRAT: Tracking by attention using spatio-temporal features

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 17 publications
(1 citation statement)
references
References 29 publications
0
1
0
Order By: Relevance
“…Extracting spatial and temporal information from different sequences is another approach many researchers use to estimate the target location based on the variation of target state across multiple frames. TRAT (tracking by attention) aggregates spatial and temporal features extracted from different CNNs using local channel correlation to enhance the prediction of tracked targets [46]. An existing work learned spatial correlation filters from temporal information of previous frames to improve target motion prediction [47].…”
Section: Related Workmentioning
confidence: 99%
“…Extracting spatial and temporal information from different sequences is another approach many researchers use to estimate the target location based on the variation of target state across multiple frames. TRAT (tracking by attention) aggregates spatial and temporal features extracted from different CNNs using local channel correlation to enhance the prediction of tracked targets [46]. An existing work learned spatial correlation filters from temporal information of previous frames to improve target motion prediction [47].…”
Section: Related Workmentioning
confidence: 99%