Anticipating human actions by correlating past with the future with Jaccard similarity measures

Page view(s)
24
Checked on Dec 04, 2022
Anticipating human actions by correlating past with the future with Jaccard similarity measures
Title:
Anticipating human actions by correlating past with the future with Jaccard similarity measures
Other Titles:
Computer Vision and Pattern Recognition
DOI:
Publication Date:
25 June 2021
Citation:
3
Abstract:
We propose a framework for early action recognition and anticipation by correlating past features with the future using three novel similarity measures called Jaccard vector similarity, Jaccard cross-correlation and Jaccard Frobenius inner product over covariances. Using these combinations of novel losses and using our framework, we obtain state-of-the-art results for early action recognition in UCF101 and JHMDB datasets by obtaining 91.7 % and 83.5 % accuracy respectively for an observation percentage of 20. Similarly, we obtain state-of-the-art results for Epic-Kitchen55 and Breakfast datasets for action anticipation by obtaining 20.35 and 41.8 top-1 accuracy respectively.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Research Foundation, Singapore - AI Singapore Programme
Grant Reference no. : AISG Award No: AISG-RP-2019-010
Description:
ISBN:
NA
Files uploaded: