Predicting the Next Action by Modeling the Abstract Goal

Page view(s)
0
Checked on
Predicting the Next Action by Modeling the Abstract Goal
Title:
Predicting the Next Action by Modeling the Abstract Goal
Journal Title:
Lecture Notes in Computer Science
Keywords:
Publication Date:
03 December 2024
Citation:
Roy, D., & Fernando, B. (2024). Predicting the Next Action by Modeling the Abstract Goal. In Pattern Recognition (pp. 162–177). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-78354-8_11
Abstract:
The problem of predicting human actions from observed videos is an inherently uncertain one. We present an action anticipation model that leverages latent goal information to reduce the uncertainty in future predictions. We develop a latent variable representing goal information called abstract goal which is conditioned on observed sequences of visual features for action anticipation. We design the abstract goal as a distribution whose parameters are estimated using a variational recurrent model. We sample multiple candidates for the next action and use goal consistency criterion to determine the best candidate that follows from the abstract goal. Our method obtains impressive results on the very challenging Epic-Kitchens55 (EK55) and good results in Epic-Kitchens100 (EK100) datasets. Code is available at https://github.com/LAHAproject/Abstract_Goal
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Research Foundation - NRF Fellowship
Grant Reference no. : NRF-NRFF14-2022-0001

This research / project is supported by the National Research Foundation - AI Singapore Programme
Grant Reference no. : AISG2-RP-2020-016

This research / project is supported by the A*STAR - Science and Engineering Research Council (SERC) Central Research Fund
Grant Reference no. :
Description:
This is a post-peer-review, pre-copyedit version of an article published in Lecture Notes in Computer Science. The final authenticated version is available online at: http://dx.doi.org/10.1007/978-3-031-78354-8_11
ISSN:
9783031783548
ISBN:
9783031783531
Files uploaded:

File Size Format Action
2024-icpr.pdf 599.02 KB PDF Open