Action Anticipation with Goal Consistency

In this paper, we address the problem of short-term action anticipation, i.e., we want to predict an upcoming action one second before it happens. We propose to harness high-level intent information to anticipate actions that will take place in the future. To this end, we incorporate an additional g...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE International Conference on Image Processing (ICIP) pp. 1630 - 1634
Main Authors Zatsarynna, Olga, Gall, Juergen
Format Conference Proceeding
LanguageEnglish
Published IEEE 08.10.2023
Subjects
Action Anticipation
Action Forecasting
Activity Understanding
Codes
Computational modeling
Image processing
Predictive models
Task analysis
Video Understanding
Online AccessGet full text
DOI10.1109/ICIP49359.2023.10222914

Cover

More Information
Summary:In this paper, we address the problem of short-term action anticipation, i.e., we want to predict an upcoming action one second before it happens. We propose to harness high-level intent information to anticipate actions that will take place in the future. To this end, we incorporate an additional goal prediction branch into our model and propose a consistency loss function that encourages the anticipated actions to conform to the high-level goal pursued in the video. In our experiments, we show the effectiveness of the proposed approach and demonstrate that our method achieves state-of-the-art results on two large-scale datasets: Assembly101 and COIN. The code is available at https://github.com/olga-zats/goal_consistency.
DOI:10.1109/ICIP49359.2023.10222914