Future Moment Assessment for Action Query

Ke, Qiuhong and Fritz, Mario and Schiele, Bernt
(2021) Future Moment Assessment for Action Query.
In: IEEE Winter Conference on Applications of Computer Vision (WACV ’21).
Conference: WACV IEEE Workshop on Applications of Computer Vision

Full text not available from this repository.
Official URL: https://openaccess.thecvf.com/content/WACV2021/htm...


In this paper, we aim to tackle the task of Assessing Future Moment of an Action of Interest (AFM-AI). The goal of this task is to assess if an action of interest will happen or not as well as the starting moment of the action. We aim to assess starting moments at any time-horizon of the future. To this end, we tackle the regression task of the starting moments as a generation task using a Deterministic Residual Guided Variational Regression Module (DR-VRM), which is built on a Variational Regression Module (VRM) and a deterministic residual network. The VRM takes the uncertainty into account and is capable of generating diverse predictions for the starting moment. The deterministic network encourages the VRM to learn from deterministic residual information in order to generate more precise predictions for moment assessment. Experimental results on three datasets clearly show that the proposed method is capable of generating both diverse and precise predictions of starting moments for query actions.


Actions (login required)

View Item View Item