Next Article in Journal
Challenges of Developing a Mobile Game for Children with Down Syndrome to Test Gestural Interface
Previous Article in Journal
Playful Learning with a Location-Based Digital Card Environment: A Promising Tool for Informal, Non-Formal, and Formal Learning
Open AccessArticle

A Multi-Task Framework for Action Prediction

School of Computer Science, Shenyang Aerospace University, Shenyang 110136, China
*
Authors to whom correspondence should be addressed.
Information 2020, 11(3), 158; https://doi.org/10.3390/info11030158
Received: 23 January 2020 / Revised: 27 February 2020 / Accepted: 6 March 2020 / Published: 16 March 2020
Predicting the categories of actions in partially observed videos is a challenging task in the computer vision field. The temporal progress of an ongoing action is of great importance for action prediction, since actions can present different characteristics at different temporal stages. To this end, we propose a novel multi-task deep forest framework, which treats temporal progress analysis as a relevant task to action prediction and takes advantage of observation ratio labels of incomplete videos during training. The proposed multi-task deep forest is a cascade structure of random forests and multi-task random forests. Unlike the traditional single-task random forests, multi-task random forests are built upon incomplete training videos annotated with action labels as well as temporal progress labels. Meanwhile, incorporating both random forests and multi-task random forests can increase the diversity of classifiers and improve the discriminative power of the multi-task deep forest. Experiments on the UT-Interaction and the BIT-Interaction datasets demonstrate the effectiveness of the proposed multi-task deep forest. View Full-Text
Keywords: action prediction; multi-task deep forest; random forest; multi-task random forest action prediction; multi-task deep forest; random forest; multi-task random forest
Show Figures

Figure 1

MDPI and ACS Style

Yu, T.; Liu, C.; Yan, Z.; Shi, X. A Multi-Task Framework for Action Prediction. Information 2020, 11, 158.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop