RIT-18: A Novel Dataset for Compositional Group Activity Understanding
Junwen Chen, Haiting Hao, Hanbin Hong, Yu Kong; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 362-363
Abstract
Group activity understanding is a challenging task as multiple people are involved, and their relations may vary over time. Currently, the literature of group activity is limited to group activity recognition, because videos are trimmed in very short duration and focus on a single activity. This slows down the progress in the group activity domain. In this paper, we propose a new large-scale untrimmed compositional group activity dataset RIT-18 based on the volleyball games captured from YouTube. Each clip in our dataset depicts an entire rally which spans the duration from serve to a point being scored. Comprehensive annotations including group activity labels, temporal boundaries of activities, key persons, and winning teams are provided. We describe group activity recognition, future activity anticipation, and rally-level winner prediction challenges, and evaluate several baseline methods over these challenges. We report their performance on our dataset and demonstrate further efforts need to be made. The dataset is available at https://pht180.rit.edu/actionlab/rit-18.
Related Material
[pdf]
[
bibtex]
@InProceedings{Chen_2020_CVPR_Workshops,
author = {Chen, Junwen and Hao, Haiting and Hong, Hanbin and Kong, Yu},
title = {RIT-18: A Novel Dataset for Compositional Group Activity Understanding},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2020}
}