Towards More Practical Group Activity Detection: A New Benchmark and Model
This work addresses practical challenges in group activity detection for video analysis, though it is incremental as it builds on existing datasets and methods.
The paper tackles the problem of group activity detection in videos by introducing a new large-scale dataset called Café with practical scenarios and metrics, and proposes a model that handles unknown numbers of groups efficiently, achieving improved accuracy and inference speed compared to previous work.
Group activity detection (GAD) is the task of identifying members of each group and classifying the activity of the group at the same time in a video. While GAD has been studied recently, there is still much room for improvement in both dataset and methodology due to their limited capability to address practical GAD scenarios. To resolve these issues, we first present a new dataset, dubbed Café. Unlike existing datasets, Café is constructed primarily for GAD and presents more practical scenarios and metrics, as well as being large-scale and providing rich annotations. Along with the dataset, we propose a new GAD model that deals with an unknown number of groups and latent group members efficiently and effectively. We evaluated our model on three datasets including Café, where it outperformed previous work in terms of both accuracy and inference speed.