Collective activity recognition is an important subtask of human action recognition, where the existing datasets are mostly limited. In this paper, we look into this issue and introduce the “Collective Sports (C-Sports)” dataset, which is a novel benchmark dataset for multi-task recognition of both collective activity and sports categories. Various state-of-the-art techniques are evaluated on this dataset, together with multi-task variants which demonstrate increased performance. From the experimental results, we can say that while sports categories of the videos are inferred accurately, there is still room for improvement for collective activity recognition, especially regarding the generalization ability beyond previously unseen sports categories. In order to evaluate this ability, we introduce a novel evaluation protocol called unseen sports, where the training and test are carried out on disjoint sets of sports categories. The relatively lower recognition performances in this evaluation protocol indicate that the recognition models tend to be influenced by the surrounding context, rather than focusing on the essence of the collective activities. We believe that C-Sports dataset will stir further interest in this research direction.

集体活动识别是人类动作识别的重要子任务，其中现有数据集大多受到限制。在本文中，我们研究了这个问题，并介绍了“集体体育（C-Sports）”数据集，这是一种新颖的基准数据集，用于对集体活动和体育类别进行多任务识别。在此数据集上评估了各种最新技术，以及展示出更高性能的多任务变体。从实验结果可以看出，虽然可以准确地推断出视频的运动类别，但对于集体活动识别仍然存在改进的空间，尤其是在超越以前看不见的运动类别的泛化能力方面。为了评估此能力，我们引入了一种新颖的评估协议，称为看不见的运动，其中对不相关的运动类别进行训练和测试。在此评估协议中相对较低的识别性能表明识别模型倾向于受周围环境的影响，而不是关注集体活动的本质。我们相信，C-Sports数据集将在此研究方向上引起更多兴趣。