Weakly-Supervised Group Activity Recognition (WSGAR) aims to understand the
activity performed together by a group of individuals with the video-level
label and without actor-level labels. We propose Flow-Assisted Motion Learning
Network (Flaming-Net) for WSGAR, which consists of the motion-aware actor
encoder to extract actor features and the two-pathways relation module to infer
the interaction among actors and their activity. Flaming-Net leverages an
additional optical flow modality in the training stage to enhance its motion
awareness when finding locally active actors. The first pathway of the relation
module, the actor-centric path, initially captures the temporal dynamics of
individual actors and then constructs inter-actor relationships. In parallel,
the group-centric path starts by building spatial connections between actors
within the same timeframe and then captures simultaneous spatio-temporal
dynamics among them. We demonstrate that Flaming-Net achieves new
state-of-the-art WSGAR results on two benchmarks, including a 2.8%p higher MPCA
score on the NBA dataset. Importantly, we use the optical flow modality only
for training and not for inference.

弱监督群体活动识别（WSGAR）旨在通过视频级标签而不使用参与者级标签来理解群体共同参与的活动。提出了一种用于 WSGAR 的流辅助运动学习网络（Flaming-Net），它由具有运动感知能力的参与者编码器和用于推断参与者之间的交互和活动的双路径关系模块组成。Flaming-Net 在训练阶段利用额外的光流信息来增强其对运动的感知能力，以便找到局部活动的参与者。关系模块的第一路径，即以参与者为中心的路径，首先捕捉个体参与者的时间动态，然后构建参与者之间的相互关系。同时，以群体为中心的路径在同一时间框架内建立参与者之间的空间连接，然后捕捉它们之间的同时空间动态。我们证明 Flaming-Net 在两个基准数据集上取得了新的最先进的 WSGAR 结果，包括 NBA 数据集上高出 2.8% p 的 MPCA 分数。重要的是，我们只在训练过程中使用光流信息，而不在推断过程中使用。