论文标题
弱监督小组活动识别的社会自适应模块
Social Adaptive Module for Weakly-supervised Group Activity Recognition
论文作者
论文摘要
本文提出了一项名为弱监督的小组活动识别（GAR）的新任务，该任务与传统的GAR任务不同，因为只有视频级标签可用，但是即使在培训数据中，每个框架中的重要人员也没有提供。这使我们可以收集和注释一个大规模的NBA数据集，从而为Gar提出新的挑战。为了从弱监督中挖掘有用的信息，我们提供了一个关键见解，即关键实例可能相互关联，从而设计一个社交自适应模块（SAM），以推理有关嘈杂数据中关键人物和框架的推理。实验显示了NBA数据集以及流行的排球数据集的显着改善。特别是，我们接受视频级注释训练的模型可以达到与需要强标签的先前算法相当的精度。
This paper presents a new task named weakly-supervised group activity recognition (GAR) which differs from conventional GAR tasks in that only video-level labels are available, yet the important persons within each frame are not provided even in the training data. This eases us to collect and annotate a large-scale NBA dataset and thus raise new challenges to GAR. To mine useful information from weak supervision, we present a key insight that key instances are likely to be related to each other, and thus design a social adaptive module (SAM) to reason about key persons and frames from noisy data. Experiments show significant improvement on the NBA dataset as well as the popular volleyball dataset. In particular, our model trained on video-level annotation achieves comparable accuracy to prior algorithms which required strong labels.
