arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.06754cs.CV
收藏

从没有个人行动标签的事件中学习小组活动

Learning Group Activities from Skeletons without Individual Action Labels

University of Florence(佛罗伦萨大学)

Fabio Zappardino, Tiberio Uricchio, Lorenzo Seidenari, Alberto Del Bimbo

摘要:

为了理解人类行为,我们不仅要识别个体行为,还要对复杂的群体活动和互动进行建模。层次模型在群体活动识别中获得最佳结果,但需要在演员级别上进行细粒度的个人动作注释。在本文中,我们表明,只使用骨架数据,我们可以训练一个国家的最先进的端到端系统,只使用组活动标签在序列水平。我们的实验表明,在没有个人动作监督的情况下训练的模型表现不佳。另一方面,我们证明了可以从任何预训练的特征提取器中计算伪标签,并具有可比的最终性能。最后,我们精心设计的精益构成唯一的架构显示出高度竞争力的结果,甚至在自我监督的变体更复杂的多模态方法。

英文摘要:

To understand human behavior we must not just recognize individual actions but model possibly complex group activity and interactions. Hierarchical models obtain the best results in group activity recognition but require fine grained individual action annotations at the actor level. In this paper we show that using only skeletal data we can train a state-of-the art end-to-end system using only group activity labels at the sequence level. Our experiments show that models trained without individual action supervision perform poorly. On the other hand we show that pseudo-labels can be computed from any pre-trained feature extractor with comparable final performance. Finally our carefully designed lean pose only architecture shows highly competitive results versus more complex multimodal approaches even in the self-supervised variant.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑