FCA-RAC:首周期标注的重复动作计数
FCA-RAC: First Cycle Annotated Repetitive Action Counting
AI总结:
针对现有动作计数数据集动作多样性不足、模型泛化性差的问题,提出FCA-RAC框架,通过首周期标注、自适应采样等四部分技术,在RepCount-A等数据集上取得优异效果,提升了模型对见过及未见过动作的计数性能与泛化能力。
摘要:
重复动作计数用于量化个体执行特定动作的频率。然而,现有动作计数数据集的动作多样性有限,可能会影响模型在未见过的动作上的性能。为解决这一问题,我们提出了名为First Cycle Annotated Repetitive Action Counting(首周期标注重复动作计数,简称FCA-RAC)的框架。该框架包含4个部分:1)一种标注技术,为每个训练视频标注第一个动作周期的起止点以及总动作次数。该技术使模型能够捕捉初始动作周期与后续动作之间的关联;2)一种自适应采样策略,通过适配视频中已标注的首个动作周期的速度,最大化保留动作信息;3)多时间粒度卷积(Multi-Temporal Granularity Convolution,简称MTGC)模块,利用多尺度的首个动作作为核对整个视频进行卷积。这使模型能够捕捉视频内不同时间尺度下的动作变化;4)一种名为Training Knowledge Augmentation(训练知识增强,简称TKA)的策略,利用整个数据集中已标注的首个动作周期信息。这使得网络能够有效利用不同动作间的共有特征,从而提升模型性能以及对未见过动作的泛化能力。实验结果表明,我们的方法在RepCount-A及相关数据集上取得了优异的结果,凸显了该框架在提升模型对见过和未见过动作的性能方面的有效性。本文通过解决现有数据集的局限性,并提出提升模型泛化能力的新技术,为动作计数领域做出了重要贡献。
英文摘要:
Repetitive action counting quantifies the frequency of specific actions performed by individuals. However, existing action-counting datasets have limited action diversity, potentially hampering model performance on unseen actions. To address this issue, we propose a framework called First Cycle Annotated Repetitive Action Counting (FCA-RAC). This framework contains 4 parts: 1) a labeling technique that annotates each training video with the start and end of the first action cycle, along with the total action count. This technique enables the model to capture the correlation between the initial action cycle and subsequent actions; 2) an adaptive sampling strategy that maximizes action information retention by adjusting to the speed of the first annotated action cycle in videos; 3) a Multi-Temporal Granularity Convolution (MTGC) module, that leverages the muli-scale first action as a kernel to convolve across the entire video. This enables the model to capture action variations at different time scales within the video; 4) a strategy called Training Knowledge Augmentation (TKA) that exploits the annotated first action cycle information from the entire dataset. This allows the network to harness shared characteristics across actions effectively, thereby enhancing model performance and generalizability to unseen actions. Experimental results demonstrate that our approach achieves superior outcomes on RepCount-A and related datasets, highlighting the efficacy of our framework in improving model performance on seen and unseen actions. Our paper makes significant contributions to the field of action counting by addressing the limitations of existing datasets and proposing novel techniques for improving model generalizability.
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。