arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2108.06706cs.CV
收藏

基于高级复杂活动标签的时态动作分割

Temporal Action Segmentation with High-level Complex Activity Labels

National University of Singapore(新加坡国立大学)

Guodong Ding, Angela Yao

摘要:

时间动作分割任务对视频进行时间分割,并预测所有帧的动作标签。充分监督这样的分割模型需要密集的帧明智的行动注释,这是昂贵的和繁琐的collect.This工作是第一个提出一个组成行动发现(CAD)框架,只需要视频明智的高层次的复杂活动标签作为监督时间动作分割。该方法使用活动分类任务自动发现组成视频动作。具体来说,我们定义了有限数量的潜在动作原型来构建视频级的双重表示,这些原型通过活动分类训练集体学习。这种设置赋予我们的方法在多个复杂活动中发现潜在共享操作的能力。由于缺乏行动层面的监督,我们采用匈牙利匹配算法相关的潜在行动原型地面真实语义类进行评估。我们表明,与高层次的监督,匈牙利匹配可以从现有的视频和活动水平扩展到全球水平。全局级匹配允许跨活动的行动共享,这在以前的文献中从未被考虑过。大量的实验表明,我们发现的动作可以帮助执行时间动作分割和活动识别任务。

英文摘要:

The temporal action segmentation task segments videos temporally and predicts action labels for all frames. Fully supervising such a segmentation model requires dense frame-wise action annotations, which are expensive and tedious to collect. This work is the first to propose a Constituent Action Discovery (CAD) framework that only requires the video-wise high-level complex activity label as supervision for temporal action segmentation. The proposed approach automatically discovers constituent video actions using an activity classification task. Specifically, we define a finite number of latent action prototypes to construct video-level dual representations with which these prototypes are learned collectively through the activity classification training. This setting endows our approach with the capability to discover potentially shared actions across multiple complex activities. Due to the lack of action-level supervision, we adopt the Hungarian matching algorithm to relate latent action prototypes to ground truth semantic classes for evaluation. We show that with the high-level supervision, the Hungarian matching can be extended from the existing video and activity levels to the global level. The global-level matching allows for action sharing across activities, which has never been considered in the literature before. Extensive experiments demonstrate that our discovered actions can help perform temporal action segmentation and activity recognition tasks.

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。

↑