提出在线动作分割新框架，解决动态上下文建模难题。
OnlineTAS: An Online Baseline for Temporal Action Segmentation
- 用自适应记忆模块捕捉随时间变化的上下文信息
- 在三个基准上达到当前最优性能，显著降低过分割
- 适合实时动作识别场景，对在线系统有实用价值
时间上下文对动作分割至关重要。离线设置下，分割网络可通过观察完整序列来捕获上下文，但在在线设置中，如何有效获取和利用上下文仍是一个未充分探索的问题。本文提出一种在线动作分割框架，核心是自适应记忆模块，可动态适应上下文变化，并结合特征增强模块，将记忆信息注入帧特征。此外，设计了一种后处理方法以缓解在线设置下的严重过分割问题。在三个常用分割基准上，该方法均取得了当前最优表现。
原文摘要 · Abstract (English)
Temporal context plays a significant role in temporal action segmentation. In an offline setting, the context is typically captured by the segmentation network after observing the entire sequence. However, capturing and using such context information in an online setting remains an under-explored problem. This work presents the an online framework for temporal action segmentation. At the core of the framework is an adaptive memory designed to accommodate dynamic changes in context over time, alongside a feature augmentation module that enhances the frames with the memory. In addition, we propose a post-processing approach to mitigate the severe over-segmentation in the online setting. On three common segmentation benchmarks, our approach achieves state-of-the-art performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。