OnlineTAS: An Online Baseline for Temporal Action Segmentation

Autor:	Zhong, Qing, Ding, Guodong, Yao, Angela
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: 16 pages, 4 figures, 12 tables. Accepted to NeurIPS 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2411.01122 Zobrazit plný text záznamu View this record from Arxiv