Temporal action segmentation (TAS) is essential for identifying when actions are performed by a subject, with appli- cations ranging from healthcare to Industry 5.0. In such contexts, the need for real-time, low-latency responses and privacy-aware data handling often requires the use of edge devices, despite their limited memory, power, and computational resources. This paper presents OLORAS, a novel TAS model designed for real-time performance on edge devices. By leveraging human pose data instead of video frames and employing linear recurrent units (LRUs), OLORAS efficiently processes long sequences while minimizing memory usage. Tested on the standard Assembly101 dataset, the model outperforms state-of-the-art TAS methods in accuracy with 10x memory footprint reduction, making it well-suited for deployment on resource-constrained devices.
OLORAS: Online LOng Range Action Segmentation for Edge Devices
Ziche, Filippo;Bombieri, Nicola
2025-01-01
Abstract
Temporal action segmentation (TAS) is essential for identifying when actions are performed by a subject, with appli- cations ranging from healthcare to Industry 5.0. In such contexts, the need for real-time, low-latency responses and privacy-aware data handling often requires the use of edge devices, despite their limited memory, power, and computational resources. This paper presents OLORAS, a novel TAS model designed for real-time performance on edge devices. By leveraging human pose data instead of video frames and employing linear recurrent units (LRUs), OLORAS efficiently processes long sequences while minimizing memory usage. Tested on the standard Assembly101 dataset, the model outperforms state-of-the-art TAS methods in accuracy with 10x memory footprint reduction, making it well-suited for deployment on resource-constrained devices.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
