Streaming Video Temporal Action Segmentation In Real Time

TL;DR

This paper introduces a novel multi-modality model for real-time streaming video action segmentation, achieving high accuracy with significantly reduced computation, enabling practical real-time applications.

Contribution

It presents the first multi-modality real-time temporal action segmentation model that operates without future information, combining language and image features for improved performance.

Findings

Achieves 90% accuracy of full video models in real time.

Uses less than 40% of the computation of state-of-the-art models.

First to propose a multi-modality approach for real-time TAS.

Abstract

Temporal action segmentation (TAS) is a critical step toward long-term video understanding. Recent studies follow a pattern that builds models based on features instead of raw video picture information. However, we claim those models are trained complicatedly and limit application scenarios. It is hard for them to segment human actions of video in real time because they must work after the full video features are extracted. As the real-time action segmentation task is different from TAS task, we define it as streaming video real-time temporal action segmentation (SVTAS) task. In this paper, we propose a real-time end-to-end multi-modality model for SVTAS task. More specifically, under the circumstances that we cannot get any future information, we segment the current human action of streaming video chunk in real time. Furthermore, the model we propose combines the last steaming video chunk feature extracted by language model with the current image feature extracted by image model to improve the quantity of real-time temporal action segmentation. To the best of our knowledge, it is the first multi-modality real-time temporal action segmentation model. Under the same evaluation criteria as full video temporal action segmentation, our model segments human action in real time with less than 40% of state-of-the-art model computation and achieves 90% of the accuracy of the full video state-of-the-art model.