End-to-End Streaming Video Temporal Action Segmentation with Reinforce Learning
This work addresses the problem of real-time action segmentation in videos for applications requiring online processing, representing an incremental improvement by adapting existing methods to a new task setting.
The paper tackles the streaming temporal action segmentation (STAS) task, which extends action segmentation to online scenarios, by introducing an end-to-end model with reinforcement learning (SVTAS-RL) that significantly outperforms existing STAS models and achieves competitive performance to state-of-the-art TAS models on multiple datasets, with notable advantages on the ultra-long video dataset EGTEA.
The streaming temporal action segmentation (STAS) task, a supplementary task of temporal action segmentation (TAS), has not received adequate attention in the field of video understanding. Existing TAS methods are constrained to offline scenarios due to their heavy reliance on multimodal features and complete contextual information. The STAS task requires the model to classify each frame of the entire untrimmed video sequence clip by clip in time, thereby extending the applicability of TAS methods to online scenarios. However, directly applying existing TAS methods to SATS tasks results in significantly poor segmentation outcomes. In this paper, we thoroughly analyze the fundamental differences between STAS tasks and TAS tasks, attributing the severe performance degradation when transferring models to model bias and optimization dilemmas. We introduce an end-to-end streaming video temporal action segmentation model with reinforcement learning (SVTAS-RL). The end-to-end modeling method mitigates the modeling bias introduced by the change in task nature and enhances the feasibility of online solutions. Reinforcement learning is utilized to alleviate the optimization dilemma. Through extensive experiments, the SVTAS-RL model significantly outperforms existing STAS models and achieves competitive performance to the state-of-the-art TAS model on multiple datasets under the same evaluation criteria, demonstrating notable advantages on the ultra-long video dataset EGTEA. Code is available at https://github.com/Thinksky5124/SVTAS.