Diffusion Action Segmentation
This work addresses the problem of understanding human actions in videos for applications like video analysis, but it is incremental as it adapts an existing iterative refinement paradigm using diffusion models.
The authors tackled temporal action segmentation in long-form videos by proposing a denoising diffusion model framework that iteratively generates action predictions from random noise, conditioned on video features, and achieved superior or comparable results to state-of-the-art methods on GTEA, 50Salads, and Breakfast datasets.
Temporal action segmentation is crucial for understanding long-form videos. Previous works on this task commonly adopt an iterative refinement paradigm by using multi-stage models. We propose a novel framework via denoising diffusion models, which nonetheless shares the same inherent spirit of such iterative refinement. In this framework, action predictions are iteratively generated from random noise with input video features as conditions. To enhance the modeling of three striking characteristics of human actions, including the position prior, the boundary ambiguity, and the relational dependency, we devise a unified masking strategy for the conditioning inputs in our framework. Extensive experiments on three benchmark datasets, i.e., GTEA, 50Salads, and Breakfast, are performed and the proposed method achieves superior or comparable results to state-of-the-art methods, showing the effectiveness of a generative approach for action segmentation.