Action Detection via an Image Diffusion Process
This work addresses the problem of localizing actions in videos for computer vision applications, presenting a novel approach with incremental improvements.
The paper tackles action detection in untrimmed videos by reformulating it as an image generation problem, proposing the ADI-Diff framework that achieves state-of-the-art results on two widely-used datasets.
Action detection aims to localize the starting and ending points of action instances in untrimmed videos, and predict the classes of those instances. In this paper, we make the observation that the outputs of the action detection task can be formulated as images. Thus, from a novel perspective, we tackle action detection via a three-image generation process to generate starting point, ending point and action-class predictions as images via our proposed Action Detection Image Diffusion (ADI-Diff) framework. Furthermore, since our images differ from natural images and exhibit special properties, we further explore a Discrete Action-Detection Diffusion Process and a Row-Column Transformer design to better handle their processing. Our ADI-Diff framework achieves state-of-the-art results on two widely-used datasets.