Video action detection by learning graph-based spatio-temporal interactions
Abstract: Action Detection is a complex task that aims to detect and classify human actions in video clips. Typically, it has been addressed by processing fine-grained features extracted from a video classification backbone. Recently, thanks to the robustness of object and people detectors, a deeper focus has been added on relationship modelling. Following this line, we propose a graph-based framework to learn high-level interactions between people and objects, in both space and time. In our formulation, spatio-temporal relationships are learned through self-attention on a multi-layer graph structure which can connect entities from consecutive clips, thus considering long-range spatial and temporal dependencies. The proposed module is backbone independent by design and does not require end-to-end training. Extensive experiments are conducted on the AVA dataset, where our model demonstrates state-of-the-art results and consistent improvements over baselines built with different backbones. Code is publicly available at https://github.com/aimagelab/STAGE_action_detection.
Citation:
Tomei, Matteo; Baraldi, Lorenzo; Calderara, Simone; Bronzin, Simone; Cucchiara, Rita "Video action detection by learning graph-based spatio-temporal interactions" COMPUTER VISION AND IMAGE UNDERSTANDING, vol. 206, pp. 1 -9 , 2021 DOI: 10.1016/j.cviu.2021.103187
not available
Paper download:
- Author version:
- DOI: 10.1016/j.cviu.2021.103187