Camera motion and surrounding scene appearance as context for action recognition

F.C. Heilbron, A. Thabet, J.C. Niebles, B. Ghanem
Asian Conference on Computer Vision, volume 9006, pp. 583-597, (2014)

Camera motion and surrounding scene appearance as context for action recognition

Keywords

Action recognition

Abstract

​This paper describes a framework for recognizing human actions in videos by incorporating a new set of visual cues that represent the context of the action. We develop a weak foreground-background segmentation approach in order to robustly extract not only foreground features that are focused on the actors, but also global camera motion and contextual scene information. Using dense point trajectories, our approach separates and describes the foreground motion from the background, represents the appearance of the extracted static background, and encodes the global camera motion that interestingly is shown to be discriminative for certain action classes. Our experiments on four challenging benchmarks (HMDB51, Hollywood2, Olympic Sports, and UCF50) show that our contextual features enable a significant performance improvement over state-of-the-art algorithms.

Code

DOI: 10.1007/978-3-319-16817-3_38

Sources

Website PDF

See all publications 2014