Skip to Main content Skip to Navigation

Explicit modeling of human-object interactions in realistic videos

Alessandro Prest 1, 2 Vittorio Ferrari 2 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : We introduce an approach for learning human actions as interactions between persons and objects in realistic videos. Previous works typically represent actions with low-level features such as image gradients or optical flow. In contrast, we explicitly localize in space and track over time both the object and the person, and represent an action as the trajectory of the object wrt to the person position. Our approach relies on state-of-the-art approaches for human [32] and object detection [10] as well as tracking [39]. We show that this results in human and object tracks of sufficient quality to model and localize human-object interactions in realistic videos. Our human-object interaction features capture relative trajectory of the object wrt the human. Experimental results on the Coffee & Cigarettes [25], the video dataset of [19] and the Rochester Daily Activities dataset [29] show that (i) our explicit human-object model is an informative cue for action recognition; (ii) it is complementary to traditional low-level descriptors such as 3D-HOG extracted over human tracks. When combining our human-object interaction features with 3D-HOG features [23], we show to improve over their separate performance as well as over the state of the art.
Complete list of metadata

Cited literature [12 references]  Display  Hide  Download
Contributor : Alessandro Prest Connect in order to contact the contributor
Submitted on : Thursday, May 10, 2012 - 12:16:04 PM
Last modification on : Thursday, January 20, 2022 - 5:28:05 PM
Long-term archiving on: : Thursday, December 15, 2016 - 5:39:53 AM


Files produced by the author(s)


  • HAL Id : inria-00626929, version 4



Alessandro Prest, Vittorio Ferrari, Cordelia Schmid. Explicit modeling of human-object interactions in realistic videos. [Technical Report] RT-0411, 2011. ⟨inria-00626929v4⟩



Les métriques sont temporairement indisponibles