Joint Pose Estimation and Action Recognition in Image Graphs - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2011

Joint Pose Estimation and Action Recognition in Image Graphs


Human analysis in images and video is a hard problem due to the large variation in human pose, clothing, camera view-points, lighting and other factors. While the explicit modeling of this variability is difficult, the huge amount of available person images motivates for the implicit, data-driven approach to human analysis. In this work we aim to explore this approach using the large amount of images spanning a subspace of human appearance. We model this subspace by connecting images into a graph and propagating information through such a graph using a discriminatively trained graphical model. We particularly address the problems of human pose estimation and action recognition and demonstrate how image graphs help solving these problems jointly. We report results on still images with human actions from the KTH dataset.
Fichier principal
Vignette du fichier
raja11.pdf (275.48 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01063329 , version 1 (15-09-2014)


  • HAL Id : hal-01063329 , version 1


Kumar Raja, Ivan Laptev, Patrick Pérez, Lionel Oisel. Joint Pose Estimation and Action Recognition in Image Graphs. IEEE International Conference on Image Processing, Sep 2011, Brussels, Belgium. ⟨hal-01063329⟩
145 View
149 Download


Gmail Facebook X LinkedIn More