Learning person-object interactions for action recognition in still images - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2011

Learning person-object interactions for action recognition in still images

Abstract

We investigate a discriminatively trained model of person-object interactions for recognizing common human actions in still images. We build on the locally order-less spatial pyramid bag-of-features model, which was shown to perform extremely well on a range of object, scene and human action recognition tasks. We introduce three principal contributions. First, we replace the standard quantized local HOG/SIFT features with stronger discriminatively trained body part and object detectors. Second, we introduce new person-object interaction features based on spatial co-occurrences of individual body parts and objects. Third, we address the combinatorial problem of a large number of possible interaction pairs and propose a discriminative selection procedure using a linear support vector machine (SVM) with a sparsity inducing regularizer. Learning of action-specific body part and object interactions bypasses the difficult problem of estimating the complete human body pose configuration. Benefits of the proposed model are shown on human action recognition in consumer photographs, outperforming the strong bag-of-features baseline.
Fichier principal
Vignette du fichier
delaitre11.pdf (963.5 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00648156 , version 1 (05-12-2011)

Identifiers

  • HAL Id : hal-00648156 , version 1

Cite

V. Delaitre, J. Sivic, I. Laptev. Learning person-object interactions for action recognition in still images. NIPS 2011 : Twenty-Fifth Annual Conference on Neural Information Processing Systems, NIPS Foundation, Dec 2011, Grenada, Spain. ⟨hal-00648156⟩
302 View
191 Download

Share

Gmail Facebook X LinkedIn More