Weakly supervised learning of interactions between humans and objectsReport as inadecuate

Weakly supervised learning of interactions between humans and objects - Download this document for free, or read online. Document in PDF available to download.

1 LEAR - Learning and recognition in vision Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble 2 ETH Zürich - Eidgenössische Technische Hochschule Zürich

Abstract : We introduce a weakly supervised approach for learning human actions modeled as interactions between humans and objects. Our approach is human-centric: we first localize a human in the image and then determine the object relevant for the action and its spatial relation with the human. The model is learned automatically from a set of still images annotated only with the action label. Our approach relies on a human detector to initialize the model learning. For robustness to various degrees of visibility, we build a detector that learns to combine a set of existing part detectors. Starting from humans detected in a set of images depicting the action, our approach determines the action object and its spatial relation to the human. Its final output is a probabilistic model of the human-object interaction, i.e. the spatial relation between the human and the object.

Author: Alessandro Prest - Cordelia Schmid - Vittorio Ferrari -

Source: https://hal.archives-ouvertes.fr/


Related documents