Skip to Main content Skip to Navigation
Journal articles

Weakly supervised learning of interactions between humans and objects

Alessandro Prest 1, 2 Cordelia Schmid 1 Vittorio Ferrari 2
1 LEAR - Learning and recognition in vision
Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology, LJK - Laboratoire Jean Kuntzmann, Inria Grenoble - Rhône-Alpes
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. We present an extensive experimental evaluation on the sports action dataset from Gupta et al., the PASCAL Action 2010 dataset, and a new human-object interaction dataset.
Document type :
Journal articles
Complete list of metadatas

https://hal.inria.fr/inria-00611482
Contributor : Thoth Team <>
Submitted on : Monday, October 24, 2011 - 10:13:00 AM
Last modification on : Thursday, November 19, 2020 - 1:00:23 PM
Long-term archiving on: : Thursday, March 30, 2017 - 5:40:56 PM

File

AT.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00611482, version 3

Citation

Alessandro Prest, Cordelia Schmid, Vittorio Ferrari. Weakly supervised learning of interactions between humans and objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2011. ⟨inria-00611482v3⟩

Share

Metrics

Record views

66

Files downloads

36