Multi-task recurrent neural network for immediacy prediction
Refereed conference paper presented and published in conference proceedings


Times Cited
Altmetrics Information
.

Other information
AbstractIn this paper, we propose to predict immediacy for interacting persons from still images. A complete immediacy set includes interactions, relative distance, body leaning direction and standing orientation. These measures are found to be related to the attitude, social relationship, social interaction, action, nationality, and religion of the communicators. A large-scale dataset with 10,000 images is constructed, in which all the immediacy measures and the human poses are annotated. We propose a rich set of immediacy representations that help to predict immediacy from imperfect 1-person and 2-person pose estimation results. A multi-task deep recurrent neural network is constructed to take the proposed rich immediacy representation as input and learn the complex relationship among immediacy predictions multiple steps of refinement. The effectiveness of the proposed approach is proved through extensive experiments on the large scale dataset.
All Author(s) ListChu X., Ouyang W., Yang W., Wang X.
Name of Conference15th IEEE International Conference on Computer Vision, ICCV 2015
Start Date of Conference11/12/2015
End Date of Conference18/12/2015
Place of ConferenceSantiago
Country/Region of ConferenceRepublic of Chile
Detailed descriptionorganized by IEEE,
Year2016
Month2
Day17
Volume Number11-18-December-2015
Pages3352 - 3360
ISBN9781467383912
ISSN1550-5499
LanguagesEnglish-United Kingdom

Last updated on 2021-27-01 at 00:39