Joint Estimation of Human Pose and Conversational Groups from Social Scenes |
| |
Authors: | Jagannadan Varadarajan Ramanathan Subramanian Samuel Rota Bulò Narendra Ahuja Oswald Lanz Elisa Ricci |
| |
Affiliation: | 1.Advanced Digital Sciences Center,Singapore,Singapore;2.International Institute of Information Technology,Hyderabad,India;3.University of Glasgow,Glasgow,UK;4.Mapillary Research,Graz,Austria;5.Fondazione Bruno Kessler,Trento,Italy;6.University of Illinois Urbana Champaign,Champaign,USA;7.Department of Engineering,University of Perugia,Perugia,Italy |
| |
Abstract: | Despite many attempts in the last few years, automatic analysis of social scenes captured by wide-angle camera networks remains a very challenging task due to the low resolution of targets, background clutter and frequent and persistent occlusions. In this paper, we present a novel framework for jointly estimating (i) head, body orientations of targets and (ii) conversational groups called F-formations from social scenes. In contrast to prior works that have (a) exploited the limited range of head and body orientations to jointly learn both, or (b) employed the mutual head (but not body) pose of interactors for deducing F-formations, we propose a weakly-supervised learning algorithm for joint inference. Our algorithm employs body pose as the primary cue for F-formation estimation, and an alternating optimization strategy is proposed to iteratively refine F-formation and pose estimates. We demonstrate the increased efficacy of joint inference over the state-of-the-art via extensive experiments on three social datasets. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|