Title:
Categorizing Turn-Taking Interactions
Categorizing Turn-Taking Interactions
| dc.contributor.author | Prabhakar, Karthir | |
| dc.contributor.author | Rehg, James M. | |
| dc.contributor.corporatename | Georgia Institute of Technology. Center for Robotics and Intelligent Machines | en_US |
| dc.contributor.corporatename | Georgia Institute of Technology. College of Computing | en_US |
| dc.contributor.corporatename | Georgia Institute of Technology. School of Interactive Computing | en_US |
| dc.date.accessioned | 2013-03-04T20:00:47Z | |
| dc.date.available | 2013-03-04T20:00:47Z | |
| dc.date.issued | 2012-10 | |
| dc.description | ©2012 Springer-Verlag Berlin Heidelberg. The original publication is available at www.springerlink.com | en_US |
| dc.description | Presented at the ECCV 12th European Conference on Computer Vision (ECCV 2012), 7-13 October 2012, Florence, Italy. | |
| dc.description | DOI: 10.1007/978-3-642-33715-4_28 | |
| dc.description.abstract | We address the problem of categorizing turn-taking interactions between individuals. Social interactions are characterized by turn-taking and arise frequently in real-world videos. Our approach is based on the use of temporal causal analysis to decompose a space-time visual word representation of video into co-occuring independent segments, called causal sets [1]. These causal sets then serves the input to a multiple instance learning framework to categorize turn- taking interactions. We introduce a new turn-taking interactions dataset consisting of social games and sports rallies. We demonstrate that our formulation of multiple instance learning (QP-MISVM) is better able to leverage the repetitive structure in turn-taking interactions and demonstrates superior performance relative to a conventional bag of words model. | en_US |
| dc.embargo.terms | null | en_US |
| dc.identifier.citation | Prabhakar, K., & Rehg, J.M. (2012). “Categorizing Turn-taking Interactions”. A. Fitzgibbon et al. (Eds.). Computer Vision - ECCV 12th European Conference on Computer Vision (ECCV 2012), 7-13 October 2012. Proceedings, Part V. In Lecture Notes in Computer Science, 2012, Vol. 7576, pp. 383-396. | en_US |
| dc.identifier.doi | 10.1007/978-3-642-33715-4_28 | |
| dc.identifier.isbn | 978-3-642-33714-7 (Print) | |
| dc.identifier.isbn | 978-3-642-33715-4 (Online) | |
| dc.identifier.issn | 0302-9743 | |
| dc.identifier.uri | http://hdl.handle.net/1853/46288 | |
| dc.language.iso | en_US | en_US |
| dc.publisher | Georgia Institute of Technology | en_US |
| dc.publisher.original | Springer-Verlag Berlin / Heidelberg | |
| dc.subject | Categorizing | en_US |
| dc.subject | Multiple instance learning | en_US |
| dc.subject | Social games | en_US |
| dc.subject | Temporal causal analysis | en_US |
| dc.subject | Turn-taking interactions | en_US |
| dc.title | Categorizing Turn-Taking Interactions | en_US |
| dc.type | Text | |
| dc.type.genre | Book Chapter | |
| dc.type.genre | Proceedings | |
| dspace.entity.type | Publication | |
| local.contributor.author | Rehg, James M. | |
| local.contributor.corporatename | Institute for Robotics and Intelligent Machines (IRIM) | |
| local.contributor.corporatename | College of Computing | |
| relation.isAuthorOfPublication | af5b46ec-ffe2-4ce4-8722-1373c9b74a37 | |
| relation.isOrgUnitOfPublication | 66259949-abfd-45c2-9dcc-5a6f2c013bcf | |
| relation.isOrgUnitOfPublication | c8892b3c-8db6-4b7b-a33a-1b67f7db2021 |