DMCA
Categorizing Turn-Taking Interactions
Cached
Download Links
| Citations: | 3 - 1 self |
BibTeX
@MISC{Prabhakar_categorizingturn-taking,
author = {Karthir Prabhakar and James M. Rehg},
title = {Categorizing Turn-Taking Interactions},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
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 turntaking 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. 1
Keyphrases
turn-taking interaction causal set multiple instance learning temporal causal analysis turntaking interaction conventional bag repetitive structure new turn-taking interaction superior performance relative sport rally real-world video co-occuring independent segment social game social interaction multiple instance space-time visual word representation word model
