Coaction discovery: Segmentation of common actions across multiple videos

Caiming Xiong, Jason J. Corso

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

We introduce a new problem called coaction discovery: the task of discovering and segmenting the common actions (coactions) between videos that may contain several actions. This paper presents an approach for coaction discovery; the key idea of our approach is to compute an action proposal map for each video based jointly on dynamic object-motion and static appearance semantics, and unsupervisedly cluster each video into atomic action clips, called actoms. Subsequently, we use a temporally coherent discriminative clustering framework for extracting the coactions. We apply our coaction discovery approach to two datasets and demonstrate convincing and superior performance to three baseline methods.

Original languageEnglish
Title of host publicationProceedings of the 12th International Workshop on Multimedia Data Mining, MDMKDD'12 - Held in Conjunction with SIGKDD'12
Pages17-24
Number of pages8
DOIs
StatePublished - 2012
Event12th International Workshop on Multimedia Data Mining, MDMKDD 2012 - Held in Conjunction with SIGKDD 2012 - Beijing, China
Duration: 12 Aug 201212 Aug 2012

Publication series

NameProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Conference

Conference12th International Workshop on Multimedia Data Mining, MDMKDD 2012 - Held in Conjunction with SIGKDD 2012
Country/TerritoryChina
CityBeijing
Period12/08/1212/08/12

Keywords

  • coaction discovery
  • discriminative clustering
  • time series clustering

Fingerprint

Dive into the research topics of 'Coaction discovery: Segmentation of common actions across multiple videos'. Together they form a unique fingerprint.

Cite this