A Space-Time Graph Optimization Approach Based on Maximum Cliques for Action Detection

Sunyoung Cho, Hyeran Byun

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

We present an efficient action detection method that takes a space-time (ST) graph optimization approach for real-world videos. Given an ST graph representing the entire action video, our method identifies a maximum-weight connected subgraph (MWCS) indicating an action region by applying an optimization approach based on clique information. We define an energy function based on maximum weight cliques for subregions of the graph and formulate it using an optimization problem that can be represented as a linear system. Our energy function includes the maximum and connectivity properties for finding the MWCS, and its optimization solution indicates the probability of belonging to the maximum subgraph for each node. Our graph optimization method efficiently solves the detection problem by applying the clique-based approach and simple linear system solver. We demonstrate that our detection method results in a more accurate localization compared with conventional methods through our experimental results with real-world data sets, such as the Hollywood and MSR action data sets. We also show that our method outperforms the state-of-the-art methods of action detection.

Original languageEnglish
Article number7088570
Pages (from-to)661-672
Number of pages12
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume26
Issue number4
DOIs
Publication statusPublished - 2016 Apr

Fingerprint

Linear systems

All Science Journal Classification (ASJC) codes

  • Media Technology
  • Electrical and Electronic Engineering

Cite this

@article{e977ef59c8d74aabb8091d05f38855bb,
title = "A Space-Time Graph Optimization Approach Based on Maximum Cliques for Action Detection",
abstract = "We present an efficient action detection method that takes a space-time (ST) graph optimization approach for real-world videos. Given an ST graph representing the entire action video, our method identifies a maximum-weight connected subgraph (MWCS) indicating an action region by applying an optimization approach based on clique information. We define an energy function based on maximum weight cliques for subregions of the graph and formulate it using an optimization problem that can be represented as a linear system. Our energy function includes the maximum and connectivity properties for finding the MWCS, and its optimization solution indicates the probability of belonging to the maximum subgraph for each node. Our graph optimization method efficiently solves the detection problem by applying the clique-based approach and simple linear system solver. We demonstrate that our detection method results in a more accurate localization compared with conventional methods through our experimental results with real-world data sets, such as the Hollywood and MSR action data sets. We also show that our method outperforms the state-of-the-art methods of action detection.",
author = "Sunyoung Cho and Hyeran Byun",
year = "2016",
month = "4",
doi = "10.1109/TCSVT.2015.2424054",
language = "English",
volume = "26",
pages = "661--672",
journal = "IEEE Transactions on Circuits and Systems for Video Technology",
issn = "1051-8215",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

A Space-Time Graph Optimization Approach Based on Maximum Cliques for Action Detection. / Cho, Sunyoung; Byun, Hyeran.

In: IEEE Transactions on Circuits and Systems for Video Technology, Vol. 26, No. 4, 7088570, 04.2016, p. 661-672.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Space-Time Graph Optimization Approach Based on Maximum Cliques for Action Detection

AU - Cho, Sunyoung

AU - Byun, Hyeran

PY - 2016/4

Y1 - 2016/4

N2 - We present an efficient action detection method that takes a space-time (ST) graph optimization approach for real-world videos. Given an ST graph representing the entire action video, our method identifies a maximum-weight connected subgraph (MWCS) indicating an action region by applying an optimization approach based on clique information. We define an energy function based on maximum weight cliques for subregions of the graph and formulate it using an optimization problem that can be represented as a linear system. Our energy function includes the maximum and connectivity properties for finding the MWCS, and its optimization solution indicates the probability of belonging to the maximum subgraph for each node. Our graph optimization method efficiently solves the detection problem by applying the clique-based approach and simple linear system solver. We demonstrate that our detection method results in a more accurate localization compared with conventional methods through our experimental results with real-world data sets, such as the Hollywood and MSR action data sets. We also show that our method outperforms the state-of-the-art methods of action detection.

AB - We present an efficient action detection method that takes a space-time (ST) graph optimization approach for real-world videos. Given an ST graph representing the entire action video, our method identifies a maximum-weight connected subgraph (MWCS) indicating an action region by applying an optimization approach based on clique information. We define an energy function based on maximum weight cliques for subregions of the graph and formulate it using an optimization problem that can be represented as a linear system. Our energy function includes the maximum and connectivity properties for finding the MWCS, and its optimization solution indicates the probability of belonging to the maximum subgraph for each node. Our graph optimization method efficiently solves the detection problem by applying the clique-based approach and simple linear system solver. We demonstrate that our detection method results in a more accurate localization compared with conventional methods through our experimental results with real-world data sets, such as the Hollywood and MSR action data sets. We also show that our method outperforms the state-of-the-art methods of action detection.

UR - http://www.scopus.com/inward/record.url?scp=84963796120&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963796120&partnerID=8YFLogxK

U2 - 10.1109/TCSVT.2015.2424054

DO - 10.1109/TCSVT.2015.2424054

M3 - Article

AN - SCOPUS:84963796120

VL - 26

SP - 661

EP - 672

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

SN - 1051-8215

IS - 4

M1 - 7088570

ER -