Video object graph: A novel semantic level representation for videos

Xin Feng, Yuanyi Xue, Yao Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a novel object based graph framework for video representation. The proposed framework describes a video as a graph, in which objects are represented by nodes, and their relations between objects are represented by edges. We investigated several spatial and temporal features as the graph node attributes, and different features of spatial-temporal relationship between objects as the edge attributes. To overcome the influence of the camera motion on the detected object motion, a global motion estimation and correction approach is proposed to reveal the true object trajectory. We further propose to evaluate the similarity between two videos by establishing the object correspondence between two object graphs through graph matching. Results show that our method outperforms other video representation frameworks in matching videos with the same semantic content. The proposed framework provides a compact and robust semantic descriptor for a video, which has broad appeal to many video retrieval applications.

Original languageEnglish (US)
Title of host publication2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages680-685
Number of pages6
ISBN (Electronic)9781538605608
DOIs
StatePublished - Sep 5 2017
Event2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017 - Hong Kong, Hong Kong
Duration: Jul 10 2017Jul 14 2017

Publication series

Name2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017

Other

Other2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017
CountryHong Kong
CityHong Kong
Period7/10/177/14/17

Keywords

  • Video representation
  • graph matching
  • object graph

ASJC Scopus subject areas

  • Computer Science Applications
  • Media Technology

Fingerprint Dive into the research topics of 'Video object graph: A novel semantic level representation for videos'. Together they form a unique fingerprint.

Cite this