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

Other

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

Fingerprint

Semantics
Motion estimation
Cameras
Trajectories

Keywords

  • graph matching
  • object graph
  • Video representation

ASJC Scopus subject areas

  • Computer Science Applications
  • Media Technology

Cite this

Feng, X., Xue, Y., & Wang, Y. (2017). Video object graph: A novel semantic level representation for videos. In 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017 (pp. 680-685). [8026327] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMEW.2017.8026327

Video object graph : A novel semantic level representation for videos. / Feng, Xin; Xue, Yuanyi; Wang, Yao.

2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 680-685 8026327.

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

Feng, X, Xue, Y & Wang, Y 2017, Video object graph: A novel semantic level representation for videos. in 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017., 8026327, Institute of Electrical and Electronics Engineers Inc., pp. 680-685, 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017, Hong Kong, Hong Kong, 7/10/17. https://doi.org/10.1109/ICMEW.2017.8026327
Feng X, Xue Y, Wang Y. Video object graph: A novel semantic level representation for videos. In 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 680-685. 8026327 https://doi.org/10.1109/ICMEW.2017.8026327
Feng, Xin ; Xue, Yuanyi ; Wang, Yao. / Video object graph : A novel semantic level representation for videos. 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 680-685
@inproceedings{02f88c99161a4aa795cbbc761eb2fae9,
title = "Video object graph: A novel semantic level representation for videos",
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.",
keywords = "graph matching, object graph, Video representation",
author = "Xin Feng and Yuanyi Xue and Yao Wang",
year = "2017",
month = "9",
day = "5",
doi = "10.1109/ICMEW.2017.8026327",
language = "English (US)",
pages = "680--685",
booktitle = "2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Video object graph

T2 - A novel semantic level representation for videos

AU - Feng, Xin

AU - Xue, Yuanyi

AU - Wang, Yao

PY - 2017/9/5

Y1 - 2017/9/5

N2 - 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.

AB - 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.

KW - graph matching

KW - object graph

KW - Video representation

UR - http://www.scopus.com/inward/record.url?scp=85031679550&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85031679550&partnerID=8YFLogxK

U2 - 10.1109/ICMEW.2017.8026327

DO - 10.1109/ICMEW.2017.8026327

M3 - Conference contribution

AN - SCOPUS:85031679550

SP - 680

EP - 685

BT - 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -