TY - GEN
T1 - Video object graph
T2 - 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017
AU - Feng, Xin
AU - Xue, Yuanyi
AU - Wang, Yao
N1 - Publisher Copyright:
© 2017 IEEE.
Copyright:
Copyright 2017 Elsevier B.V., All rights reserved.
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 - Video representation
KW - graph matching
KW - object graph
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
T3 - 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017
SP - 680
EP - 685
BT - 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 10 July 2017 through 14 July 2017
ER -