TY - GEN
T1 - A life-log search model based on Bayesian Network
AU - Ushiama, Taketoshi
AU - Watanabe, Toyohide
PY - 2004/12/1
Y1 - 2004/12/1
N2 - The integration of life-log data in different media enables to represent the same activities from various viewpoints. Integrated life-log data represent contexts each other that are not able to represent in single. Each media has its own characteristic features, and the limitation on its content representation ability. Life-log data consists of records of activities. Examples of life-log data are the e-mail massages that he/she sent and received, TV programs that he/she watched, and photographs that he/she took, and so on. One of the most important characteristic of life-log is that the same activities are represented in different media. This paper focuses on the integrate life-logs in different media and to search them based on their contexts. A problem of the integration is that it is difficult to make correspondences between life-logs in different media types strictly and the correspondences consists uncertainty. In this paper, we introduce a framework based on Bayesian Network.
AB - The integration of life-log data in different media enables to represent the same activities from various viewpoints. Integrated life-log data represent contexts each other that are not able to represent in single. Each media has its own characteristic features, and the limitation on its content representation ability. Life-log data consists of records of activities. Examples of life-log data are the e-mail massages that he/she sent and received, TV programs that he/she watched, and photographs that he/she took, and so on. One of the most important characteristic of life-log is that the same activities are represented in different media. This paper focuses on the integrate life-logs in different media and to search them based on their contexts. A problem of the integration is that it is difficult to make correspondences between life-logs in different media types strictly and the correspondences consists uncertainty. In this paper, we introduce a framework based on Bayesian Network.
UR - http://www.scopus.com/inward/record.url?scp=20844452591&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=20844452591&partnerID=8YFLogxK
U2 - 10.1109/MMSE.2004.11
DO - 10.1109/MMSE.2004.11
M3 - Conference contribution
AN - SCOPUS:20844452591
SN - 0769522173
SN - 9780769522173
T3 - Proceedings - IEEE Sixth International Symposium on Multimedia Software Engineering, MSE 2004
SP - 337
EP - 343
BT - Proceedings - IEEE Sixth International Symposium on Multimedia Software Engineering, MSE 2004
T2 - Proceedings - IEEE Sixth International Symposium on Multimedia Software Engineering, MSE 2004
Y2 - 13 December 2004 through 15 December 2004
ER -