Instructive Video retrieval based on hybrid ranking and attribute learning

A case study on surgical skill training

Lin Chen, Peng Zhang, Baoxin Li

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

3 Citations (Scopus)

Abstract

Video-based systems have been increasingly used in various training tasks in applications like sports, dancing, and surgery. One key task to add automation to such systems is to automatically select reference videos for a given training video of a trainee. In this paper, we formulate a new problem of instructive video retrieval and propose a solution using both attribute learning and learning to rank. The method first evaluates a user's skill attributes by relative attribute learning. Then, the most critical skill attribute in need of improvement is selected and reported to the user. Finally, a hybrid ranking learning to rank method is employed to retrieve instructive videos from a dataset, which serve as reference for the user. Two main technical problems are solved in this method. First, we combine both skill and visual feature to characterize skill superiority and context similarity. Second, we propose a hybrid ranking approach that works with both pair-wise and point-wise labels of the data. The benefit of the proposed method over other heuristic methods is demonstrated by both objective and subjective experiments, using surgical training videos as a case study.

Original languageEnglish (US)
Title of host publicationMM 2014 - Proceedings of the 2014 ACM Conference on Multimedia
PublisherAssociation for Computing Machinery, Inc
Pages1045-1048
Number of pages4
ISBN (Print)9781450330633
DOIs
StatePublished - Nov 3 2014
Event2014 ACM Conference on Multimedia, MM 2014 - Orlando, United States
Duration: Nov 3 2014Nov 7 2014

Other

Other2014 ACM Conference on Multimedia, MM 2014
CountryUnited States
CityOrlando
Period11/3/1411/7/14

Fingerprint

Heuristic methods
Sports
Surgery
Labels
Automation
Experiments

Keywords

  • Attribute learning
  • Learning to rank
  • Video retrieval

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Media Technology
  • Software

Cite this

Chen, L., Zhang, P., & Li, B. (2014). Instructive Video retrieval based on hybrid ranking and attribute learning: A case study on surgical skill training. In MM 2014 - Proceedings of the 2014 ACM Conference on Multimedia (pp. 1045-1048). Association for Computing Machinery, Inc. https://doi.org/10.1145/2647868.2655050

Instructive Video retrieval based on hybrid ranking and attribute learning : A case study on surgical skill training. / Chen, Lin; Zhang, Peng; Li, Baoxin.

MM 2014 - Proceedings of the 2014 ACM Conference on Multimedia. Association for Computing Machinery, Inc, 2014. p. 1045-1048.

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

Chen, L, Zhang, P & Li, B 2014, Instructive Video retrieval based on hybrid ranking and attribute learning: A case study on surgical skill training. in MM 2014 - Proceedings of the 2014 ACM Conference on Multimedia. Association for Computing Machinery, Inc, pp. 1045-1048, 2014 ACM Conference on Multimedia, MM 2014, Orlando, United States, 11/3/14. https://doi.org/10.1145/2647868.2655050
Chen L, Zhang P, Li B. Instructive Video retrieval based on hybrid ranking and attribute learning: A case study on surgical skill training. In MM 2014 - Proceedings of the 2014 ACM Conference on Multimedia. Association for Computing Machinery, Inc. 2014. p. 1045-1048 https://doi.org/10.1145/2647868.2655050
Chen, Lin ; Zhang, Peng ; Li, Baoxin. / Instructive Video retrieval based on hybrid ranking and attribute learning : A case study on surgical skill training. MM 2014 - Proceedings of the 2014 ACM Conference on Multimedia. Association for Computing Machinery, Inc, 2014. pp. 1045-1048
@inproceedings{768017fc0fc842c3a9294edda0dbe71d,
title = "Instructive Video retrieval based on hybrid ranking and attribute learning: A case study on surgical skill training",
abstract = "Video-based systems have been increasingly used in various training tasks in applications like sports, dancing, and surgery. One key task to add automation to such systems is to automatically select reference videos for a given training video of a trainee. In this paper, we formulate a new problem of instructive video retrieval and propose a solution using both attribute learning and learning to rank. The method first evaluates a user's skill attributes by relative attribute learning. Then, the most critical skill attribute in need of improvement is selected and reported to the user. Finally, a hybrid ranking learning to rank method is employed to retrieve instructive videos from a dataset, which serve as reference for the user. Two main technical problems are solved in this method. First, we combine both skill and visual feature to characterize skill superiority and context similarity. Second, we propose a hybrid ranking approach that works with both pair-wise and point-wise labels of the data. The benefit of the proposed method over other heuristic methods is demonstrated by both objective and subjective experiments, using surgical training videos as a case study.",
keywords = "Attribute learning, Learning to rank, Video retrieval",
author = "Lin Chen and Peng Zhang and Baoxin Li",
year = "2014",
month = "11",
day = "3",
doi = "10.1145/2647868.2655050",
language = "English (US)",
isbn = "9781450330633",
pages = "1045--1048",
booktitle = "MM 2014 - Proceedings of the 2014 ACM Conference on Multimedia",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Instructive Video retrieval based on hybrid ranking and attribute learning

T2 - A case study on surgical skill training

AU - Chen, Lin

AU - Zhang, Peng

AU - Li, Baoxin

PY - 2014/11/3

Y1 - 2014/11/3

N2 - Video-based systems have been increasingly used in various training tasks in applications like sports, dancing, and surgery. One key task to add automation to such systems is to automatically select reference videos for a given training video of a trainee. In this paper, we formulate a new problem of instructive video retrieval and propose a solution using both attribute learning and learning to rank. The method first evaluates a user's skill attributes by relative attribute learning. Then, the most critical skill attribute in need of improvement is selected and reported to the user. Finally, a hybrid ranking learning to rank method is employed to retrieve instructive videos from a dataset, which serve as reference for the user. Two main technical problems are solved in this method. First, we combine both skill and visual feature to characterize skill superiority and context similarity. Second, we propose a hybrid ranking approach that works with both pair-wise and point-wise labels of the data. The benefit of the proposed method over other heuristic methods is demonstrated by both objective and subjective experiments, using surgical training videos as a case study.

AB - Video-based systems have been increasingly used in various training tasks in applications like sports, dancing, and surgery. One key task to add automation to such systems is to automatically select reference videos for a given training video of a trainee. In this paper, we formulate a new problem of instructive video retrieval and propose a solution using both attribute learning and learning to rank. The method first evaluates a user's skill attributes by relative attribute learning. Then, the most critical skill attribute in need of improvement is selected and reported to the user. Finally, a hybrid ranking learning to rank method is employed to retrieve instructive videos from a dataset, which serve as reference for the user. Two main technical problems are solved in this method. First, we combine both skill and visual feature to characterize skill superiority and context similarity. Second, we propose a hybrid ranking approach that works with both pair-wise and point-wise labels of the data. The benefit of the proposed method over other heuristic methods is demonstrated by both objective and subjective experiments, using surgical training videos as a case study.

KW - Attribute learning

KW - Learning to rank

KW - Video retrieval

UR - http://www.scopus.com/inward/record.url?scp=84913583950&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84913583950&partnerID=8YFLogxK

U2 - 10.1145/2647868.2655050

DO - 10.1145/2647868.2655050

M3 - Conference contribution

SN - 9781450330633

SP - 1045

EP - 1048

BT - MM 2014 - Proceedings of the 2014 ACM Conference on Multimedia

PB - Association for Computing Machinery, Inc

ER -