Action attribute detection from sports videos with contextual constraints

Xiaodong Yu, Ching Lik Teo, Yezhou Yang, Cornelia Fermüller, Yiannis Aloimonos

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

2 Scopus citations


In this paper, we are interested in detecting action attributes from sports videos for event understanding and video analysis. Action attribute is a middle layer between low level motion features and high level action classes, which includes various motion patterns of human limbs and bodies and the interaction between human and objects. Successfully detecting action attributes provides a richer video description that facilitates many other important tasks, such action classification, video understanding, automatic video transcript, etc. A naive approach to deal with this challenging problem is to train a classifier for each attribute and then use them to detect attributes in novel videos independently. However, this independence assumption is often too strong, and as we show in our experiments, produces a large number of false positives in practice. We propose a novel approach that incorporates the contextual constraints for activity attribute detection. The temporal contexts within an attribute and the co-occurrence contexts between different attributes are modelled by a factorial conditional random field, which encourages agreement between different time points and attributes. The effectiveness of our methods are clearly illustrated by the experimental evaluations.

Original languageEnglish (US)
Title of host publicationBMVC 2013 - Electronic Proceedings of the British Machine Vision Conference 2013
PublisherBritish Machine Vision Association, BMVA
StatePublished - 2013
Externally publishedYes
Event2013 24th British Machine Vision Conference, BMVC 2013 - Bristol, United Kingdom
Duration: Sep 9 2013Sep 13 2013


Other2013 24th British Machine Vision Conference, BMVC 2013
Country/TerritoryUnited Kingdom

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Action attribute detection from sports videos with contextual constraints'. Together they form a unique fingerprint.

Cite this