PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Domain Adaptation in the Context of Sport Video Action Recognition
Nazli Faraji Davar, Teo de Campos, David Windridge, Josef Kittler and William Christmas
In: NIPS Domain Adaptation Workshop, 17 Dec 2011, Sierra Nevada, Spain.

Abstract

We apply domain adaptation to the problem of recognizing common actions between differing court-game sport videos (in particular tennis and badminton games). Actions are characterized in terms of HOG3D features extracted at the bounding box of each detected player, and thus have large intrinsic dimensionality. The techniques evaluated here for domain adaptation are based on estimating linear transformations to adapt the source domain features in order to maximize the similarity between posterior PDFs for each class in the source domain and the expected posterior PDF for each class in the target domain. As such, the problem scales linearly with feature dimensionality, making the video-environment domain adaptation problem tractable on reasonable time scales and resilient to over-fitting. We thus demonstrate that significant performance improvement can be achieved by applying domain adaptation in this context.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:8417
Deposited By:Teo de Campos
Deposited On:15 December 2011