University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Video segmentation via adaptive higher-order CRF with windowed dynamics

Song, X, Han, Y, Jiang, J and Hilton, A (2014) Video segmentation via adaptive higher-order CRF with windowed dynamics ACM International Conference Proceeding Series. pp. 6-9.

Full text not available from this repository.


In this paper, we propose an adaptive higher-order CRF (HCRF) labeling approach towards automatic video object segmentation with better performances, higher effectiveness and efficiency. In comparison with the existing state of the arts, our approach achieves further improvements in terms of segmentation results. Our contribution can be highlighted as: (i) HCRF labeling is made adaptive to video content changes via a windowed dynamics; (ii) Fusion of multiple features is automatically optimized via adaptive weight parameters; (iii) Our approach is suitable for presegmentations base on a simpler image segmentation to reduce the overall computing cost, and be easily generalized without compromising on its performances. The experimental results show that our method can improve the video segmentation performance. Copyright 2014 ACM.

Item Type: Article
Divisions : Surrey research (other units)
Authors :
Song, X
Han, Y
Hilton, A
Date : 1 January 2014
DOI : 10.1145/2632856.2632896
Depositing User : Symplectic Elements
Date Deposited : 17 May 2017 13:22
Last Modified : 24 Jan 2020 23:51

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800