%0 Electronic Article %A A.A. Liu %K sequence segmentation information %K BIRF model %K bidirectional integrated random fields model %K human behaviour understanding %K conditional random fields %K sequence classification information %K hidden-state conditional random fields %X Proposed is a bidirectional integrated random fields (BIRF) model for human behaviour understanding. The traditional hidden-state conditional random fields (HCRF) and conditional random fields (CRF) are bridged by modifying the feature functions of both, which propagates sequence classification or segmentation information in-between. Consequently, the sequence classification result by HCRF and the sequence segmentation results by CRF can be utilised to supervise the decision of each other and the performance of both models will be boosted iteratively. Large-scale experiments show that the BIRF model can achieve competing performance with the state-of-the-art methods for human behaviour understanding. %@ 0013-5194 %T Bidirectional integrated random fields for human behaviour understanding %B Electronics Letters %D March 2012 %V 48 %N 5 %P 262-264 %I Institution of Engineering and Technology %U https://digital-library.theiet.org/;jsessionid=bllpun0q48852.x-iet-live-01content/journals/10.1049/el.2011.3530 %G EN