Publications (2)0 Total impact
-
Conference Proceeding: Saliency-based video segmentation with graph cuts and sequentially updated priors
[show abstract] [hide abstract]
ABSTRACT: This paper proposes a new method for achieving precise video segmentation without any supervision or interaction. The main contributions of this report include 1) the introduction of fully automatic segmentation based on the maximum a posteriori (MAP) estimation of the Markov random field (MRF) with graph cuts and saliency-driven priors and 2) the updating of priors and feature likelihoods by integrating the previous segmentation results and the currently estimated saliency-based visual attention. Test results indicate that our new method precisely extracts probable regions from videos without any supervised interactions.Multimedia and Expo, 2009. ICME 2009. IEEE International Conference on; 08/2009 -
Conference Proceeding: Real-time estimation of human visual attention with dynamic Bayesian network and MCMC-based particle filter
[show abstract] [hide abstract]
ABSTRACT: Recent studies in signal detection theory suggest that the human responses to the stimuli on a visual display are nondeterministic. People may attend to different locations on the same visual input at the same time. Constructing a stochastic model of human visual attention would be promising to tackle the above problem. This paper proposes a new method to achieve a quick and precise estimation of human visual attention based on our previous stochastic model with a dynamic Bayesian network. A particle filter with Markov chain Monte-Carlo (MCMC) sampling make it possible to achieve a quick and precise estimation through stream processing. Experimental results indicate that the proposed method can estimate human visual attention in real time and more precisely than previous methods.Multimedia and Expo, 2009. ICME 2009. IEEE International Conference on; 08/2009
