In many visual tracking and surveillance systems, it is important to initialize a background model using a training video sequence which may include foreground objects. In such a c...
We investigate the challenging issue of joint audio-visual analysis of generic videos targeting at semantic concept detection. We propose to extract a novel representation, the Sh...
Wei Jiang, Courtenay V. Cotton, Shih-Fu Chang, Dan...
Topology is an important prior in many image segmentation tasks. In this paper, we design and implement a novel graph-based min-cut/max-flow algorithm that incorporates topology p...
In this paper, we propose a new method, video repairing, to robustly infer missing static background and moving foreground due to severe damage or occlusion from a video. To recov...
Jiaya Jia, Tai-Pang Wu, Yu-Wing Tai, Chi-Keung Tan...
We propose a system for the automatic segmentation of novelties from the background in scenarios where multiple images of the same environment are available e.g. obtained by weara...
Omid Aghazadeh, Josephine Sullivan, Stefan Carlsso...