This paper presents a dynamic conditional random field (DCRF) model to integrate contextual constraints for object segmentation in image sequences. Spatial and temporal dependenci...
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of hu...
Weaddress the issue ofEuclideanpath mu& ling ina single camerafor activity monitoring in a multi-camera video surveillance system m e paperpmposes a novel linear solufwnro aut...
This paper introduces a variational formulation for image denoising based on a quadratic function over kernels of variable bandwidth. These kernels are scale adaptive and reflect ...
Given an input video sequence of one person conducting a sequence of continuous actions, we consider the problem of jointly segmenting and recognizing actions. We propose a discri...
Qinfeng Shi, Li Wang, Li Cheng, Alexander J. Smola