Abstract We propose 4 insights that help to significantly improve the performance of deep learning models that predict surface normals and semantic labels from a single RGB image. These insights are: (1) denoise the ”ground truth” surface normals in the training set to ensure consistency with the semantic labels; (2) concurrently train on a mix […]
Paper/Citation Abstract Analysis and Recognition of motions and activities of objects in videos requires effective representations for analysis and matching of motion trajectories. In this paper, we introduce a new representation specifically aimed at matching motion trajectories. We model a trajectory as a continuous dense flow field from a sparse set of vector sequences using […]
R. Hamid, S. Maddi, A. Bobick, I. Essa (2007). Structure from Statistics – Unsupervised Activity Analysis using Suffix Trees, At the International Conference on Computer Vision 2007. October 2007, Rio de Janeiro, BRAZIL [PDF][DOI] Abstract Models of activity structure for unconstrained environments are generally not available a priori. Recent representational approaches to this end are limited by […]
Motion Based Decompositing Video Abstract We present a method to decompose video sequences into layers that represent the relative depths of complex scenes. Our method combines spatial information with temporal occlusions to determine relative depths of these layers. Spatial information is obtained through edge detection and a customized contour completion algorithm. Activity in a scene […]