Towards the goal of realizing a generic automatichuman activity recognition system, a new formalism is proposed. Activities are described by a chained hierarchical representation ...
It is common in object recognition algorithms based on viewpoint consistency to find object poses that align many of the object features with features extracted from a search imag...
We describe an algorithmfor reconstructing a scene containing multiple moving objects. Given a monocular image sequence, we recover the scene structure, the trajectories of the mo...
The bounding box representation employed by many popular object detection models [3, 6] implicitly assumes all pixels inside the box belong to the object. This assumption makes th...
We address the problem of detection and tracking of moving objects in a video stream obtained from a moving airborne platform. The proposed method relies on a graph representation...