Abstract— Network tomography infers internal network characteristics by sending and collecting probe packets from the network edge. Traditional tomographic techniques for general...
Minas Gjoka, Christina Fragouli, Pegah Sattari, At...
We present an approach for identifying and segmenting independently moving objects from dense scene flow information, using a moving stereo camera system. The detection and segmen...
Real-world databases often contain syntactic and semantic errors, in spite of integrity constraints and other safety measures incorporated into modern DBMSs. We present ERACER, an...
Conditional Random Field models have proved effective for several low-level computer vision problems. Inference in these models involves solving a combinatorial optimization probl...
Recognition of human actions in a video acquired by a moving camera typically requires standard preprocessing steps such as motion compensation, moving object detection and object ...