We describe a system to learn an object template from a video stream, and localize and track the corresponding object in live video. The template is decomposed into a number of lo...
Robust video streaming over time-varying, error-prone wireless LANs (WLANs) poses many challenges. In this paper, we present a Time-based Opportunistic Relay (TOR) scheme for high...
This paper presents a novel approach to object recognition involving a sparse 2D model and matching using video. The model is generated on the basis of geometry and image measurab...
Humera Noor, Shahid H. Mirza, Yaser Sheikh, Amit J...
Current pattern-detection proposals for streaming data recognize the need to move beyond a simple regular-expression model over strictly ordered input. We continue in this directi...
Badrish Chandramouli, Jonathan Goldstein, David Ma...
Abstract. We introduce a view–point invariant representation of moving object trajectories that can be used in video database applications. It is assumed that trajectories lie on...