In this paper we extend Active Monte Carlo Recognition (AMCR), a recently proposed framework for object recognition. The approach is based on the analogy between mobile robot loca...
In this paper we introduce Active Monte Carlo Recognition (AMCR), a new approach for object recognition. The method is based on seeding and propagating "relational" part...
We explore an approach to 3D people tracking with learned motion models and deterministic optimization. The tracking problem is formulated as the minimization of a differentiable ...
The ambiguity inherent in a localized analysis of events from video can be resolved by exploiting constraints between events and examining only feasible global explanations. We sho...
Dima Damen (University of Leeds), David Hogg (Univ...
The majority of existing pedestrian trackers concentrate on maintaining the identities of targets, however systems for remote biometric analysis or activity recognition in surveill...