Sciweavers

567 search results - page 26 / 114
» Learning Pedestrian Dynamics from the Real World
Sort
View
CVPR
2012
IEEE
13 years 4 days ago
Robust plane-based structure from motion
We introduce a new approach to structure and motion recovery directly from one or more large planes in the scene. When such a plane exists, we demonstrate how to automatically det...
Zihan Zhou, Hailin Jin, Yi Ma
AROBOTS
1998
100views more  AROBOTS 1998»
14 years 9 months ago
Interleaving Planning and Robot Execution for Asynchronous User Requests
Rogue is an architecture built on a real robot which provides algorithms for the integration of highlevel planning, low-level robotic execution, and learning. Rogue addresses succ...
Karen Zita Haigh, Manuela M. Veloso
VRCAI
2004
ACM
15 years 3 months ago
Real time 3D avatar for interactive mixed reality
This paper presents real-time reconstruction of dynamic 3D avatar for interactive mixed reality. In computer graphics, one of the main goals is the combination of virtual scenes w...
Sang Yup Lee, Ig-Jae Kim, Sang Chul Ahn, Heedong K...
ISCAS
2006
IEEE
144views Hardware» more  ISCAS 2006»
15 years 3 months ago
A VLSI spike-driven dynamic synapse which learns only when necessary
— We describe an analog VLSI circuit implementing spike-driven synaptic plasticity, embedded in a network of integrate-and-fire neurons. This biologically inspired synapse is hi...
S. Mitra, Stefano Fusi, Giacomo Indiveri
DAGSTUHL
2007
14 years 11 months ago
Learning Probabilistic Relational Dynamics for Multiple Tasks
The ways in which an agent’s actions affect the world can often be modeled compactly using a set of relational probabilistic planning rules. This paper addresses the problem of ...
Ashwin Deshpande, Brian Milch, Luke S. Zettlemoyer...