Sciweavers

616 search results - page 80 / 124
» Learning Hierarchical Models of Scenes, Objects, and Parts
Sort
View
ESWS
2007
Springer
15 years 8 months ago
Annotating Relationships Between Multiple Mixed-Media Digital Objects by Extending Annotea
Annotea provides an annotation protocol to support collaborative Semantic Web-based annotation of digital resources accessible through the Web. It provides a model whereby a user m...
Ronald Schroeter, Jane Hunter, Andrew Newman
TCSV
2010
14 years 8 months ago
Compressed Domain Video Object Segmentation
We propose a compressed domain video object segmentation method for MPEG or MPEG-like encoded videos. Computational superiority is the main advantage of the compressed domain proc...
Fatih Murat Porikli, Faisal I. Bashir, Huifang Sun
CVPR
2011
IEEE
14 years 5 months ago
How does Person Identity Recognition Help Multi-Person Tracking?
We address the problem of multi-person tracking in a complex scene from a single camera. Although trackletassociation methods have shown impressive results in several challenging ...
Cheng-Hao Kuo, Ram Nevatia
ICPR
2008
IEEE
16 years 3 months ago
Parametric video compression using appearance space
The novelty of the approach presented in this paper is the unique object-based video coding framework for videos obtained from a static camera. As opposed to most existing methods...
Santanu Chaudhury, Subarna Tripathi, Sumantra Dutt...
IJCV
2006
129views more  IJCV 2006»
15 years 1 months ago
An a contrario Decision Framework for Region-Based Motion Detection
The aim of motion detection is to decide whether a given part of an image belongs to a moving object or to the static background. This paper proposes an automatic decision rule for...
Thomas Veit, Frédéric Cao, Patrick B...