Sciweavers

320 search results - page 21 / 64
» Outlier detection by active learning
Sort
View
ECCV
2010
Springer
13 years 9 months ago
Activities as Time Series of Human Postures
Abstract. This paper presents an exemplar-based approach to detecting and localizing human actions, such as running, cycling, and swinging, in realistic videos with dynamic backgro...
William Brendel, Sinisa Todorovic
ICCV
2009
IEEE
15 years 1 months ago
Modelling Activity Global Temporal Dependencies using Time Delayed Probabilistic Graphical Model
We present a novel approach for detecting global behaviour anomalies in multiple disjoint cameras by learning time delayed dependencies between activities cross camera views. Sp...
Chen Change Loy, Tao Xiang and Shaogang Gong
MM
2005
ACM
160views Multimedia» more  MM 2005»
14 years 2 months ago
Putting active learning into multimedia applications: dynamic definition and refinement of concept classifiers
The authors developed an extensible system for video exploitation that puts the user in control to better accommodate novel situations and source material. Visually dense displays...
Ming-yu Chen, Michael G. Christel, Alexander G. Ha...
ECCV
2008
Springer
14 years 10 months ago
Learning Spatial Context: Using Stuff to Find Things
The sliding window approach of detecting rigid objects (such as cars) is predicated on the belief that the object can be identified from the appearance in a small region around the...
Geremy Heitz, Daphne Koller
FQAS
2004
Springer
126views Database» more  FQAS 2004»
14 years 1 months ago
Cluster Characterization through a Representativity Measure
Clustering is an unsupervised learning task which provides a decomposition of a dataset into subgroups that summarize the initial base and give information about its structure. We ...
Marie-Jeanne Lesot, Bernadette Bouchon-Meunier