Sciweavers

27 search results - page 1 / 6
» A neural-field-like approach for modeling human group action...
Sort
View
ICMCS
2005
IEEE
68views Multimedia» more  ICMCS 2005»
14 years 1 months ago
A neural-field-like approach for modeling human group actions in meetings
In this paper we investigate a new architecture for recognizing human group actions in meetings. These group actions provide a basis that enables effective browsing and querying i...
Stephan Reiter, Gerhard Rigoll
MLMI
2005
Springer
14 years 27 days ago
Multimodal Integration for Meeting Group Action Segmentation and Recognition
We address the problem of segmentation and recognition of sequences of multimodal human interactions in meetings. These interactions can be seen as a rough structure of a meeting, ...
Marc Al-Hames, Alfred Dielmann, Daniel Gatica-Pere...
ICPR
2004
IEEE
14 years 8 months ago
Human Action Segmentation via Controlled Use of Missing Data in HMMs
Segmentation of individual actions from a stream of human motion is an open problem in computer vision. This paper approaches the problem of segmenting higher-level activities int...
Patrick Peursum, Hung Hai Bui, Svetha Venkatesh, G...
PAA
2008
13 years 7 months ago
Human action recognition in videos based on the Transferable Belief Model
Abstract This paper focuses on human behavior recognition where the main problem is to bridge the semantic gap between the analogue observations of the real world and the symbolic ...
Emmanuel Ramasso, Costas Panagiotakis, Denis Pelle...
ICMCS
2007
IEEE
151views Multimedia» more  ICMCS 2007»
14 years 1 months ago
Exploring Contextual Information in a Layered Framework for Group Action Recognition
Contextual information is important for sequence modeling. Hidden Markov Models (HMMs) and extensions, which have been widely used for sequence modeling, make simplifying, often u...
Dong Zhang, Samy Bengio