Sciweavers

376 search results - page 34 / 76
» On the Use of Virtual Evidence in Conditional Random Fields
Sort
View
CVPR
2008
IEEE
14 years 2 months ago
View and scale invariant action recognition using multiview shape-flow models
Actions in real world applications typically take place in cluttered environments with large variations in the orientation and scale of the actor. We present an approach to simult...
Pradeep Natarajan, Ram Nevatia
TASLP
2008
115views more  TASLP 2008»
13 years 7 months ago
Recognition of Dialogue Acts in Multiparty Meetings Using a Switching DBN
Abstract--This paper is concerned with the automatic recognition of dialogue acts (DAs) in multiparty conversational speech. We present a joint generative model for DA recognition ...
Alfred Dielmann, Steve Renals
EMNLP
2009
13 years 5 months ago
Generalized Expectation Criteria for Bootstrapping Extractors using Record-Text Alignment
Traditionally, machine learning approaches for information extraction require human annotated data that can be costly and time-consuming to produce. However, in many cases, there ...
Kedar Bellare, Andrew McCallum
IJCV
2008
281views more  IJCV 2008»
13 years 7 months ago
Simultaneous Segmentation and Pose Estimation of Humans Using Dynamic Graph Cuts
Abstract This paper presents a novel algorithm for performing integrated segmentation and 3D pose estimation of a human body from multiple views. Unlike other state of the art meth...
Pushmeet Kohli, Jonathan Rihan, Matthieu Bray, Phi...
JCDL
2005
ACM
111views Education» more  JCDL 2005»
14 years 1 months ago
Developing practical automatic metadata assignment and evaluation tools for internet resources
This paper describes the development of practical automatic metadata assignment tools to support automatic record creation for virtual libraries, metadata repositories and digital...
Gordon W. Paynter