Advanced Search
DSpace@MIT

Latent-Dynamic Discriminative Models for Continuous Gesture Recognition

Research and Teaching Output of the MIT Community

Show simple item record

dc.contributor.advisor Trevor Darrell
dc.contributor.author Morency, Louis-Philippe
dc.contributor.author Quattoni, Ariadna
dc.contributor.author Darrell, Trevor
dc.contributor.other Vision
dc.date.accessioned 2007-01-08T01:16:48Z
dc.date.available 2007-01-08T01:16:48Z
dc.date.issued 2007-01-07
dc.identifier.other MIT-CSAIL-TR-2007-002
dc.identifier.uri http://hdl.handle.net/1721.1/35276
dc.description.abstract Many problems in vision involve the prediction of a class label for each frame in an unsegmented sequence. In this paper we develop a discriminative framework for simultaneous sequence segmentation and labeling which can capture both intrinsic and extrinsic class dynamics. Our approach incorporates hidden state variables which model the sub-structure of a class sequence and learn the dynamics between class labels. Each class label has a disjoint set of associated hidden states, which enables efficient training and inference in our model. We evaluated our method on the task of recognizing human gestures from unsegmented video streams and performed experiments on three different datasets of head and eye gestures. Our results demonstrate that our model for visual gesture recognition outperform models based on Support Vector Machines, Hidden Markov Models, and Conditional Random Fields.
dc.format.extent 8 p.
dc.format.extent 366380 bytes
dc.format.extent 946243 bytes
dc.format.mimetype application/pdf
dc.format.mimetype application/postscript
dc.language.iso en_US
dc.relation.ispartofseries Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory
dc.title Latent-Dynamic Discriminative Models for Continuous Gesture Recognition


Files in this item

Name Size Format Description
MIT-CSAIL-TR-2007 ... 357.7Kb PDF

Files in this item

Name Size Format Description
MIT-CSAIL-TR-2007 ... 924.0Kb Postscript

This item appears in the following Collection(s)

Show simple item record

MIT-Mirage