2007 IEEE Conference on Computer Vision and Pattern Recognition 2007
DOI: 10.1109/cvpr.2007.383299
|View full text |Cite
|
Sign up to set email alerts
|

Latent-Dynamic Discriminative Models for Continuous Gesture Recognition

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… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
287
0
2

Year Published

2009
2009
2015
2015

Publication Types

Select...
5
1
1

Relationship

1
6

Authors

Journals

citations
Cited by 305 publications
(290 citation statements)
references
References 20 publications
1
287
0
2
Order By: Relevance
“…The second term is the log of a Gaussian prior with variance σ 2 , i.e., P (θ) ∼ exp 1 2σ 2 ||θ|| 2 . For a more detailed discussion of LDCRF training and inference see Morency et al [13].…”
Section: Approachmentioning
confidence: 99%
See 3 more Smart Citations
“…The second term is the log of a Gaussian prior with variance σ 2 , i.e., P (θ) ∼ exp 1 2σ 2 ||θ|| 2 . For a more detailed discussion of LDCRF training and inference see Morency et al [13].…”
Section: Approachmentioning
confidence: 99%
“…As described in Morency et al [13], the task of the LDCRF model is to learn a mapping between a sequence of observations x = {x 1 , x 2 , ..., x m } and a sequence of labels y = {y 1 , y 2 , ..., y m }. Each y j is a class label for the j th observation in a sequence and is a member of a set Y of possible class labels, for example, Y = {positive-valence, negative-valence}.…”
Section: Approachmentioning
confidence: 99%
See 2 more Smart Citations
“…In the literature, there is a large number of work referring to this problem, and many impressive results have been obtained over the past several years, such as Hidden Markov Models (HMMs), Autogressive Moving Average (ARMA) [10], Conditional Random Fields (CRFs) [11], Finite State Machine(FSM) [12], [13] and their variations [14], semi-Markov model [15], 1-Nearest Neighbor with Metric Learning [16], ActionNets [17], LDCRF [18]. Wang and Suter [19] presented the use of FCRF in the vision community, and demonstrated its superiority to both HMM and general CRF.…”
Section: Related Workmentioning
confidence: 99%