Conditional models for contextual human motion recognition

Sminchisescu, Cristian; Kanaujia, Atul; Metaxas, Dimitris N.

doi:10.1016/j.cviu.2006.07.014

Cited by 214 publications

(120 citation statements)

References 10 publications

Supporting

Mentioning

119

Contrasting

Unclassified

Order By: Relevance

“…We compare the results from our model against those of other existing action models including GMM [8], HMM [12,1], logistic regression (LR) [5], SVM [6] and CRF [20].…”

Section: Methodsmentioning

confidence: 99%

“…Thus, to this point, HMM is not optimal. To overcome this limitation, conditional random field (CRF) was recently introduced [22,20]. However, CRF cannot incorporate the need for labelling a whole sequence as an action, and also cannot capture the intermediate structures using hidden state variables [15].…”

Section: Introductionmentioning

confidence: 99%

“…In general, there are two key elements in modelling human actions [13]: local appearance and temporal dependencies. To date, silhouettebased action recognition has been popular [13,23,20,3], i.e. an action is represented by a series of human body shapes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Action categorization with modified hidden conditional random field

Zhang

Gong

2010

Pattern Recognition

View full text Add to dashboard Cite

In this paper, we present a method for action categorization with a modified hidden conditional random field (HCRF). Specifically, effective silhouette-based action features are extracted using motion moments and spectrum of chain code. We formulate a modified HCRF (mHCRF) to have a guaranteed global optimum in the modelling of the temporal action dependencies after the HMM pathing stage. Experimental results on action categorization using this model are compared favorably against several existing modelbased methods including GMM, SVM, Logistic Regression, HMM, CRF and HCRF.

show abstract

“…We compare the results from our model against those of other existing action models including GMM [8], HMM [12,1], logistic regression (LR) [5], SVM [6] and CRF [20].…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Action categorization with modified hidden conditional random field

Zhang

Gong

2010

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…As well as generative models like HMM, Lan et al [14] employed a discriminative model which was aided by interaction analysis between people. Sminchisescu et al [33] used conditional random fields (CRF) and maximum-entropy Markov models, arguing that these models overcome some of the limitations presented by HMMs. Notably, HMMs create long-term dependencies between observations and tries to model observations, which are already fixed at runtime.…”

Section: Introductionmentioning

confidence: 99%

“…As a result, none of these models fit our problem of online detection of human activities in uncontrolled and cluttered environment. Since MEMM enables longer interaction among observations unlike HMM [33], the hierarchical MEMM allows us to take new observations and utilize dynamic programming to consider them in an online setting.…”

Section: Introductionmentioning

confidence: 99%

Unstructured human activity detection from RGBD images

Sung

Ponce

Selman

et al. 2012

2012 IEEE International Conference on Robotics and Automation

201

View full text Add to dashboard Cite

Abstract-Being able to detect and recognize human activities is essential for several applications, including personal assistive robotics. In this paper, we perform detection and recognition of unstructured human activity in unstructured environments. We use a RGBD sensor (Microsoft Kinect) as the input sensor, and compute a set of features based on human pose and motion, as well as based on image and pointcloud information. Our algorithm is based on a hierarchical maximum entropy Markov model (MEMM), which considers a person's activity as composed of a set of sub-activities. We infer the two-layered graph structure using a dynamic programming approach. We test our algorithm on detecting and recognizing twelve different activities performed by four people in different environments, such as a kitchen, a living room, an office, etc., and achieve good performance even when the person was not seen before in the training set. 1

show abstract

Activity Recognition

Liu

Zhang

2014

Computer Vision

View full text Add to dashboard Cite

Conditional models for contextual human motion recognition

Cited by 214 publications

References 10 publications

Action categorization with modified hidden conditional random field

Action categorization with modified hidden conditional random field

Unstructured human activity detection from RGBD images

Activity Recognition

Contact Info

Product

Resources

About