A Factorization Approach for Activity Recognition

Chowdhury, Amit K. Roy; Chellappa, Rama

doi:10.1109/cvprw.2003.10040

Cited by 22 publications

(15 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Vaswani et al, 2003), action trajectories are modeled utilizing flexible shapes and a dynamic model that describes the variation in the shape structure. Chowdhury and Chellappa (2003) utilize a subspace technique to model activities as a linear blending of 3D basis shapes. Deviations from the learned activity shapes can be used to detect abnormal ones.…”

Section: Scene Interpretationmentioning

confidence: 99%

Automatic visual detection of human behavior: A review from 2000 to 2014

Afsar

Cortez

Santos

2015

Expert Systems with Applications

View full text Add to dashboard Cite

Please cite this article as: Afsar, P., Cortez, P., Santos, H., Automatic visual detection of human behavior: a review from 2000 to 2014, Expert Systems with Applications (2015), doi: http://dx. AbstractDue to advances in information technology (e.g., digital video cameras, ubiquitous sensors), the automatic detection of human behaviors from video is a very recent research topic. In this paper, we perform a systematic and recent literature review on this topic, from 2000 to 2014, covering a selection of 193 papers that were searched from six major scientific publishers. The selected papers were classified into three main subjects: detection techniques, datasets and applications. The detection techniques were divided into four categories (initialization, tracking, pose estimation and recognition). The list of datasets includes eight examples (e.g., Hollywood action). Finally, several application areas were identified, including human detection, abnormal activity detection, action recognition, player modeling and pedestrian detection. Our analysis provides a road map to guide future research for designing automatic visual human behavior detection systems.

show abstract

Section: Scene Interpretationmentioning

confidence: 99%

Automatic visual detection of human behavior: A review from 2000 to 2014

Afsar

Cortez

Santos

2015

Expert Systems with Applications

View full text Add to dashboard Cite

show abstract

“…Temporal variations of the shape were modeled in its tangent space using continuous hidden Markov models. In [12], shapes were decomposed using the factorization approach into a set of basis shapes. Singular value decomposition (SVD) was used to compute the basis shapes.…”

Section: Prior Workmentioning

confidence: 99%

Recognizing Shapes in Video Sequences Using Multi-class Boosting

Cuntoor

Welborn

2008

2008 IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance

View full text Add to dashboard Cite

We model the spatio-temporal variations of the shape of objects in a video sequence using a unique SVD-like decomposition. The decomposition is used to compute shape features, which form an approximation of the original shape sequence. The features are used to train separate classifiers using multi-class boosting strategy. We demonstrate the effectiveness of the proposed approach for shape recognition using the China Lake outdoor surveillance dataset; and compare the results using mean shapes as baseline. We illustrate the usefulness of the proposed shape features for detecting shapes of interest using the SIG group activity dataset.

show abstract

“…Factorization approach was used in [6] to model activities based on rank constraints. Its effectiveness was demonstrated for activities such as passengers embarking an aircraft.…”

Section: Introductionmentioning

confidence: 99%

Epitomic Representation of Human Activities

Cuntoor

Chellappa

2007

2007 IEEE Conference on Computer Vision and Pattern Recognition

Self Cite

View full text Add to dashboard Cite

We introduce an epitomic representation for modeling human activities in video sequences. A video sequence is divided into segments within which the dynamics of objects is assumed to be linear and modeled using linear dynamical systems. The tuple consisting of the estimated system matrix, statistics of the input signal and the initial state value is said to form an epitome. The system matrices are decomposed using the Iwasawa matrix decomposition to isolate the effect of rotation, scaling and projective action on the state vector. We demonstrate the usefulness of the proposed representation and decomposition for activity recognition using the TSA airport surveillance dataset and the UCF indoor human action dataset.

show abstract

A Factorization Approach for Activity Recognition

Cited by 22 publications

References 9 publications

Automatic visual detection of human behavior: A review from 2000 to 2014

Automatic visual detection of human behavior: A review from 2000 to 2014

Recognizing Shapes in Video Sequences Using Multi-class Boosting

Epitomic Representation of Human Activities

Contact Info

Product

Resources

About