An online spatio-temporal tensor learning model for visual tracking and its applications to facial expression recognition

Khan, Sheheryar; Xu, Gaochao; Chan, Raymond H.; Yan, Hong

doi:10.1016/j.eswa.2017.08.039

Cited by 21 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Efficient convolution operators (ECOs) [27] were proposed to achieve a lightweight version of the CCOT with a generative sample space and dimension-reduction mechanism. Furthermore, a 3rd-order tensor was used in [28] to represent the joint features of spatial and temporal information to achieve better tracking results with incremental N-mode SVD. Moreover, supervised tensor learning-based methods [29] have been proved to perform well when using a decomposition method to overcome the tracking representation overfitting problem in the field of target tracking.…”

Section: A Dcf-based Trackersmentioning

confidence: 99%

Bilateral Weighted Regression Ranking Model With Spatial-Temporal Correlation Filter for Visual Tracking

Zhu

Peng

et al. 2022

IEEE Trans. Multimedia

Self Cite

View full text Add to dashboard Cite

Section: A Dcf-based Trackersmentioning

confidence: 99%

Bilateral Weighted Regression Ranking Model With Spatial-Temporal Correlation Filter for Visual Tracking

Zhu

Peng

et al. 2022

IEEE Trans. Multimedia

Self Cite

View full text Add to dashboard Cite

“…Naturally, video datasets can be represented as 4-th order streaming tensors of dimensionality, width × height × channel × time. Accordingly, there are several studies devoted to developing tensor-based visual trackers for better modeling the appearance of target objects, such as [80], [121]- [123], to name a few. For example, Hu et al in [80] proposed the so-called IRTSA tracker using incremental tensor subspace learning to capture the appearance of objects.…”

Section: Computer Visionmentioning

confidence: 99%

A Contemporary and Comprehensive Survey on Streaming Tensor Decomposition

Thanh¹,

abed-meraim²,

Linh-Trung³

et al. 2022

Preprint

View full text Add to dashboard Cite

<p>Tensor decomposition has been demonstrated to be successful in a wide range of applications, from neuroscience and wireless communications to social networks. In an online setting, factorizing tensors derived from multidimensional data streams is however non-trivial due to several inherent problems of real-time stream processing. In recent years, many research efforts have been dedicated to developing online techniques for decomposing such tensors, resulting in significant advances in streaming tensor decomposition or tensor tracking. This topic is emerging and enriches the literature on tensor decomposition, particularly from the data stream analystics perspective. Thus, it is imperative to carry out an overview of tensor tracking to help researchers and practitioners understand its development and achievements, summarise the current trends and advances, and identify challenging problems. In this article, we provide a contemporary and comprehensive survey on different types of tensor tracking techniques. We particularly categorize the state-of-the-art methods into three main groups: streaming CP decompositions, streaming Tucker decompositions, and streaming decompositions under other tensor formats (i.e., tensor-train, t-SVD, and BTD). In each group, we further divide the existing algorithms into sub-categories based on their main optimization framework and model architectures. Finally, we present several research challenges, open problems, and potential directions of tensor tracking in the future.</p>

show abstract

“…To align the face features, image normalization is necessary. Although, very good performance for the face and landmark localization has been shown by many researchers [21]. When it comes to the applications that requires an excellent accuracy such as facial behavior and motion.…”

Section: Face and Landmarks Detectionmentioning

confidence: 99%

Human expression recognition using facial shape based Fourier descriptors fusion

Shahid

Khan

Yan

2020

Twelfth International Conference on Machine Vision (ICMV 2019)

Self Cite

View full text Add to dashboard Cite

Dynamic facial expression recognition has many useful applications in social networks, multimedia content analysis, security systems and others. This challenging process must be done under recurrent problems of image illumination and low resolution which changes at partial occlusions. This paper aims to produce a new facial expression recognition method based on the changes in the facial muscles. The geometric features are used to specify the facial regions i.e., mouth, eyes, and nose. The generic Fourier shape descriptor in conjunction with elliptic Fourier shape descriptor is used as an attribute to represent different emotions under frequency spectrum features. Afterwards a multi-class support vector machine is applied for classification of seven human expression. The statistical analysis showed our approach obtained overall competent recognition using 5-fold cross validation with high accuracy on well-known facial expression dataset.

show abstract

An online spatio-temporal tensor learning model for visual tracking and its applications to facial expression recognition

Cited by 21 publications

References 24 publications

Bilateral Weighted Regression Ranking Model With Spatial-Temporal Correlation Filter for Visual Tracking

Bilateral Weighted Regression Ranking Model With Spatial-Temporal Correlation Filter for Visual Tracking

A Contemporary and Comprehensive Survey on Streaming Tensor Decomposition

Human expression recognition using facial shape based Fourier descriptors fusion

Contact Info

Product

Resources

About