Exemplar-embed complex matrix factorization for facial expression recognition

Duong, Viet-Hang; Lee, Yuan-Shan; Ding, Jian-Jiun; Pham, Bach-Tung; Bui, Manh-Quan; Wang, Jia-Ching

doi:10.1109/icassp.2017.7952474

Cited by 5 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nguyen and Smeulders [43] used color invariants to discriminate targets from the background. Godec et al [44] employed HOG features for probabilistic matching. Held et al [45] used deep regression networks for matching.…”

Section: Template Matching-based Trackersmentioning

confidence: 99%

“…Recently, matrix factorization techniques have been extended to complex matrix factorizations (CMFs) where the input data are complex matrices. These models have been obtaining promising results in facial expression recognition and data representation tasks [43][44][45]. The main idea of complex methods for face and facial expression recognition is that the original signal is projected on to the complex field by a mapping such that the distances of two data points in the original space and projection space are equivalent.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Visual Object Tracking with Deep Neural Networks

Mazzeo¹,

Ramakrishnan²,

Spagnolo³

2019

View full text Add to dashboard Cite

Since then, he has been working on several research topics regarding artificial intelligence and computer vision. Dr. Mazzeo joined the Italian National Research Council of Italy (CNR) as a researcher in 2002. He is currently involved in projects for algorithms for video object tracking, face detection and recognition, facial expression recognition, deep neural networks, and machine learning. He has authored and co-authored 80 publications, including 10 papers published in international journals and book chapters. He has also co-authored five national and international patents. Dr. Mazzeo acts as a reviewer for several international journals and for some book publishers. Since 2004, he has been regularly invited to take part in the scientific committees of national and international conferences.Dr. Srinivasan Ramakrishnan has 20 years of teaching experience and one year of industry experience. He is a professor and the head of the

show abstract

Section: Template Matching-based Trackersmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Visual Object Tracking with Deep Neural Networks

Mazzeo¹,

Ramakrishnan²,

Spagnolo³

2019

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Matrix Factorization on Complex Domain for Face Recognition

Duong¹,

Bui²,

Wang³

2019

Visual Object Tracking With Deep Neural Networks

Self Cite

View full text Add to dashboard Cite

Matrix factorization on complex domain is a natural extension of nonnegative matrix factorization, but it is still a very new trend in face recognition. In this chapter, we present two complex matrix factorization-based models for face recognition, in which the objective functions are the real-valued functions of complex variables. Our first model aims to build a learned base, which is embedded within original space. The second model finds the base whose volume is maximized. Experimental results on datasets with and without outliers show that our proposed algorithms are more effective than competitive algorithms.

show abstract

“…Through this transformation space, the optimization problem using cosine dissimilarity in the real field will be replaced by an equivalent complex optimization problem where the Frobenious norm is employed for reconstruction error measurement [10], [11].…”

Section: Fast Robust Correlation and Image Representation In Complex mentioning

confidence: 99%

“…Motivated by the interesting works of Liwicki et al [9] and Duong et al [10], [11], which showed the effectiveness of projecting pixel intensity values to the complex plane, this work develops a new approach for data representation, named simplicial complex matrix factorization (siCMF). Herein, the cosine dissimilarity, used on the reconstruction error function, is exploited judiciously by transferring data from the real-valued space to the complex field.…”

Section: Introductionmentioning

confidence: 99%

A New Approach of Matrix Factorization on Complex Domain for Data Representation

Duong

Bui

Ding

et al. 2017

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYThis work presents a new approach which derives a learned data representation method through matrix factorization on the complex domain. In particular, we introduce an encoding matrix-a new representation of data-that satisfies the simplicial constraint of the projective basis matrix on the field of complex numbers. A complex optimization framework is provided. It employs the gradient descent method and computes the derivative of the cost function based on Wirtinger's calculus.

show abstract

Exemplar-embed complex matrix factorization for facial expression recognition

Cited by 5 publications

References 24 publications

Visual Object Tracking with Deep Neural Networks

Visual Object Tracking with Deep Neural Networks

Matrix Factorization on Complex Domain for Face Recognition

A New Approach of Matrix Factorization on Complex Domain for Data Representation

Contact Info

Product

Resources

About