Deep Convolutional Neural Network for Age Estimation based on VGG-Face Model

Qawaqneh, Zakariya; Mallouh, Arafat Abu; Barkana, Buket D.

doi:10.48550/arxiv.1709.01664

Cited by 11 publications

(16 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Importance of two-and three-body interactions in aluminum, tungsten and carbon. For every dataset the following information is included: 1) standard deviation of ab initio energies in the dataset; 2) standard deviation of energies predicted by only two-body component of two-and three-body potential; 3) same for three-body component; 4) RMSE error of only two-body potential; 5) RMSE error of two-and three-body potential; [6][7][8][9][10]…”

Section: Discussionmentioning

confidence: 99%

“…Regression problem is one of the standard problems of machine learning. Examples are varying from prediction of age by photo [10] to prediction of number of comments a blog post will receive based on its features [11]. The approximation of the PES can be also formulated as a regression problem and the general scheme is the following: first, energies and forces are calculated by ab initio methods for some set of structures, next, this dataset is used to fit some machine learning model and after that it can be used to efficiently and accurately predict energies and forces for new structures.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast general two- and three-body interatomic potential

Pozdnyakov¹,

Oganov²,

Mazhnik³

et al. 2019

Preprint

View full text Add to dashboard Cite

We introduce a new class of machine learning interatomic potentials-fast General Two-and Three-body Potential (GTTP) which are as fast as conventional empirical potentials and require computational time that remains constant with increasing fitting flexibility. GTTP does not contain any assumptions about functional form of two-and three-body interactions. These interactions can be modeled arbitrarily accurately potentially by thousands of parameters not affecting resulting computational cost. Time complexity is O(1) per every considered pair or triple of atoms. The fitting procedure is reduced to simple linear regression on ab initio calculated energies and forces and leads to effective two-and three-body potential which reproduces quantum many-body interactions as accurately as possible. Our potential can be made continuously differentiable any number of times at the expense of increased computational time. We made a number of performance tests on one-, two-and three-component systems. Flexibility of the introduced approach makes the potential transferable in terms of size and type of atomic systems. We show, that trained on randomly generated structures with just 8 atoms in the unit cell, it significantly outperforms common empirical interatomic potentials in the study of large systems, such as grain boundaries in polycrystalline materials.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fast general two- and three-body interatomic potential

Pozdnyakov¹,

Oganov²,

Mazhnik³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…ResNet-50 is used for processing the body regions in the image. VGG Face-16 is a suitable fit for the task since it is a deep CNN model that was trained on a database for face recognition task [9]. They used ResNet-50 since the body region has more texture, color, and shape.…”

Section: Cnn-based Multi-modal Deep Learning For Person Re-identifica...mentioning

confidence: 99%

Multi-Modal Long-Term Person Re-Identification Using Physical Soft Bio-Metrics and Body Figure

2022

View full text Add to dashboard Cite

Person re-identification is the task of recognizing a subject across different non-overlapping cameras across different views and times. Most state-of-the-art datasets and proposed solutions tend to address the problem of short-term re-identification. Those models can re-identify a person as long as they are wearing the same clothes. The work presented in this paper addresses the task of long-term re-identification. Therefore, the proposed model is trained on a dataset that incorporates clothes variation. This paper proposes a multi-modal person re-identification model. The first modality includes soft bio-metrics: hair, face, neck, shoulders, and part of the chest. The second modality is the remaining body figure that mainly focuses on clothes. The proposed model is composed of two separate neural networks, one for each modality. For the first modality, a two-stream Siamese network with pre-trained FaceNet as a feature extractor for the first modality is utilized. Part-based Convolutional Baseline classifier with a feature extractor network OSNet for the second modality. Experiments confirm that the proposed model can outperform several state-of-the-art models achieving 81.4 % accuracy on Rank-1, 82.3% accuracy on Rank-5, 83.1% accuracy on Rank-10, and 83.7% accuracy on Rank-20.

show abstract

“…Researchers have investigated many approaches to address illumination issues for face recognition [7], [8], [9], [10], [11], [12], [13], [14], [15], [16], [6], [17], [18], [19]. These approaches can be broadly categorized into three sub types: invariant feature extraction, 3D face modeling, and data augmentation.…”

Section: Introductionmentioning

confidence: 99%

“…However, these methods require many training images with different lighting conditions to construct such a generative model. More recently, deep learning methods have been employed for face recognition [11], [12], [13], [14]. These end-to-end solutions leverage a large number of training images and can result in increased performance in standard face recognition tasks [20].…”

Section: Introductionmentioning

confidence: 99%

Local Sliced-Wasserstein Feature Sets for Illumination-invariant Face Recognition

Zhou¹,

Li²,

Shifat‐E‐Rabbi³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present a new method for face recognition from digital images acquired under varying illumination conditions. The method is based on mathematical modeling of local gradient distributions using the Radon Cumulative Distribution Transform (R-CDT) [1]. We demonstrate that lighting variations cause certain types of deformations of local image gradient distributions which, when expressed in R-CDT domain, can be modeled as a subspace. Face recognition is then performed using a nearest subspace in R-CDT domain of local gradient distributions. Experiment results demonstrate the proposed method outperforms other alternatives in several face recognition tasks with challenging illumination conditions. Python code implementing the proposed method is available at [2], which is integrated as a part of the software package PyTransKit [3].

show abstract

Deep Convolutional Neural Network for Age Estimation based on VGG-Face Model

Cited by 11 publications

References 0 publications

Fast general two- and three-body interatomic potential

Fast general two- and three-body interatomic potential

Multi-Modal Long-Term Person Re-Identification Using Physical Soft Bio-Metrics and Body Figure

Local Sliced-Wasserstein Feature Sets for Illumination-invariant Face Recognition

Contact Info

Product

Resources

About