Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian

Cao, Zhiwen; Liu, Dongfang; Wang, Qifan; Chen, Yingjie

doi:10.1007/978-3-031-19775-8_43

Cited by 22 publications

(4 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For label distribution construction, the spherical Fibonacci lattice algorithm proposed by González [ 66 ] can be used for point sampling and obtaining a distribution that possesses unbiased expectation. Afterwards, the loss function introduced in [ 67 ] can be introduced into the modeling framework, with an attempt to understand the corresponding parameters of each input sample.…”

Section: Discussion and Limitationsmentioning

confidence: 99%

Application of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game Design

Mak

Han

Yin

2023

Sensors

View full text Add to dashboard Cite

In recent decades, the Variational AutoEncoder (VAE) model has shown good potential and capability in image generation and dimensionality reduction. The combination of VAE and various machine learning frameworks has also worked effectively in different daily life applications, however its possible use and effectiveness in modern game design has seldom been explored nor assessed. The use of its feature extractor for data clustering has also been minimally discussed in the literature neither. This study first attempts to explore different mathematical properties of the VAE model, in particular, the theoretical framework of the encoding and decoding processes, the possible achievable lower bound and loss functions of different applications; then applies the established VAE model to generate new game levels based on two well-known game settings; and to validate the effectiveness of its data clustering mechanism with the aid of the Modified National Institute of Standards and Technology (MNIST) database. Respective statistical metrics and assessments are also utilized to evaluate the performance of the proposed VAE model in aforementioned case studies. Based on the statistical and graphical results, several potential deficiencies, for example, difficulties in handling high-dimensional and vast datasets, as well as insufficient clarity of outputs are discussed; then measures of future enhancement, such as tokenization and the combination of VAE and GAN models, are also outlined. Hopefully, this can ultimately maximize the strengths and advantages of VAE for future game design tasks and relevant industrial missions.

show abstract

Section: Discussion and Limitationsmentioning

confidence: 99%

Application of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game Design

Mak

Han

Yin

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Nowadays, learning-based methods using AI are found in every aspect of society. For instance, Cao et al [12] suggested a novel label distribution learning (LDL) method in the domain of computer vision. The authors implemented the LDL approach using Anisotropic Spherical Gaussian (ASG) in order to predict face orientation from a single RGB image.…”

Section: Literature Reviewmentioning

confidence: 99%

Emotional Speaker Verification Using Novel Modified Capsule Neural Network

Nassif

Shahin²,

Nemmour³

et al. 2023

Mathematics

View full text Add to dashboard Cite

Capsule Neural Network (CapsNet) models are regarded as efficient substitutes for convolutional neural networks (CNN) due to their powerful hierarchical representation capability. Nevertheless, CNN endure their inability of recording spatial information in spectrograms. The main constraint of CapsNet is related to the compression method which can be implemented in CNN models but cannot be directly employed in CapsNet. As a result, we propose a novel architecture based on dual-channel long short-term memory compressed CapsNet (DC-LSTM–COMP CapsNet) for speaker verification in emotional as well as stressful talking environments. The proposed approach is perceived as a modified Capsule network that attempts to overcome the limitations that exist within the original CapsNet, as well as in CNN while enhancing the verification performance. The proposed architecture is assessed on four distinct databases. The experimental analysis reveals that the average speaker verification performance is improved in comparison with CNN, the original CapsNet, as well as the conventional classifiers. The proposed algorithm notably achieves the best verification accuracy across the four speech databases. For example, using the Emirati dataset, the average percentage equal error rates (EERs) obtained is 10.50%, based on the proposed architecture which outperforms other deep and classical models.

show abstract

“…In the past decade, the computer vision community has achieved significant progress in many tasks with the development of deep learning [1]- [4]. Among various visual tasks, instance segmentation [5] has drawn wide attention due to its importance in many emerging applications, such as autonomous driving [6]- [11], augmented reality [12], [13], and video captioning [14], [15]. Technically, it is quite challenging as it is a compound task consisting of both object detection and segmentation, each of which is a difficult task and has been studied for a long time.…”

Section: Introductionmentioning

confidence: 99%

Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation

Cui,

Han,

Liu

2024

ACM J. Auton. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

The advancement of computer vision has pushed visual analysis tasks from still images to the video domain. In recent years, video instance segmentation, which aims to track and segment multiple objects in video frames, has drawn much attention for its potential applications in various emerging areas such as autonomous driving, intelligent transportation, and smart retail. In this paper, we propose an effective framework for instance-level visual analysis on video frames, which can simultaneously conduct object detection, instance segmentation, and multi-object tracking. The core idea of our method is collaborative multi-task learning which is achieved by a novel structure, named associative connections among detection, segmentation, and tracking task heads in an end-to-end learnable CNN. These additional connections allow information propagation across multiple related tasks, so as to benefit these tasks simultaneously. We evaluate the proposed method extensively on KITTI MOTS and MOTS Challenge datasets and obtain quite encouraging results.

show abstract

Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian

Cited by 22 publications

References 49 publications

Application of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game Design

Application of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game Design

Emotional Speaker Verification Using Novel Modified Capsule Neural Network

Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation

Contact Info

Product

Resources

About