Multiple Views and Categories Condition GAN for High Resolution Image

Doan, Huong-Giang

doi:10.1007/978-3-030-97610-1_40

Cited by 2 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They range from traditional techniques, such as rotate, slip, strength, and so on, to more complex techniques, such as the Generative Adversarial Network (GAN). For gesture data generation, GAN networks are mainly used to generate static gesture images from single viewpoint [9], [10] or multiple viewpoints [11], [12]. Some GAN-based networks are proposed for making synthetic videos of gestures or dynamic gestures.…”

Section: Introductionmentioning

confidence: 99%

An End-to-End Model of ArVi-MoCoGAN and C3D with Attention Unit for Arbitrary-view Dynamic Gesture Recognition

Doan,

Luong,

Pham

2024

IJACSA

View full text Add to dashboard Cite

Human gesture recognition is an attractive research area in computer vision with many applications such as humanmachine interaction, virtual reality, etc. Recent deep learning techniques have been efficiently applied for gesture recognition, but they require a large and diverse amount of training data. In fact, the available gesture datasets contain mostly static gestures and/or certain fixed viewpoints. Some contain dynamic gestures, but they are not diverse in poses and viewpoints. In this paper, we propose a novel end-to-end framework for dynamic gesture recognition from unknown viewpoints. It has two main components: (1) an efficient GAN-based architecture, named ArVi-MoCoGAN; (2) the gesture recognition component, which contains C3D backbones and an attention unit. ArVi-MoCoGAN aims at generating videos at multiple fixed viewpoints from a real dynamic gesture at an arbitrary viewpoint. It also returns the probability that a real arbitrary view gesture belongs to which of the fixed-viewpoint gestures. These outputs of ArVi-MoCoGAN will be processed in the next component to improve the arbitrary view recognition performance through multi-view synthetic gestures. The proposed system is extensively analyzed and evaluated on four standard dynamic gesture datasets. The experimental results of our proposed method are better than the current solutions, from 1% to 13.58% for arbitrary view gesture recognition and from 1.2% to 7.8% for single view gesture recognition.

show abstract

Section: Introductionmentioning

confidence: 99%

An End-to-End Model of ArVi-MoCoGAN and C3D with Attention Unit for Arbitrary-view Dynamic Gesture Recognition

Doan,

Luong,

Pham

2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…Hand gestures have proffered a natural and efficient way for human machine interaction. Until now, hand gestures have been deployed in certain applications such as hand-3D-Object manipulation [1], handrobot interactions [2], [3], hand-based surgery assistance [4], and hand-in-home appliance controlling [5], [6]. Such applications always require a high accurate recognition rate as well as a low computational cost.…”

Section: Introductionmentioning

confidence: 99%

“…The convolution neuron network (CNN) architectures [18]- [20] require a very large dataset [21], [22] to train models while existing hand gesture datasets have not adapted for this demand. In addition, even through traditional augmentation method (such as flip, rotate, scale, strength images) or generative adversarial network (GAN) method [6] that could not increase enough large hand gesture dataset.…”

Section: Introductionmentioning

confidence: 99%

New blender-based augmentation method with quantitative evaluation of CNNs for hand gesture recognition

Doan

Nguyen

2023

IJEECS

View full text Add to dashboard Cite

<p>In this study, we extensively analyze and evaluate the performance of recent deep neural networks (DNNs) for hand gesture recognition and static gestures in particular. To this end, we captured an unconstrained hand dataset with complex appearances, shapes, scales, backgrounds, and viewpoints. We then deployed some new trending convolution neuron networks (CNNs) for gesture classification. We arrived at three major conclusions: i) DenseNet121 architecture is the best recognition rate through almost evaluated red, green, blue (RGB) and augmentation datasets. Its performance is outstanding in most original works; ii) blender-based augmentation help to significantly increase 9% of accuracy, compared to the use of a RGB cues; iii) most CNNs can achieve impressive results at 97% accuracy when the training and testing datasets come from the same lab-based or constrained environment. Their performance is drastically reduced when dealing with gestures collected in unconstrained environments. In particular, we validated the best CNN on a new unconstrained dataset. We observed a significant reduction with an accuracy of only 74.55%. This performance can be improved up to 80.59% by strategies such as blender-based and/or GAN-based data augmentations to obtain an acceptable result of 83.17%. These findings contribute crucial factors and make fruitful recommendations for the development of a robust hand-based interface in practice</p>

show abstract

Multiple Views and Categories Condition GAN for High Resolution Image

Cited by 2 publications

References 16 publications

An End-to-End Model of ArVi-MoCoGAN and C3D with Attention Unit for Arbitrary-view Dynamic Gesture Recognition

An End-to-End Model of ArVi-MoCoGAN and C3D with Attention Unit for Arbitrary-view Dynamic Gesture Recognition

New blender-based augmentation method with quantitative evaluation of CNNs for hand gesture recognition

Contact Info

Product

Resources

About