Et Al. K. Dinesh Kumar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Et Al. K. Dinesh Kumar has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Dona Valy
Department of Information and Communication Engineering, Institute of Technology of Cambodia, Phnom Penh, Cambodia
1 shared publication - Sarot Srang
Department of Industrial and Mechanical Engineering, Institute of Technology of Cambodia
1 shared publication
Latest Publications
- Open Access
- 27 October 2023
- Published by Auricle Technologies, Pvt., Ltd. in International Journal on Recent and Innovation Trends in Computing and Communication
- Vol. 11 (9) , 1899-1906
Visual Storytelling: A Generative Adversarial Networks (GANs) and Graph Embedding Framework
Visual storytelling is a powerful educational tool, using image sequences to convey complex ideas and establish emotional connections with the audience. A study at the Chinese University of Hong Kong found that 92.7% of students prefer visual storytelling through animation over text alone [21]. Our approach integrates dual coding and propositional theory to generate visual representations of text, such as graphs and images, thereby enhancing students' memory retention and visualization skills. We use Generative Adversarial Networks (GANs) with graph data to generate images while preserving semantic consistency across objects, encompassing their attributes and relationships. By incorporating graph embedding, which includes node and relation embedding, we further enhance the semantic consistency of the generated high-quality images, improving the effectiveness of visual storytelling in education.
- 27 October 2023
- Published by Auricle Technologies, Pvt., Ltd. in International Journal on Recent and Innovation Trends in Computing and Communication
- Vol. 11 (9) , 1899-1906
Open AccessVisual Storytelling: A Generative Adversarial Networks (GANs) and Graph Embedding Framework
Visual storytelling is a powerful educational tool, using image sequences to convey complex ideas and establish emotional connections with the audience. A study at the Chinese University of Hong Kong found that 92.7% of students prefer visual storytelling through animation over text alone [21]. Our approach integrates dual coding and propositional theory to generate visual representations of text, such as graphs and images, thereby enhancing students' memory retention and visualization skills. We use Generative Adversarial Networks (GANs) with graph data to generate images while preserving semantic consistency across objects, encompassing their attributes and relationships. By incorporating graph embedding, which includes node and relation embedding, we further enhance the semantic consistency of the generated high-quality images, improving the effectiveness of visual storytelling in education.
- Open Access
- 18 August 2023
- Published by Auricle Technologies, Pvt., Ltd. in International Journal on Recent and Innovation Trends in Computing and Communication
- Vol. 11 (8s) , 618-627
Evaluating Text-to-Image GANs Performance: A Comparative Analysis of Evaluation Metrics
Generative Adversarial Networks (GANs) have emerged as powerful techniques for generating high-quality images in various domains but assessing how realistic the generated images are is a challenging task. To address this issue, researchers have proposed a variety of evaluation metrics for GANs, each with its own strengths and limitations. This paper presents a comprehensive analysis of popular GAN evaluation metrics, including FID, Mode Score, Inception Score, MMD, PSNR, and SSIM. The strengths, weaknesses, and calculation processes of these metrics are discussed, focusing on assessing image fidelity and diversity. Two approaches, pixel distance, and feature distance, are employed to measure image similarity, while the importance of evaluating individual objects using input captions is emphasized. Experimental results on a basic GAN trained on the MNIST dataset demonstrate improvement in various metrics across different epochs. The FID score decreases from 497.54594 at Epoch 0 to 136.91156 at Epoch 100, indicating improved differentiation between real and generated images. In addition, the Inception Score increases from 1.1533 to 1.6408, reflecting enhanced image quality and diversity. These findings highlight the effectiveness of the GAN model in generating more realistic and diverse images with training progression. However, when it comes to evaluating GANs on complex datasets, challenges arise, highlighting the need to combine evaluation metrics with visual inspection and subjective measures of image quality. By adopting a comprehensive evaluation approach, researchers can gain a deeper understanding of GAN performance and guide the development of advanced models.
- 18 August 2023
- Published by Auricle Technologies, Pvt., Ltd. in International Journal on Recent and Innovation Trends in Computing and Communication
- Vol. 11 (8s) , 618-627
Open AccessEvaluating Text-to-Image GANs Performance: A Comparative Analysis of Evaluation Metrics
Generative Adversarial Networks (GANs) have emerged as powerful techniques for generating high-quality images in various domains but assessing how realistic the generated images are is a challenging task. To address this issue, researchers have proposed a variety of evaluation metrics for GANs, each with its own strengths and limitations. This paper presents a comprehensive analysis of popular GAN evaluation metrics, including FID, Mode Score, Inception Score, MMD, PSNR, and SSIM. The strengths, weaknesses, and calculation processes of these metrics are discussed, focusing on assessing image fidelity and diversity. Two approaches, pixel distance, and feature distance, are employed to measure image similarity, while the importance of evaluating individual objects using input captions is emphasized. Experimental results on a basic GAN trained on the MNIST dataset demonstrate improvement in various metrics across different epochs. The FID score decreases from 497.54594 at Epoch 0 to 136.91156 at Epoch 100, indicating improved differentiation between real and generated images. In addition, the Inception Score increases from 1.1533 to 1.6408, reflecting enhanced image quality and diversity. These findings highlight the effectiveness of the GAN model in generating more realistic and diverse images with training progression. However, when it comes to evaluating GANs on complex datasets, challenges arise, highlighting the need to combine evaluation metrics with visual inspection and subjective measures of image quality. By adopting a comprehensive evaluation approach, researchers can gain a deeper understanding of GAN performance and guide the development of advanced models.