A GAN-Based Video Intra Coding

Zhong, Guangyu; Wang, Jun; Hu, Jiyuan; Li, Fan

doi:10.3390/electronics10020132

Cited by 6 publications

(2 citation statements)

References 33 publications

(94 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A new semantic image inpainting model was proposed by Yeh et al [390] based on GAN MA, whereby semantic inpainting was viewed as an issue of image generation. Their adversarial model [391,392] had been trained to seek encoding of corrupted image 'closest' to the target image in latent space. Next, the image is reconstructed using G via encoding.…”

Section: Image Inpaintingmentioning

confidence: 99%

A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications

et al. 2023

View full text Add to dashboard Cite

Data scarcity is a major challenge when training deep learning (DL) models. DL demands a large amount of data to achieve exceptional performance. Unfortunately, many applications have small or inadequate data to train DL frameworks. Usually, manual labeling is needed to provide labeled data, which typically involves human annotators with a vast background of knowledge. This annotation process is costly, time-consuming, and error-prone. Usually, every DL framework is fed by a significant amount of labeled data to automatically learn representations. Ultimately, a larger amount of data would generate a better DL model and its performance is also application dependent. This issue is the main barrier for many applications dismissing the use of DL. Having sufficient data is the first step toward any successful and trustworthy DL application. This paper presents a holistic survey on state-of-the-art techniques to deal with training DL models to overcome three challenges including small, imbalanced datasets, and lack of generalization. This survey starts by listing the learning techniques. Next, the types of DL architectures are introduced. After that, state-of-the-art solutions to address the issue of lack of training data are listed, such as Transfer Learning (TL), Self-Supervised Learning (SSL), Generative Adversarial Networks (GANs), Model Architecture (MA), Physics-Informed Neural Network (PINN), and Deep Synthetic Minority Oversampling Technique (DeepSMOTE). Then, these solutions were followed by some related tips about data acquisition needed prior to training purposes, as well as recommendations for ensuring the trustworthiness of the training dataset. The survey ends with a list of applications that suffer from data scarcity, several alternatives are proposed in order to generate more data in each application including Electromagnetic Imaging (EMI), Civil Structural Health Monitoring, Medical imaging, Meteorology, Wireless Communications, Fluid Mechanics, Microelectromechanical system, and Cybersecurity. To the best of the authors’ knowledge, this is the first review that offers a comprehensive overview on strategies to tackle data scarcity in DL.

show abstract

Section: Image Inpaintingmentioning

confidence: 99%

A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In addition, matrix coding is used to encrypt the video. Zhong et al (2021) proposed a Generative Adversarial Network (GAN)based intra prediction approach to enhance intra prediction accuracy. Gan's good training generator acts as the mapping from the adjacent reconstructed signal to the PU, and is applied to the encoder and decoder to reduce the bit rate in the experimental results.…”

mentioning

confidence: 99%

HEVC Information-Hiding Algorithm Based on Intra-Prediction and Matrix Coding

Liu

2021

International Journal of Digital Crime and Forensics

View full text Add to dashboard Cite

Aiming at the problem that the data hiding algorithm of high efficiency video coding (HEVC) has great influence on the video bit rate and visual quality, an information hiding algorithm based on intra prediction mode and matrix coding is proposed. Firstly, 8 prediction modes are selected from 4×4 luminance blocks in I frame to embed the hidden information. Then, the Least Significant Bit (LSB) algorithm is used to modulate the LSB of the last prediction mode. Finally, the modulated luminance block is re-encoded to embed 4 bits secret information. Experimental results show that the algorithm improves the embedding capacity, guarantees the subjective and objective quality of the video, and the bit rate increases by 1.14% on average.

show abstract