Visible to the public Biblio

Filters: Keyword is Video compression  [Clear All Filters]
2023-07-13
Chen, Chen, Wang, Xingjun, Huang, Guanze, Liu, Guining.  2022.  An Efficient Randomly-Selective Video Encryption Algorithm. 2022 IEEE 8th International Conference on Computer and Communications (ICCC). :1287–1293.
A randomly-selective encryption (RSE) algorithm is proposed for HEVC video bitstream in this paper. It is a pioneer algorithm with high efficiency and security. The encryption process is completely independent of video compression process. A randomly-selective sequence (RSS) based on the RC4 algorithm is designed to determine the extraction position in the video bitstream. The extracted bytes are encrypted by AES-CTR to obtain the encrypted video. Based on the high efficiency video coding (HEV C) bitstream, the simulation and analysis results show that the proposed RSE algorithm has low time complexity and high security, which is a promising tool for video cryptographic applications.
2023-06-23
Choi, Hankaram, Bae, Yongchul.  2022.  Prediction of encoding bitrate for each CRF value using video features and deep learning. 2022 Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems (SCIS&ISIS). :1–2.

In this paper, we quantify elements representing video features and we propose the bitrate prediction of compressed encoding video using deep learning. Particularly, to overcome disadvantage that we cannot predict bitrate of compression video by using Constant Rate Factor (CRF), we use deep learning. We can find element of video feature with relationship of bitrate when we compress the video, and we can confirm its possibility to find relationship through various deep learning techniques.

Rajin, S M Ataul Karim, Murshed, Manzur, Paul, Manoranjan, Teng, Shyh Wei, Ma, Jiangang.  2022.  Human pose based video compression via forward-referencing using deep learning. 2022 IEEE International Conference on Visual Communications and Image Processing (VCIP). :1–5.

To exploit high temporal correlations in video frames of the same scene, the current frame is predicted from the already-encoded reference frames using block-based motion estimation and compensation techniques. While this approach can efficiently exploit the translation motion of the moving objects, it is susceptible to other types of affine motion and object occlusion/deocclusion. Recently, deep learning has been used to model the high-level structure of human pose in specific actions from short videos and then generate virtual frames in future time by predicting the pose using a generative adversarial network (GAN). Therefore, modelling the high-level structure of human pose is able to exploit semantic correlation by predicting human actions and determining its trajectory. Video surveillance applications will benefit as stored “big” surveillance data can be compressed by estimating human pose trajectories and generating future frames through semantic correlation. This paper explores a new way of video coding by modelling human pose from the already-encoded frames and using the generated frame at the current time as an additional forward-referencing frame. It is expected that the proposed approach can overcome the limitations of the traditional backward-referencing frames by predicting the blocks containing the moving objects with lower residuals. Our experimental results show that the proposed approach can achieve on average up to 2.83 dB PSNR gain and 25.93% bitrate savings for high motion video sequences compared to standard video coding.

ISSN: 2642-9357

P, Dayananda, Subramanian, Siddharth, Suresh, Vijayalakshmi, Shivalli, Rishab, Sinha, Shrinkhla.  2022.  Video Compression using Deep Neural Networks. 2022 Fourth International Conference on Cognitive Computing and Information Processing (CCIP). :1–5.

Advanced video compression is required due to the rise of online video content. A strong compression method can help convey video data effectively over a constrained bandwidth. We observed how more internet usage for video conferences, online gaming, and education led to decreased video quality from Netflix, YouTube, and other streaming services in Europe and other regions, particularly during the COVID-19 epidemic. They are represented in standard video compression algorithms as a succession of reference frames after residual frames, and these approaches are limited in their application. Deep learning's introduction and current advancements have the potential to overcome such problems. This study provides a deep learning-based video compression model that meets or exceeds current H.264 standards.

Ke, Zehui, Huang, Hailiang, Liang, Yingwei, Ding, Yi, Cheng, Xin, Wu, Qingyao.  2022.  Robust Video watermarking based on deep neural network and curriculum learning. 2022 IEEE International Conference on e-Business Engineering (ICEBE). :80–85.

With the rapid development of multimedia and short video, there is a growing concern for video copyright protection. Some work has been proposed to add some copyright or fingerprint information to the video to trace the source of the video when it is stolen and protect video copyright. This paper proposes a video watermarking method based on a deep neural network and curriculum learning for watermarking of sliced videos. The first frame of the segmented video is perturbed by an encoder network, which is invisible and can be distinguished by the decoder network. Our model is trained and tested on an online educational video dataset consisting of 2000 different video clips. Experimental results show that our method can successfully discriminate most watermarked and non-watermarked videos with low visual disturbance, which can be achieved even under a relatively high video compression rate(H.264 video compress with CRF 32).

Konuko, Goluck, Valenzise, Giuseppe, Lathuilière, Stéphane.  2022.  Ultra-Low Bitrate Video Conferencing Using Deep Image Animation. 2022 IEEE International Conference on Image Processing (ICIP). :3515–3520.

In this work we propose a novel deep learning approach for ultra-low bitrate video compression for video conferencing applications. To address the shortcomings of current video compression paradigms when the available bandwidth is extremely limited, we adopt a model-based approach that employs deep neural networks to encode motion information as keypoint displacement and reconstruct the video signal at the decoder side. The overall system is trained in an end-to-end fashion minimizing a reconstruction error on the encoder output. Objective and subjective quality evaluation experiments demonstrate that the proposed approach provides an average bitrate reduction for the same visual quality of more than 60% compared to HEVC.

ISSN: 2381-8549

Chen, Meixu, Webb, Richard, Bovik, Alan C..  2022.  Foveated MOVI-Codec: Foveation-based Deep Video Compression without Motion. 2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP). :1–5.

The requirements of much larger file sizes, different storage formats, and immersive viewing conditions pose significant challenges to the goals of compressing VR content. At the same time, the great potential of deep learning to advance progress on the video compression problem has driven a significant research effort. Because of the high bandwidth requirements of VR, there has also been significant interest in the use of space-variant, foveated compression protocols. We have integrated these techniques to create an end-to-end deep learning video compression framework. A feature of our new compression model is that it dispenses with the need for expensive search-based motion prediction computations by using displaced frame differences. We also implement foveation in our learning based approach, by introducing a Foveation Generator Unit (FGU) that generates foveation masks which direct the allocation of bits, significantly increasing compression efficiency while making it possible to retain an impression of little to no additional visual loss given an appropriate viewing geometry. Our experiment results reveal that our new compression model, which we call the Foveated MOtionless VIdeo Codec (Foveated MOVI-Codec), is able to efficiently compress videos without computing motion, while outperforming foveated version of both H.264 and H.265 on the widely used UVG dataset and on the HEVC Standard Class B Test Sequences.

2022-07-01
Yudin, Oleksandr, Artemov, Volodymyr, Krasnorutsky, Andrii, Barannik, Vladimir, Tupitsya, Ivan, Pris, Gennady.  2021.  Creating a Mathematical Model for Estimating the Impact of Errors in the Process of Reconstruction of Non-Uniform Code Structures on the Quality of Recoverable Video Images. 2021 IEEE 3rd International Conference on Advanced Trends in Information Theory (ATIT). :40—45.
Existing compression coding technologies are investigated using a statistical approach. The fundamental strategies used in the process of statistical coding of video information data are analyzed. Factors that have a significant impact on the reliability and efficiency of video delivery in the process of statistical coding are analyzed. A model for estimating the impact of errors in the process of reconstruction of uneven code structures on the quality of recoverable video images is being developed.The influence of errors that occur in data transmission channels on the reliability of the reconstructed video image is investigated.
2022-04-25
Hussain, Shehzeen, Neekhara, Paarth, Jere, Malhar, Koushanfar, Farinaz, McAuley, Julian.  2021.  Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples. 2021 IEEE Winter Conference on Applications of Computer Vision (WACV). :3347–3356.
Recent advances in video manipulation techniques have made the generation of fake videos more accessible than ever before. Manipulated videos can fuel disinformation and reduce trust in media. Therefore detection of fake videos has garnered immense interest in academia and industry. Recently developed Deepfake detection methods rely on Deep Neural Networks (DNNs) to distinguish AI-generated fake videos from real videos. In this work, we demonstrate that it is possible to bypass such detectors by adversarially modifying fake videos synthesized using existing Deepfake generation methods. We further demonstrate that our adversarial perturbations are robust to image and video compression codecs, making them a real-world threat. We present pipelines in both white-box and black-box attack scenarios that can fool DNN based Deepfake detectors into classifying fake videos as real.