Video data have become the main data traffic on the Internet, and their traffic is increasing explosively every year, thus increasing the pressure of video transmission. Video coding technology has become the key to compressing original videos. As an indispensable technology, rate control plays an important role in stabilizing video stream transmission. Rate control (RC) is part of rate distortion optimization (RDO) whose job is to find the optimal solution based on balancing rate and distortion. It not only needs to consider the buffer and network status but also adjust the corresponding bit rate according to the video content. This paper reviews the related technologies of rate control under high efficiency video coding (HEVC) and versatile video coding (VVC) standards so that subsequent researchers can quickly understand the field and promote the development of rate control algorithms. Firstly, the paper summarizes the various aspects of RC, including basic principles, rate-distortion models, major processes, and performance criteria. Secondly, the paper surveys, in detail, the research progress in the field of rate control and analyzes several mainstream research directions. Thirdly, we carry out relevant experiments on the standard reference software and analyze and discuss the experimental results of the existing studies. Finally, we look ahead to the future trends of rate control and provide feasible improvement suggestions.

The transferability of adversarial examples has been proven to be a potent tool for successful attacks on target models, even in challenging black-box environments. However, the majority of current research focuses on non-targeted attacks, making it arduous to enhance the transferability of targeted attacks using traditional methods. This paper identifies a crucial issue in existing gradient iteration algorithms that generate adversarial perturbations in a fixed manner. These perturbations have a detrimental impact on subsequent gradient computations, resulting in instability of the update direction after momentum accumulation. Consequently, the transferability of adversarial examples is negatively affected. To overcome this issue, we propose an approach called Adversarial Perturbation Transform (APT) that introduces a transformation to the perturbations at each iteration. APT randomly samples clean patches from the original image and replaces the corresponding patches in the iterative output image. This transformed image is then used to compute the next momentum. In addition, APT could seamlessly integrate with other iterative gradient-based algorithms, incurring minimal additional computational overhead. Experimental results demonstrate that APT significantly enhances the transferability of targeted attacks when combined with traditional methods. Our approach achieves this improvement while maintaining computational efficiency.

High Efficiency Video Coding (HEVC) achieves a significant improvement in compression efficiency at the cost of extremely high computational complexity. Therefore, large-scale and wide deployment applications, especially mobile real-time video applications under low-latency and power-constrained conditions, are more challenging. In order to solve the above problems, a fast decision method for intra-coding unit size based on a new fuzzy support vector machine classifier is proposed in this paper. The relationship between the depth levels of coding units is accurately expressed by defining the cost evaluation criteria of texture and non-texture rate-distortion cost. The fuzzy support vector machine is improved by using the information entropy measure to solve the negative impact of data noise and the outliers problem. The proposed method includes three stages: the optimal coded depth level “0” early decision, coding unit depth early skip, and optimal coding unit early terminate. In order to further improve the rate-distortion complexity optimization performance, more feature vectors are introduced, including features such as space complexity, the relationship between coding unit depths, and rate-distortion cost. The experimental results showed that, compared with the HEVC reference test model HM16.5, the proposed algorithm can reduce the encoding time of various test video sequences by more than 53.24% on average, while the Bjontegaard Delta Bit Rate (BDBR) only increases by 0.82%. In addition, the proposed algorithm is better than the existing algorithms in terms of comprehensively reducing the computational complexity and maintaining the rate-distortion performance.

Human pose estimation (HPE) is a fundamental challenge in computer vision, aiming to detect anatomical keypoints in images. Traditional methods rely on CNN models, but recent advancements in Vision Transformer (ViT) models have shown superior performance. However, ViTs often require substantial computational resources. This paper introduces SPTPose, a method that employs self-distillation and token pruning to reduce computational costs while maintaining high performance. Our SPTPose-B achieves a mAP of 74.8% on the MSCOCO validation set with only 13.2 million parameters and 4.7 GFLOPs. The source code is available at https://github.com/duduxx123/SPTPose.

Human pose estimation (HPE) is a fundamental challenge in computer vision, aiming to detect anatomical keypoints in images. Traditional methods rely on CNN models, but recent advancements in Vision Transformer (ViT) models have shown superior performance. However, ViTs often require substantial computational resources. This paper introduces SPTPose, a method that employs self-distillation and token pruning to reduce computational costs while maintaining high performance. Our SPTPose-B achieves a mAP of 74.8% on the MSCOCO validation set with only 13.2 million parameters and 4.7 GFLOPs. The source code is available at https://github.com/duduxx123/SPTPose.