Low-bitrate video compression remains a fundamental challenge in video coding. Recent advances in generative technologies show great potential for addressing this problem, yet existing generative models often suffer from uncontrollability caused by error accumulation and unpredictable semantic mutation. To tackle these issues, we propose a novel low-bitrate generative video compression framework based on a spatio-temporal diffusion model. A quality comparator is designed to select the optimal feature during generation, which effectively suppresses error accumulation. In addition, we design a Semantic Mutation Feature Extraction Network (SMFN) to accurately predict frame sequences, thereby effectively handling semantically mutated features. Extensive experiments demonstrate that our framework achieves superior performance on FVD and LPIPS metrics, significantly reducing bitrate while preserving both visual fidelity and semantic consistency.

End-to-end deep video compression in the feature space has become a key research direction, where effective feature modeling is essential. However, existing methods adopt a single-branch architecture, making it difficult to effectively perform feature modeling on complex video frames. To address this issue, we propose a Context and Fine-grained Fusion Module (CFFM), which adopts a dual-branch architecture for feature modeling. Each branch consists of two Fine-grained Spatial Aggregation Modules and two Dilated Contextual Residual Fusion Modules, focusing on local fine-grained details and global contextual information, respectively. By effectively capturing these complementary features, CFFM significantly enhances the overall feature modeling capability. Additionally, we introduce a Multi-Directional Motion Perception Module (MDMP), which integrates multi-directional and standard convolutions to dynamically expand the receptive field and adaptively model complex motion patterns, improving motion offset estimation. The entire framework is jointly optimized in an end-to-end manner. Experimental results show that our method outperforms traditional codecs and recent deep video compression approaches, achieving a 41.67% bitrate reduction compared to x265 with medium preset under PSNR, and obtaining a 3.54% gain over VVC under the MS-SSIM metric.

Fueled by advancements in intelligent transportation systems, the Internet of Vehicles (IoV) seeks to connect smart vehicles, road infrastructure, and users into a unified network, enhancing traffic efficiency and reducing accident risks. Centralized cloud data collection raises concerns about privacy and communication overhead. To address these, distributed edge intelligence (DEI) reduces transmission costs and improves privacy by implementing machine learning at the network edge. In this context, cooperative adaptive cruise control (CACC) systems, combined with DEI in the IoV framework, enhance transportation system intelligence through real-time data processing and decentralized decision making. This article proposes a modeling and analysis method for CACC systems based on Petri nets. The datasets are automatically generated using tools developed by our team, and machine-learning methods are utilized to perform risk prediction analysis on the CACC model. From the perspective of Petri nets synchronization, we propose risk mitigation strategies from a design standpoint. The research results show that the proposed method significantly reduces signal accumulation and enhances synchronization in CACC systems. This improvement provides new theoretical support and technical guidance for the design and implementation of CACC systems, ultimately enhancing their safety and reliability.