JumpDASH: LLM-Based Content Perception for Intelligent Jumping DASH in Mobile Adaptive Video Streaming

Traditional Adaptive Bitrate (ABR) schemes assume that users watch videos sequentially, focusing solely on the sequential downloading of video chunks. However, these schemes often result in significant degradation of Quality of Experience (QoE) when users skip directly to their preferred segments. To address this issue, we propose JumpDASH, which leverages Large Language Model (LLM)-based content perception to enhance mobile adaptive video streaming. First, JumpDASH incorporates a low-cost video text summarization module based on large language models, enabling users to identify and navigate to the most relevant sections of videos. Second, we introduce a dynamic partitioned buffer and a Proximal Policy Optimization (PPO)-based ABR algorithm to facilitate prefetching video chunks corresponding to the perceived points of interest, along with differentiated encoding techniques to further minimize rebuffering. Extensive experiments conducted using real trace datasets under actual network conditions show that JumpDASH improves QoE by 13.82% to 262.94% compared to existing ABR technologies.