边云协同理解长视频流，省带宽又保精度。
CoVStream: Edge-Cloud Collaboration for Understanding of Long Video Streams
- 边缘端提炼视觉特征和语义摘要，减少传输数据量
- 云端构建实体图与全局上下文，仅在查询时启用大模型推理
- 在多个数据集上实现99.2%精度，带宽降低87.6%
长时连续视频流正成为多媒体智能的关键驱动力。现有方法多采用采样-编码-推理流程，依赖大模型处理长视频，但忽视了视频源常来自计算能力受限的设备这一现实。这导致两难困境：云端推理虽能力强，却带来高昂带宽开销；本地处理则受限于边缘硬件性能。为此，我们提出 CoVStream，首个面向长视频流理解的边云协同框架。边缘节点将原始视频流压缩为紧凑的视觉特征与语义字幕传至云端，显著降低带宽消耗；云端服务器则整合这些信息构建实体图与全局视觉上下文，并仅在用户查询到达时激活重型推理模型。在 VideoMME-Long、LVBench 与 RTV-Bench 上的实验表明，CoVStream 在保留 LVBench 上 99.2% 云基线精度的同时，将带宽使用降低 87.6%。
原文摘要 · Abstract (English)
Long, continuous video streams are an increasingly critical driver of multimedia intelligence. Existing efforts often handle long videos with a sample-encode-reason approach using large models. However, they overlook a crucial deployment fact: the stream is often produced by computationally constrained devices. This forces an untenable compromise: cloud offloading unlocks strong reasoning but incurs prohibitive bandwidth overhead, while on-device processing remains limited by edge hardware capacity. Therefore, we propose CoVStream, the first edge-cloud collaborative framework for understanding long video streams. The edge node distills raw video streams into compact visual features and semantic captions for transmission to the cloud, minimizing bandwidth costs, while the cloud server integrates this data into an entity graph and global visual context, activating the heavy reasoning model only when a user query arrives. Experiments on VideoMME-Long, LVBench, and RTV-Bench show that CoVStream reduces bandwidth usage by 87.6% while retaining 99.2% of the cloud baseline accuracy on LVBench.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。