ECSAM: An Edge-cloud Video Analytics Architecture for the Segment Anything Model

作者：Rui Lu, Shouyong Shi, Dan Wang · 年份：2025 · DOI：10.1145/3769696.3771216 · 被引用次数：1 · 研究领域：IoT and Edge/Fog Computing、Context-Aware Activity Recognition Systems、Visual Attention and Saliency Detection

As artificial intelligence continues to evolve, it is increasingly capable of handling a wide range of video analytics tasks with a single large model. One of the key foundation technologies is the Segment Anything Model (SAM), which enables video analytics tasks to be determined on the fly based on user input prompts. However, achieving real-time response in video analytics applications is crucial for user experiences due to the limited communication and computation resources on the edge, especially with SAM, where users may continuously interact by adding or adjusting prompts.