U-CESE: Unified Clip-based Event Search Engine for AI Challenge HCMC 2025
Researchers have developed U-CESE, a Unified Clip-based Event Search Engine designed for the AI Challenge HCMC 2025. This system aims to improve the retrieval of events from large video datasets by integrating multiple modules into a cohesive framework. Key innovations include a Unified Clipping Algorithm for efficient processing, a DAKE method for lightweight keyframe extraction using JPEG file size variations, and ReCap, a captioning framework that generates temporally consistent descriptions. AI
IMPACT Introduces novel methods for efficient video event retrieval and keyframe extraction, potentially improving AI systems that process large video datasets.