ViewsInsight2.0: Enhancing Video Retrieval for VBS 2025 with an Automatic Query Generator Powered by Large Language Models
摘要
We present ViewsInsight2.0, an advanced iteration of the ViewsInsight system, purpose-built for the Video Browser Showdown (VBS) 2025. ViewsInsight2.0 retains the core strengths of ViewsInsight while introducing significant enhancements to address previous performance limitations. This optimized architecture is designed to deliver exceptional search capabilities tailored for VBS 2025. At its core, ViewsInsight2.0 integrates the CLIP (Contrastive Language-Image Pre-training) model, trained on DFN-5B. Furthermore, we have refined our temporal query mechanism with a more efficient algorithm and a user-friendly interface. In addition, ViewsInsight2.0 utilizes an automatic query generator powered by open-source large language models to efficiently optimize user input queries.