Leveraging LLMs and Generative Models for Interactive Known-Item Video Search

While embedding techniques such as CLIP have considerably boosted search performance, user strategies in interactive video search still largely operate on a trial-and-error basis. Users are often required to manually adjust their queries and carefully inspect the search results, which greatly rely on the users’ capability and proficiency. Recent advancements in large language models (LLMs) and generative models offer promising avenues for enhancing interactivity in video retrieval and reducing the personal bias in query interpretation, particularly in the known-item search. Specifically, LLMs can expand and diversify the semantics of the queries while avoiding grammar mistakes or the language barrier. In addition, generative models have the ability to imagine or visualize the verbose query as images. We integrate these new LLM capabilities into our existing system and evaluate their effectiveness on V3C1 and V3C2 datasets. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.