Leveraging LLMs and generative models for interactive known-item video search

• Main Authors: MA, Zhixin, WU, Jiaxin, NGO, Chong-wah
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Generative Model; Interactive Video Retrieval; Known-Item Search; Large Language Models; Artificial Intelligence and Robotics; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/8748; https://ink.library.smu.edu.sg/context/sis_research/article/9751/viewcontent/24_MMM_av.pdf
• Institution: Singapore Management University

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.