AI RESEARCH
Memory-Augmented Query Intent Understanding for Efficient Chat-based Image Retrieval
arXiv CS.CV
•
ArXi:2605.17365v1 Announce Type: new Different from traditional text-to-image retrieval tasks, chat-based image retrieval allows the human-interactive system to iteratively clarify and refine user intent through multi-round dialogue, thereby achieving fine-grained retrieval results. The key challenge in this task lies in dynamically understanding and updating the user's query intent across dialogue rounds.