Telling the What while Pointing the Where: Fine-grained Mouse Trace and Language Supervision for Improved Image Retrieval

Existing image retrieval systems use text queries to provide a natural and practical way for users to express what they are looking for. However, fine-grained image retrieval often requires the ability to also express the where in the image the content they are looking for is. The textual modality can only cumbersomely express such localization preferences, whereas pointing would be a natural fit. In this paper, we describe an image retrieval setup where the user simultaneously describes an image using both spoken natural language (the "what") and mouse traces over an empty canvas (the "where") to express the characteristics of the desired target image. To this end, we learn an image retrieval model using the Localized Narratives dataset, which is capable of performing early fusion between text descriptions and synchronized mouse traces. Qualitative and quantitative experiments show that our model is capable of taking this spatial guidance into account, and provides more accurate retrieval results compared to text-only equivalent systems.