Telling the What while Pointing to the Where: Multimodal Queries for Image Retrieval
This work addresses the challenge of fine-grained image retrieval for users by enabling more intuitive and precise spatial content specification, improving retrieval accuracy.
This paper introduces a multimodal image retrieval system where users combine spoken natural language (what) with mouse traces on a blank canvas (where) to specify desired image content. The proposed model, a modification of an existing image retrieval system, effectively integrates spatial guidance, leading to significantly more accurate retrieval results compared to text-only systems.
Most existing image retrieval systems use text queries as a way for the user to express what they are looking for. However, fine-grained image retrieval often requires the ability to also express where in the image the content they are looking for is. The text modality can only cumbersomely express such localization preferences, whereas pointing is a more natural fit. In this paper, we propose an image retrieval setup with a new form of multimodal queries, where the user simultaneously uses both spoken natural language (the what) and mouse traces over an empty canvas (the where) to express the characteristics of the desired target image. We then describe simple modifications to an existing image retrieval model, enabling it to operate in this setup. Qualitative and quantitative experiments show that our model effectively takes this spatial guidance into account, and provides significantly more accurate retrieval results compared to text-only equivalent systems.