Pic2Word: Mapping pictures to words for zero-shot composed image retrieval

Image retrieval plays a crucial role in search engines. Typically, their users rely on either image or text as a query to retrieve a desired target image. However, text-based retrieval has its limitations, as describing the target image accurately using words can be challenging. For instance, when searching for a fashion item, users may want an item whose specific attribute, e.g., the …

cloud cloud ai computer vision cvpr google google research image mapping multimodal learning natural language processing query research researcher retrieval role search team text words