OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning

Understand

We introduce the task of open-vocabulary visual instance search (OVIS).

• Given an arbitrary textual search query, Open-vocabulary Visual Instance Search (OVIS) aims to return a ranked list of visual instances, i.e., image patches, that satisfies the search intent from an image database.
• The term "open vocabulary" means that there are neither restrictions to the visual instance to be searched nor restrictions to the word that can be used to compose the textual search query.
• We propose to address such a search challenge via visual-semantic aligned representation learning (ViSA).