English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We introduce the task of open-vocabulary visual instance search (OVIS). Givenan 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 "openvocabulary" means that there are neither restrictions to the visual instance tobe searched nor restrictions to the word that can be used to compose thetextual search query. We propose to address such a search challenge viavisual-semantic aligned representation learning (ViSA). ViSA leverages massiveimage-caption pairs as weak image-level (not instance-level) supervision tolearn a rich cross-modal semantic space where the representations of visualinstances (not images) and those of textual queries are aligned, thus allowingus to measure the similarities between any visual instance and an arbitrarytextual query. To evaluate the performance of ViSA, we build two datasets namedOVIS40 and OVIS1600 and also introduce a pipeline for error analysis. Throughextensive experiments on the two datasets, we demonstrate ViSA's ability tosearch for visual instances in images not available during training given awide range of textual queries including those composed of uncommon words.Experimental results show that ViSA achieves an mAP@50 of 21.9% on OVIS40 underthe most challenging setting and achieves an mAP@6 of 14.9% on OVIS1600dataset.

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