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

Image retrieval is a fundamental task in computer vision. Despite recentadvances in this field, many techniques have been evaluated on a limited numberof domains, with a small number of instance categories. Notably, most existingworks only consider domains like 3D landmarks, making it difficult togeneralize the conclusions made by these works to other domains, e.g., logo andother 2D flat objects. To bridge this gap, we introduce a new dataset forbenchmarking visual search methods on flat images with diverse patterns. Ourflat object retrieval benchmark (FORB) supplements the commonly adopted 3Dobject domain, and more importantly, it serves as a testbed for assessing theimage embedding quality on out-of-distribution domains. In this benchmark weinvestigate the retrieval accuracy of representative methods in terms ofcandidate ranks, as well as matching score margin, a viewpoint which is largelyignored by many works. Our experiments not only highlight the challenges andrich heterogeneity of FORB, but also reveal the hidden properties of differentretrieval strategies. The proposed benchmark is a growing project and we expectto expand in both quantity and variety of objects. The dataset and supportingcodes are available at https://github.com/pxiangwu/FORB/.

FORB: A Flat Object Retrieval Benchmark for Universal Image Embedding