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

In this paper we address the problem of unsupervised localization of objectsin single images. Compared to previous state-of-the-art method our method isfully unsupervised in the sense that there is no prior instance level orcategory level information about the image. Furthermore, we treat each imageindividually and do not rely on any neighboring image similarity. We employdeep-learning based generation of saliency maps and region proposals to tacklethis problem. First salient regions in the image are determined using anencoder/decoder architecture. The resulting saliency map is matched with regionproposals from a class agnostic region proposal network to roughly localize thecandidate object regions. These regions are further refined based on theoverlap and similarity ratios. Our experimental evaluations on a benchmarkdataset show that the method gets close to current state-of-the-art methods interms of localization accuracy even though these make use of multiple frames.Furthermore, we created a more challenging and realistic dataset with multipleobject categories and varying viewpoint and illumination conditions forevaluating the method's performance in real world scenarios.

Fusing Saliency Maps with Region Proposals for Unsupervised Object Localization