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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Due to the large success in object detection and instance segmentation, MaskR-CNN attracts great attention and is widely adopted as a strong baseline forarbitrary-shaped scene text detection and spotting. However, two issues remainto be settled. The first is dense text case, which is easy to be neglected butquite practical. There may exist multiple instances in one proposal, whichmakes it difficult for the mask head to distinguish different instances anddegrades the performance. In this work, we argue that the performancedegradation results from the learning confusion issue in the mask head. Wepropose to use an MLP decoder instead of the "deconv-conv" decoder in the maskhead, which alleviates the issue and promotes robustness significantly. And wepropose instance-aware mask learning in which the mask head learns to predictthe shape of the whole instance rather than classify each pixel to text ornon-text. With instance-aware mask learning, the mask branch can learnseparated and compact masks. The second is that due to large variations inscale and aspect ratio, RPN needs complicated anchor settings, making it hardto maintain and transfer across different datasets. To settle this issue, wepropose an adaptive label assignment in which all instances especially thosewith extreme aspect ratios are guaranteed to be associated with enough anchors.Equipped with these components, the proposed method named MAYOR achievesstate-of-the-art performance on five benchmarks including DAST1500, MSRA-TD500,ICDAR2015, CTW1500, and Total-Text.

Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection