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

As an important component of the detector localization branch, bounding boxregression loss plays a significant role in object detection tasks. Theexisting bounding box regression methods usually consider the geometricrelationship between the GT box and the predicted box, and calculate the lossby using the relative position and shape of the bounding boxes, while ignoringthe influence of inherent properties such as the shape and scale of thebounding boxes on bounding box regression. In order to make up for theshortcomings of existing research, this article proposes a bounding boxregression method that focuses on the shape and scale of the bounding boxitself. Firstly, we analyzed the regression characteristics of the boundingboxes and found that the shape and scale factors of the bounding boxesthemselves will have an impact on the regression results. Based on the aboveconclusions, we propose the Shape IoU method, which can calculate the loss byfocusing on the shape and scale of the bounding box itself, thereby making thebounding box regression more accurate. Finally, we validated our method througha large number of comparative experiments, which showed that our method caneffectively improve detection performance and outperform existing methods,achieving state-of-the-art performance in different detection tasks.Code isavailable at https://github.com/malagoutou/Shape-IoU

Shape-IoU: More Accurate Metric considering Bounding Box Shape and Scale