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 present a novel approach for oriented object detection, named TricubeNet,which localizes oriented objects using visual cues ($i.e.,$ heatmap) instead oforiented box offsets regression. We represent each object as a 2D Tricubekernel and extract bounding boxes using simple image-processing algorithms. Ourapproach is able to (1) obtain well-arranged boxes from visual cues, (2) solvethe angle discontinuity problem, and (3) can save computational complexity dueto our anchor-free modeling. To further boost the performance, we propose someeffective techniques for size-invariant loss, reducing false detections,extracting rotation-invariant features, and heatmap refinement. To demonstratethe effectiveness of our TricubeNet, we experiment on various tasks forweakly-occluded oriented object detection: detection in an aerial image,densely packed object image, and text image. The extensive experimental resultsshow that our TricubeNet is quite effective for oriented object detection. Codeis available at https://github.com/qjadud1994/TricubeNet.

TricubeNet: 2D Kernel-Based Object Representation for Weakly-Occluded Oriented Object Detection