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

Recognizing an event in an image can be enhanced by detecting relevantobjects in two ways: 1) indirectly utilizing object detection informationwithin the unified architecture or 2) directly making use of the objectdetection output results. We introduce a novel approach, referred to asDoubly-injected Object Detection CNN (DOD-CNN), exploiting the objectinformation in both ways for the task of event recognition. The structure ofthis network is inspired by the Integrated Object Detection CNN (IOD-CNN) whereobject information is indirectly exploited by the event recognition modulethrough the shared portion of the network. In the DOD-CNN architecture, theintermediate object detection outputs are directly injected into the eventrecognition network while keeping the indirect sharing structure inherited fromthe IOD-CNN, thus being `doubly-injected'. We also introduce a batch poolinglayer which constructs one representative feature map from multiple objecthypotheses. We have demonstrated the effectiveness of injecting the objectdetection information in two different ways in the task of malicious eventrecognition.

DOD-CNN: Doubly-injecting Object Information for Event Recognition