DOD-CNN: Doubly-injecting Object Information for Event Recognition
This work addresses event recognition in computer vision, particularly for malicious events, but is incremental as it builds on prior methods like IOD-CNN.
The paper tackled event recognition in images by proposing DOD-CNN, which doubly-injects object detection information both indirectly through shared architecture and directly from detection outputs, resulting in improved performance for malicious event recognition.
Recognizing an event in an image can be enhanced by detecting relevant objects in two ways: 1) indirectly utilizing object detection information within the unified architecture or 2) directly making use of the object detection output results. We introduce a novel approach, referred to as Doubly-injected Object Detection CNN (DOD-CNN), exploiting the object information in both ways for the task of event recognition. The structure of this network is inspired by the Integrated Object Detection CNN (IOD-CNN) where object information is indirectly exploited by the event recognition module through the shared portion of the network. In the DOD-CNN architecture, the intermediate object detection outputs are directly injected into the event recognition network while keeping the indirect sharing structure inherited from the IOD-CNN, thus being `doubly-injected'. We also introduce a batch pooling layer which constructs one representative feature map from multiple object hypotheses. We have demonstrated the effectiveness of injecting the object detection information in two different ways in the task of malicious event recognition.