papers AI Learner
The Github is limit! Click to go to the new site.

IOD-CNN: Integrating Object Detection Networks for Event Recognition

2017-03-21
Sungmin Eum, Hyungtae Lee, Heesung Kwon, David Doermann

Abstract

Many previous methods have showed the importance of considering semantically relevant objects for performing event recognition, yet none of the methods have exploited the power of deep convolutional neural networks to directly integrate relevant object information into a unified network. We present a novel unified deep CNN architecture which integrates architecturally different, yet semantically-related object detection networks to enhance the performance of the event recognition task. Our architecture allows the sharing of the convolutional layers and a fully connected layer which effectively integrates event recognition, rigid object detection and non-rigid object detection.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1703.07431

PDF

https://arxiv.org/pdf/1703.07431


Similar Posts

Comments