Abstract

Event recognition from still images is of great impor-tance for image understanding. However, compared with event recognition in videos, there are much fewer research works on event recognition in images. This paper address-es the issue of event recognition from images and proposes an effective method with deep neural networks. Specifical-ly, we design a new architecture, called Object-Scene Con-volutional Neural Network (OS-CNN). This architecture is decomposed into object net and scene net, which extrac-t useful information for event understanding from the per-spective of objects and scene context, respectively. Mean-while, we investigate different network architectures for OS-CNN design, and adapt the deep (AlexNet) and very-deep (GoogLeNet) networks to the task of event recognition. Fur-thermore, we find that the deep and very-deep networks are complementary to each other. Finally, based on the pro-posed OS-CNN and comparative study of different network architectures, we come up with a solution of five-stream CN-N for the track of cultural event recognition at the ChaLearn Looking at People (LAP) challenge 2015. Our method ob-tains the performance of 85:5 % and ranks the 1st place in this challenge. 1.