Better Exploiting OS-CNNs for Better Event Recognition in Images

TL;DR

This paper improves cultural event recognition in images by leveraging OS-CNNs, combining object and scene features, and exploring various application scenarios, leading to competitive results in a major challenge.

Contribution

It introduces a novel approach of exploiting OS-CNNs as both feature extractors and end-to-end predictors for event recognition, enhancing performance over previous methods.

Findings

OS-CNNs' global and local features are complementary

Proposed scenarios improve event recognition accuracy

Achieved third place in ICCV LAP challenge 2015

Abstract

Event recognition from still images is one of the most important problems for image understanding. However, compared with object recognition and scene recognition, event recognition has received much less research attention in computer vision community. This paper addresses the problem of cultural event recognition in still images and focuses on applying deep learning methods on this problem. In particular, we utilize the successful architecture of Object-Scene Convolutional Neural Networks (OS-CNNs) to perform event recognition. OS-CNNs are composed of object nets and scene nets, which transfer the learned representations from the pre-trained models on large-scale object and scene recognition datasets, respectively. We propose four types of scenarios to explore OS-CNNs for event recognition by treating them as either "end-to-end event predictors" or "generic feature extractors". Our experimental results demonstrate that the global and local representations of OS-CNNs are complementary to each other. Finally, based on our investigation of OS-CNNs, we come up with a solution for the cultural event recognition track at the ICCV ChaLearn Looking at People (LAP) challenge 2015. Our team secures the third place at this challenge and our result is very close to the best performance.