Complex Event Recognition from Images with Few Training Examples
This addresses the problem of recognizing complex social events in photographs for computer vision applications, though it appears incremental as it builds on existing concept-based and CNN approaches.
The paper tackles complex event recognition from images with limited training examples by leveraging concept-level representations discovered from web data, achieving state-of-the-art performance on challenging datasets and demonstrating best overall accuracy with a single training example for unseen event categories.
We propose to leverage concept-level representations for complex event recognition in photographs given limited training examples. We introduce a novel framework to discover event concept attributes from the web and use that to extract semantic features from images and classify them into social event categories with few training examples. Discovered concepts include a variety of objects, scenes, actions and event sub-types, leading to a discriminative and compact representation for event images. Web images are obtained for each discovered event concept and we use (pretrained) CNN features to train concept classifiers. Extensive experiments on challenging event datasets demonstrate that our proposed method outperforms several baselines using deep CNN features directly in classifying images into events with limited training examples. We also demonstrate that our method achieves the best overall accuracy on a dataset with unseen event categories using a single training example.