Single Image Action Recognition by Predicting Space-Time Saliency

Abstract: We propose a novel approach based on deep Convolutional Neural Networks (CNN) to recognize human actions in still images by predicting the future motion, and detecting the shape and location of the salient parts of the image. We make the following major contributions to this important area of research: (i) We use the predicted future motion in the static image (Walker et al., 2015) as a means of compensating for the missing temporal information, while using the saliency map to represent the the spatial information in the form of location and shape of what is predicted as significant. (ii) We cast action classification in static images as a domain adaptation problem by transfer learning. We first map the input static image to a new domain that we refer to as the Predicted Optical Flow-Saliency Map domain (POF-SM), and then fine-tune the layers of a deep CNN model trained on classifying the ImageNet dataset to perform action classification in the POF-SM domain. (iii) We tested our method on the popular Willow dataset. But unlike existing methods, we also tested on a more realistic and challenging dataset of over 2M still images that we collected and labeled by taking random frames from the UCF-101 video dataset. We call our dataset the UCF Still Image dataset or UCFSI-101 in short. Our results outperform the state of the art.