A Memory Network Approach for Story-based Temporal Summarization of 360deg Videos

We address the problem of story-based temporal summarization of long 360deg videos. We propose a novel memory network model named Past-Future Memory Network (PFMN), in which we first compute the scores of 81 normal field of view (NFOV) region proposals cropped from the input 360deg video, and then recover a latent, collective summary using the network with two external memories that store the embeddings of previously selected subshots and future candidate subshots. Our major contributions are two-fold. First, our work is the first to address story-based temporal summarization of 360deg videos. Second, our model is the first attempt to leverage memory networks for video summarization tasks. For evaluation, we perform three sets of experiments. First, we investigate the view selection capability of our model on the Pano2Vid dataset. Second, we evaluate the temporal summarization with a newly collected 360deg video dataset. Finally, we experiment our model's performance in another domain, with image-based storytelling VIST dataset. We verify that our model achieves state-of-the-art performance on all the tasks.