Video2GIF: Automatic Generation of Animated GIFs from Video
- 1 June 2016
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1001-1009
- https://doi.org/10.1109/cvpr.2016.114
Abstract
We introduce the novel problem of automatically generating animated GIFs from video. GIFs are short looping video with no sound, and a perfect combination between image and video that really capture our attention. GIFs tell a story, express emotion, turn events into humorous moments, and are the new wave of photojournalism. We pose the question: Can we automate the entirely manual and elaborate process of GIF creation by leveraging the plethora of user generated GIF content? We propose a Robust Deep RankNet that, given a video, generates a ranked list of its segments according to their suitability as GIF. We train our model to learn what visual content is often selected for GIFs by using over 100K user generated GIFs and their corresponding video sources. We effectively deal with the noisy web data by proposing a novel adaptive Huber loss in the ranking formulation. We show that our approach is robust to outliers and picks up several patterns that are frequently present in popular animated GIFs. On our new large-scale benchmark dataset, we show the advantage of our approach over several state-of-the-art methods.Keywords
This publication has 22 references indexed in Scilit:
- Unsupervised Learning of Visual Representations Using VideosPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Unsupervised Extraction of Video Highlights via Robust Recurrent Auto-EncodersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Learning Spatiotemporal Features with 3D Convolutional NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Video summarization by learning submodular mixtures of objectivesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Learning Fine-Grained Image Similarity with Deep RankingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- 6 Seconds of Sound and Vision: Creativity in Micro-videosPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- The Interestingness of ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Visual interestingness in image sequencesPublished by Association for Computing Machinery (ACM) ,2013
- Video abstraction: A systematic review and classificationACM Transactions on Multimedia Computing, Communications, and Applications, 2007
- Learning representations by back-propagating errorsNature, 1986