{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/video2gif-automatic-generation-of-animated","title":"Video2GIF: Automatic Generation of Animated GIFs from Video","arxiv_id":"1605.04850","date":"2016-05-16","proceeding":"CVPR 2016 6","authors":["Michael Gygli","Yale Song","Liangliang Cao"],"abstract":"We introduce the novel problem of automatically generating animated GIFs from\nvideo. GIFs are short looping video with no sound, and a perfect combination\nbetween image and video that really capture our attention. GIFs tell a story,\nexpress emotion, turn events into humorous moments, and are the new wave of\nphotojournalism. We pose the question: Can we automate the entirely manual and\nelaborate process of GIF creation by leveraging the plethora of user generated\nGIF content? We propose a Robust Deep RankNet that, given a video, generates a\nranked list of its segments according to their suitability as GIF. We train our\nmodel to learn what visual content is often selected for GIFs by using over\n100K user generated GIFs and their corresponding video sources. We effectively\ndeal with the noisy web data by proposing a novel adaptive Huber loss in the\nranking formulation. We show that our approach is robust to outliers and picks\nup several patterns that are frequently present in popular animated GIFs. On\nour new large-scale benchmark dataset, we show the advantage of our approach\nover several state-of-the-art methods.","url_abs":"http://arxiv.org/abs/1605.04850v1","url_pdf":"http://arxiv.org/pdf/1605.04850v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"video2gif-automatic-generation-of-animated","repo_url":"https://github.com/gyglim/video2gif_dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[],"methods":[{"method_slug":"huber-loss","method_name":"Huber loss"}],"datasets_introduced":[{"slug":"video2gif","name":"Video2GIF","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1605.04850","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}