{"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/circulant-temporal-encoding-for-video","title":"Circulant temporal encoding for video retrieval and temporal alignment","arxiv_id":"1506.02588","date":"2015-06-08","proceeding":null,"authors":["Matthijs Douze","Jérôme Revaud","Jakob Verbeek","Hervé Jégou","Cordelia Schmid"],"abstract":"We address the problem of specific video event retrieval. Given a query video\nof a specific event, e.g., a concert of Madonna, the goal is to retrieve other\nvideos of the same event that temporally overlap with the query. Our approach\nencodes the frame descriptors of a video to jointly represent their appearance\nand temporal order. It exploits the properties of circulant matrices to\nefficiently compare the videos in the frequency domain. This offers a\nsignificant gain in complexity and accurately localizes the matching parts of\nvideos. The descriptors can be compressed in the frequency domain with a\nproduct quantizer adapted to complex numbers. In this case, video retrieval is\nperformed without decompressing the descriptors. We also consider the temporal\nalignment of a set of videos. We exploit the matching confidence and an\nestimate of the temporal offset computed for all pairs of videos by our\nretrieval approach. Our robust algorithm aligns the videos on a global timeline\nby maximizing the set of temporally consistent matches. The global temporal\nalignment enables synchronous playback of the videos of a given scene.","url_abs":"http://arxiv.org/abs/1506.02588v2","url_pdf":"http://arxiv.org/pdf/1506.02588v2.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":"circulant-temporal-encoding-for-video","repo_url":"https://github.com/facebookresearch/videoalignment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1506.02588","atlas_url":"https://app.syntology.ai/?focus=1506.02588","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}