{"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/ridiculously-fast-shot-boundary-detection","title":"Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks","arxiv_id":"1705.08214","date":"2017-05-23","proceeding":null,"authors":["Michael Gygli"],"abstract":"Shot boundary detection (SBD) is an important component of many video\nanalysis tasks, such as action recognition, video indexing, summarization and\nediting. Previous work typically used a combination of low-level features like\ncolor histograms, in conjunction with simple models such as SVMs. Instead, we\npropose to learn shot detection end-to-end, from pixels to final shot\nboundaries. For training such a model, we rely on our insight that all shot\nboundaries are generated. Thus, we create a dataset with one million frames and\nautomatically generated transitions such as cuts, dissolves and fades. In order\nto efficiently analyze hours of videos, we propose a Convolutional Neural\nNetwork (CNN) which is fully convolutional in time, thus allowing to use a\nlarge temporal context without the need to repeatedly processing frames. With\nthis architecture our method obtains state-of-the-art results while running at\nan unprecedented speed of more than 120x real-time.","url_abs":"http://arxiv.org/abs/1705.08214v1","url_pdf":"http://arxiv.org/pdf/1705.08214v1.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":"ridiculously-fast-shot-boundary-detection","repo_url":"https://github.com/JoelLeupp/Conv3D-Shot-Boundary-Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"ridiculously-fast-shot-boundary-detection","repo_url":"https://github.com/MikeG112/RFSBD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"ridiculously-fast-shot-boundary-detection","repo_url":"https://github.com/Tangshitao/ClipShots_basline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"ridiculously-fast-shot-boundary-detection","repo_url":"https://github.com/abramjos/Scene-boundary-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"ridiculously-fast-shot-boundary-detection","repo_url":"https://github.com/oladeha2/shot_boudary_detector","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"boundary-detection","task_name":"Boundary Detection"},{"task_slug":"camera-shot-boundary-detection","task_name":"Camera shot boundary detection"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/camera-shot-boundary-detection-on-msu-shot","task":"Camera shot boundary detection","dataset":"MSU Shot Boundary Detection Benchmark","model":"johmathe","rank_in_archive_order":4,"of":10,"metrics":{"F score":"0.7492","FPS":"94"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.08214","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}