{"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/video-propagation-networks","title":"Video Propagation Networks","arxiv_id":"1612.05478","date":"2016-12-16","proceeding":"CVPR 2017 7","authors":["Varun Jampani","Raghudeep Gadde","Peter V. Gehler"],"abstract":"We propose a technique that propagates information forward through video\ndata. The method is conceptually simple and can be applied to tasks that\nrequire the propagation of structured information, such as semantic labels,\nbased on video content. We propose a 'Video Propagation Network' that processes\nvideo frames in an adaptive manner. The model is applied online: it propagates\ninformation forward without the need to access future frames. In particular we\ncombine two components, a temporal bilateral network for dense and video\nadaptive filtering, followed by a spatial network to refine features and\nincreased flexibility. We present experiments on video object segmentation and\nsemantic video segmentation and show increased performance comparing to the\nbest previous task-specific methods, while having favorable runtime.\nAdditionally we demonstrate our approach on an example regression task of color\npropagation in a grayscale video.","url_abs":"http://arxiv.org/abs/1612.05478v3","url_pdf":"http://arxiv.org/pdf/1612.05478v3.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":[],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-video-object-segmentation","task_name":"Semi-Supervised Video Object Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-propagation","task_name":"Video Propagation"},{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"VPN","rank_in_archive_order":72,"of":78,"metrics":{"F-measure (Decay)":"14.4","F-measure (Mean)":"65.6","F-measure (Recall)":"69.0","J&F":"67.9","Jaccard (Decay)":"12.4","Jaccard (Mean)":"70.2","Jaccard (Recall)":"82.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.05478","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}