{"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/fast-video-object-segmentation-by-reference","title":"Fast Video Object Segmentation by Reference-Guided Mask Propagation","arxiv_id":null,"date":"2018-06-01","proceeding":"CVPR 2018 6","authors":["Seoung Wug Oh","Joon-Young Lee","Kalyan Sunkavalli","Seon Joo Kim"],"abstract":"We present an efficient method for the semi-supervised video object segmentation. Our method achieves accuracy competitive with state-of-the-art methods while running in a fraction of time compared to others. To this end, we propose a deep Siamese encoder-decoder network that is designed to take advantage of mask propagation and object detection while avoiding the weaknesses of both approaches. Our network, learned through a two-stage training process that exploits both synthetic and real data, works robustly without any online learning or post-processing. We validate our method on four benchmark sets that cover single and multiple object segmentation. On all the benchmark sets, our method shows comparable accuracy while having the order of magnitude faster runtime. We also provide extensive ablation and add-on studies to analyze and evaluate our framework.","url_abs":"http://openaccess.thecvf.com/content_cvpr_2018/html/Oh_Fast_Video_Object_CVPR_2018_paper.html","url_pdf":"http://openaccess.thecvf.com/content_cvpr_2018/papers/Oh_Fast_Video_Object_CVPR_2018_paper.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":"fast-video-object-segmentation-by-reference","repo_url":"https://github.com/seoungwugoh/RGMP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"fast-video-object-segmentation-by-reference","repo_url":"https://github.com/xanderchf/RGMP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"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-semantic-segmentation","task_name":"Video Semantic Segmentation"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"RGMP","rank_in_archive_order":57,"of":78,"metrics":{"F-measure (Decay)":"10.1","F-measure (Mean)":"82.0","F-measure (Recall)":"90.8","J&F":"81.75","Jaccard (Decay)":"10.9","Jaccard (Mean)":"81.5","Jaccard (Recall)":"91.7"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-1","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model":"RGMP","rank_in_archive_order":51,"of":59,"metrics":{"F-measure (Decay)":"37.2","F-measure (Mean)":"54.4","F-measure (Recall)":"61.9","J&F":"52.8","Jaccard (Decay)":"34.3","Jaccard (Mean)":"51.3","Jaccard (Recall)":"59.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"RGMP","rank_in_archive_order":64,"of":81,"metrics":{"F-measure (Decay)":"19.6","F-measure (Mean)":"68.6","F-measure (Recall)":"77.7","J&F":"66.7","Jaccard (Decay)":"18.9","Jaccard (Mean)":"64.8","Jaccard (Recall)":"74.1"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}