{"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/unsupervised-video-object-segmentation-using","title":"Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation","arxiv_id":"1809.01125","date":"2018-09-04","proceeding":"ECCV 2018 9","authors":["Yuan-Ting Hu","Jia-Bin Huang","Alexander G. Schwing"],"abstract":"Unsupervised video segmentation plays an important role in a wide variety of\napplications from object identification to compression. However, to date, fast\nmotion, motion blur and occlusions pose significant challenges. To address\nthese challenges for unsupervised video segmentation, we develop a novel\nsaliency estimation technique as well as a novel neighborhood graph, based on\noptical flow and edge cues. Our approach leads to significantly better initial\nforeground-background estimates and their robust as well as accurate diffusion\nacross time. We evaluate our proposed algorithm on the challenging DAVIS,\nSegTrack v2 and FBMS-59 datasets. Despite the usage of only a standard edge\ndetector trained on 200 images, our method achieves state-of-the-art results\noutperforming deep learning based methods in the unsupervised setting. We even\ndemonstrate competitive results comparable to deep learning based methods in\nthe semi-supervised setting on the DAVIS dataset.","url_abs":"http://arxiv.org/abs/1809.01125v1","url_pdf":"http://arxiv.org/pdf/1809.01125v1.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":"deep-learning","task_name":"Deep Learning"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"saliency-prediction","task_name":"Saliency Prediction"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-video-object-segmentation","task_name":"Unsupervised Video Object Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-salient-object-detection","task_name":"Video Salient Object Detection"},{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-salient-object-detection-on-davsod-2","task":"Video Salient Object Detection","dataset":"DAVSOD-Difficult20","model":"MBNM","rank_in_archive_order":4,"of":8,"metrics":{"Average MAE":"0.140","S-Measure":"0.561","max E-measure":"0.635"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.01125","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}