{"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/geodesic-distance-histogram-feature-for-video","title":"Geodesic Distance Histogram Feature for Video Segmentation","arxiv_id":"1704.00077","date":"2017-03-31","proceeding":null,"authors":["Hieu Le","Vu Nguyen","Chen-Ping Yu","Dimitris Samaras"],"abstract":"This paper proposes a geodesic-distance-based feature that encodes global\ninformation for improved video segmentation algorithms. The feature is a joint\nhistogram of intensity and geodesic distances, where the geodesic distances are\ncomputed as the shortest paths between superpixels via their boundaries. We\nalso incorporate adaptive voting weights and spatial pyramid configurations to\ninclude spatial information into the geodesic histogram feature and show that\nthis further improves results. The feature is generic and can be used as part\nof various algorithms. In experiments, we test the geodesic histogram feature\nby incorporating it into two existing video segmentation frameworks. This leads\nto significantly better performance in 3D video segmentation benchmarks on two\ndatasets.","url_abs":"http://arxiv.org/abs/1704.00077v1","url_pdf":"http://arxiv.org/pdf/1704.00077v1.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":"superpixels","task_name":"Superpixels"},{"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-segmentation-on-segtrack-v2","task":"Video Segmentation","dataset":"SegTrack v2","model":"GDHF","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"86.86"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.00077","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}