{"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/deep-spatio-temporal-random-fields-for","title":"Deep Spatio-Temporal Random Fields for Efficient Video Segmentation","arxiv_id":"1807.03148","date":"2018-07-03","proceeding":"CVPR 2018 6","authors":["Siddhartha Chandra","Camille Couprie","Iasonas Kokkinos"],"abstract":"In this work we introduce a time- and memory-efficient method for structured\nprediction that couples neuron decisions across both space at time. We show\nthat we are able to perform exact and efficient inference on a densely\nconnected spatio-temporal graph by capitalizing on recent advances on deep\nGaussian Conditional Random Fields (GCRFs). Our method, called VideoGCRF is (a)\nefficient, (b) has a unique global minimum, and (c) can be trained end-to-end\nalongside contemporary deep networks for video understanding. We experiment\nwith multiple connectivity patterns in the temporal domain, and present\nempirical improvements over strong baselines on the tasks of both semantic and\ninstance segmentation of videos.","url_abs":"http://arxiv.org/abs/1807.03148v1","url_pdf":"http://arxiv.org/pdf/1807.03148v1.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":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"},{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-camvid","task":"Semantic Segmentation","dataset":"CamVid","model":"VideoGCRF","rank_in_archive_order":9,"of":21,"metrics":{"Mean IoU":"75.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.03148","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}