{"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/r-2vos-robust-referring-video-object","title":"Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus","arxiv_id":"2207.01203","date":"2022-07-04","proceeding":null,"authors":["Xiang Li","Jinglu Wang","Xiaohao Xu","Xiao Li","Bhiksha Raj","Yan Lu"],"abstract":"Referring Video Object Segmentation (R-VOS) is a challenging task that aims to segment an object in a video based on a linguistic expression. Most existing R-VOS methods have a critical assumption: the object referred to must appear in the video. This assumption, which we refer to as semantic consensus, is often violated in real-world scenarios, where the expression may be queried against false videos. In this work, we highlight the need for a robust R-VOS model that can handle semantic mismatches. Accordingly, we propose an extended task called Robust R-VOS, which accepts unpaired video-text inputs. We tackle this problem by jointly modeling the primary R-VOS problem and its dual (text reconstruction). A structural text-to-text cycle constraint is introduced to discriminate semantic consensus between video-text pairs and impose it in positive pairs, thereby achieving multi-modal alignment from both positive and negative pairs. Our structural constraint effectively addresses the challenge posed by linguistic diversity, overcoming the limitations of previous methods that relied on the point-wise constraint. A new evaluation dataset, R\\textsuperscript{2}-Youtube-VOSis constructed to measure the model robustness. Our model achieves state-of-the-art performance on R-VOS benchmarks, Ref-DAVIS17 and Ref-Youtube-VOS, and also our R\\textsuperscript{2}-Youtube-VOS~dataset.","url_abs":"https://arxiv.org/abs/2207.01203v3","url_pdf":"https://arxiv.org/pdf/2207.01203v3.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":"r-2vos-robust-referring-video-object","repo_url":"https://github.com/lxa9867/R2VOS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"referring-video-object-segmentation","task_name":"Referring Video Object Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/referring-expression-segmentation-on-refer-1","task":"Referring Expression Segmentation","dataset":"Refer-YouTube-VOS (2021 public validation)","model":"R2VOS (Video-Swin-T)","rank_in_archive_order":22,"of":33,"metrics":{"F":"63.1","J":"59.6","J&F":"61.3"},"uses_additional_data":true},{"leaderboard":"/sota/referring-video-object-segmentation-on-refer","task":"Referring Video Object Segmentation","dataset":"Refer-YouTube-VOS","model":"R2VOS (Swin-T)","rank_in_archive_order":15,"of":18,"metrics":{"F":"61.5","J":"58.9","J&F":"60.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.01203","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}