Papers › Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus

Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus

4 Jul 2022arXiv:2207.01203archive 2025-07-28

Xiang Li, Jinglu Wang, Xiaohao Xu, Xiao Li, Bhiksha Raj, Yan Lu

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

lxa9867/R2VOS officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Referring Expression SegmentationReferring Video Object SegmentationSemantic SegmentationVideo Object SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) R2VOS (Video-Swin-T) F 63.1 #22 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) R2VOS (Video-Swin-T) J 59.6 #22 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) R2VOS (Video-Swin-T) J&F 61.3 #22 of 33 Archive leaderboard report
Referring Video Object Segmentation Refer-YouTube-VOS R2VOS (Swin-T) F 61.5 #15 of 18 Archive leaderboard report
Referring Video Object Segmentation Refer-YouTube-VOS R2VOS (Swin-T) J 58.9 #15 of 18 Archive leaderboard report
Referring Video Object Segmentation Refer-YouTube-VOS R2VOS (Swin-T) J&F 60.2 #15 of 18 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections