Research map / Video / Video segmentation and tracking
DeRVOS: Decoupling Consistent Trajectory Generation and Multimodal Understanding for Referring Video Object Segmentation
Wenxuan Cheng, Ming Dai, Huimin Lu, Wankou Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace Mask2Former with VITA then DVIS++ as frozen trajectory generator (ablation) | DeRVOS · MeViS valu | J&F: 55.5 -> 56.0 -> 57.4 | Improved |
| replace BERT-B with ViLT-B then BEiT3-B as multimodal encoder (ablation) | DeRVOS · MeViS valu | J&F: 55.9 -> 56.6 -> 57.4 | Improved |
| add CFMA instead of Text-Direct Integrator (ablation) | DeRVOS · MeViS valu | J&F: 56.1 -> 56.5 | Improved |
| add motion-guided implicit selector on top of CFMA (full TAIS) (ablation) | DeRVOS · MeViS valu | J&F: 56.5 -> 57.4 | Improved |
| use video-query integrator instead of text-direct integrator (ablation) | DeRVOS · MeViS valu | J&F: 56.1 -> 56.2 | No clear effect |
| increase trajectory branch input resolution from 320 to 640 (ablation) | DeRVOS · MeViS valu | J&F: 56.9 -> 60.9 | Improved |
| pretrain DVIS++ on OVIS rather than YouTube-VIS 2019, 2021 or VIPSeg (ablation) | DeRVOS · MeViS valu | J&F: 55.4 -> 57.4 (vs YouTube-VIS 2019) | Improved |
| add image-level pretraining on RefCOCO/+/g | DeRVOS · MeViS val | J&F: 51.8 -> 56.0 | Improved |
| decoupled design with frozen trajectory generator versus DsHmp | DeRVOS · MeViS val | J&F: 46.4 -> 51.8; training 20 hours -> 9 hours | Improved |
| DeRVOS vs DeRIS-B on RefCOCO image-level segmentation | DeRVOS · RefCOCO val | mIoU: 82.0 vs 80.2 | Hurt |
Later papers that compared with this method
1 later accepted paper reports DeRVOS as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- MomentSeg: Moment-Centric Sampling for Enhanced Referring Video Object Segmentation (ECCV 2026 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ReferDINO — ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations (ICCV 2025) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Long-RVOS: A Comprehensive Benchmark for Long-term Referring Video Object Segmentation (CVPR 2026 · similarity 0.91)
- Semantic and Sequential Alignment for Referring Video Object Segmentation (CVPR 2025 · similarity 0.90)
- InterRVOS: Interaction-Aware Referring Video Object Segmentation (CVPR 2026 · similarity 0.90)
- DTOS: Dynamic Time Object Sensing with Large Multimodal Model (CVPR 2025 · similarity 0.89)
- Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention (NeurIPS 2025 · similarity 0.87)
- LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation (CVPR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
