Research map / Detection and segmentation / Open-set and few-shot detection
You Only Infer Once: Cross-Modal Meta-Transfer for Referring Video Object Segmentation
Dezhuang Li, Ruoqi Li, Lijun Wang, Yifan Wang, Jinqing Qi, Lu Zhang, Ting Liu, Qingquan Xu, Huchuan Lu
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 |
|---|---|---|---|
| use one-stage YOFO instead of URVOS | RVOS · Refer-DAVIS2017 validation, first-frame expression | J &F: 51.63 -> 54.44 | Improved |
| use YOFO instead of RefVOS | RVOS · Refer-DAVIS2017 validation, full-video expression | J &F: 45.1 -> 52.16 | Improved |
| use YOFO instead of CMPC-V | RVOS · Refer-Youtube-VOS validation | J &F: 47.48 -> 48.59 | Improved |
| use YOFO instead of URVOS | RVOS · Refer-Youtube-VOS validation | J &F: 47.23 -> 48.59 | Improved |
| use multi-scale cross-modal feature mining instead of the baseline fusion scheme (ablation) | YOFO · Refer-DAVIS2017 validation, first-frame expression | J &F: 45.2 -> 49.5 | Improved |
| use multi-scale rather than single-scale cross-modal feature mining (ablation) | YOFO · Refer-DAVIS2017 validation, first-frame expression | J &F: 43.5 -> 49.5 | Improved |
| use the proposed feature mining rather than concatenating image and language features at each scale (ablation) | YOFO · Refer-DAVIS2017 validation, first-frame expression | J &F: 42.9 -> 49.5 | Improved |
| add the Meta-Transfer module (ablation) | YOFO · Refer-DAVIS2017 validation, first-frame expression | J &F: 42.7 -> 49.5 | Improved |
| add augmented memory of recent frames for meta-transfer learning (ablation) | YOFO · Refer-DAVIS2017 validation, first-frame expression | J &F: 48.4 -> 49.5 | Improved |
Closest papers by meaning
- Learning Cross-Modal Affinity for Referring Video Object Segmentation Targeting Limited Samples (ICCV 2023 · similarity 0.93)
- Few-Shot Referring Video Single- and Multi-Object Segmentation Via Cross-Modal Affinity with Instance Sequence Matching (IJCV 2025 · similarity 0.92)
- End-to-End Referring Video Object Segmentation With Multimodal Transformers (CVPR 2022 · similarity 0.91)
- OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation (ICCV 2023 · similarity 0.90)
- Semantic and Sequential Alignment for Referring Video Object Segmentation (CVPR 2025 · similarity 0.90)
- LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation (CVPR 2024 · similarity 0.89)
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.
