Research map / Video / Video segmentation and tracking
Few-Shot Referring Video Single- and Multi-Object Segmentation Via Cross-Modal Affinity with Instance Sequence Matching
Heng Liu, Guanghui Li, Mingqi Gao, Xiantong Zhen, Feng Zheng, Yang Wang
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 |
|---|---|---|---|
| add self-affinity block to baseline (ablation) | CMA · Mini-Ref-YouTube-VOS Fold-1 | J&F: 57.9 -> 59.2 | Improved |
| add cross-affinity block on top of self-affinity (ablation) | CMA · Mini-Ref-YouTube-VOS Fold-1 | J&F: 59.2 -> 60.2 | Improved |
| add instance sequence matching (ISM) (ablation) | Few-shot RVOS model · Mini-MeViS Fold-3 | J&F: 38.2 -> 38.7 | Improved |
| add text expression for unseen categories (ablation) | Few-shot RVOS model · Bottle (unseen) | J: 77.3 -> 82.4 | Improved |
| add text expression for unseen categories (ablation) | Few-shot RVOS model · Lego (unseen) | J: 69.5 -> 84.2 | Improved |
| add text expression for unseen categories (ablation) | Few-shot RVOS model · Coffee (unseen) | F: 64.3 -> 71.0 | Improved |
| add text expression for unseen categories (ablation) | Few-shot RVOS model · Oven (unseen) | F: 31.4 -> 35.6 | Improved |
| vary matching threshold sigma (ablation) | ISM · Mini-Ref-YouTube-VOS Fold-1 | J&F | No clear effect |
| fine-tune on 18 Mini-MeViS videos | Few-shot RVOS model (Fold3) · Mini-MeViS | J&F: 38.7 -> 41.6 | Improved |
| fine-tune RVOS baseline ReferFormer on Mini-MeViS videos | ReferFormer · Mini-MeViS | J&F: 38.2 -> 40.6 | Improved |
| fine-tune on Mini-Ref-SAIL-VOS | MUTR · Mini-Ref-SAIL-VOS | J&F: 68.4 -> 72.9 | Improved |
Closest papers by meaning
- Learning Cross-Modal Affinity for Referring Video Object Segmentation Targeting Limited Samples (ICCV 2023 · similarity 0.97)
- End-to-End Referring Video Object Segmentation With Multimodal Transformers (CVPR 2022 · similarity 0.93)
- You Only Infer Once: Cross-Modal Meta-Transfer for Referring Video Object Segmentation (AAAI 2022 · similarity 0.92)
- Semantic and Sequential Alignment for Referring Video Object Segmentation (CVPR 2025 · similarity 0.91)
- LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation (CVPR 2024 · similarity 0.91)
- SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation (CVPR 2025 · 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.
