Few-Shot Referring Video Single- and Multi-Object Segmentation via Cross-Modal Affinity with Instance Sequence Matching
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916696249335808 |
|---|---|
| author | Liu, Heng Li, Guanghui Gao, Mingqi Zhen, Xiantong Zheng, Feng Wang, Yang |
| author_facet | Liu, Heng Li, Guanghui Gao, Mingqi Zhen, Xiantong Zheng, Feng Wang, Yang |
| contents | Referring video object segmentation (RVOS) aims to segment objects in videos guided by natural language descriptions. We propose FS-RVOS, a Transformer-based model with two key components: a cross-modal affinity module and an instance sequence matching strategy, which extends FS-RVOS to multi-object segmentation (FS-RVMOS). Experiments show FS-RVOS and FS-RVMOS outperform state-of-the-art methods across diverse benchmarks, demonstrating superior robustness and accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_13710 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Few-Shot Referring Video Single- and Multi-Object Segmentation via Cross-Modal Affinity with Instance Sequence Matching Liu, Heng Li, Guanghui Gao, Mingqi Zhen, Xiantong Zheng, Feng Wang, Yang Computer Vision and Pattern Recognition Referring video object segmentation (RVOS) aims to segment objects in videos guided by natural language descriptions. We propose FS-RVOS, a Transformer-based model with two key components: a cross-modal affinity module and an instance sequence matching strategy, which extends FS-RVOS to multi-object segmentation (FS-RVMOS). Experiments show FS-RVOS and FS-RVMOS outperform state-of-the-art methods across diverse benchmarks, demonstrating superior robustness and accuracy. |
| title | Few-Shot Referring Video Single- and Multi-Object Segmentation via Cross-Modal Affinity with Instance Sequence Matching |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.13710 |