CMTM: Cross-Modal Token Modulation for Unsupervised Video Object Segmentation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911597522321408 |
|---|---|
| author | Jeon, Inseok Cho, Suhwan Lee, Minhyeok Lee, Seunghoon Kang, Minseok Lee, Jungho Park, Chaewon Kim, Donghyeong Lee, Sangyoun |
| author_facet | Jeon, Inseok Cho, Suhwan Lee, Minhyeok Lee, Seunghoon Kang, Minseok Lee, Jungho Park, Chaewon Kim, Donghyeong Lee, Sangyoun |
| contents | Recent advances in unsupervised video object segmentation have highlighted the potential of two-stream architectures that integrate appearance and motion cues. However, fully leveraging these complementary sources of information requires effectively modeling their interdependencies. In this paper, we introduce cross-modality token modulation, a novel approach designed to strengthen the interaction between appearance and motion cues. Our method establishes dense connections between tokens from each modality, enabling efficient intra-modal and inter-modal information propagation through relation transformer blocks. To improve learning efficiency, we incorporate a token masking strategy that addresses the limitations of relying solely on increased model complexity. Our approach achieves state-of-the-art performance across all public benchmarks, outperforming existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_14630 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CMTM: Cross-Modal Token Modulation for Unsupervised Video Object Segmentation Jeon, Inseok Cho, Suhwan Lee, Minhyeok Lee, Seunghoon Kang, Minseok Lee, Jungho Park, Chaewon Kim, Donghyeong Lee, Sangyoun Computer Vision and Pattern Recognition Machine Learning Recent advances in unsupervised video object segmentation have highlighted the potential of two-stream architectures that integrate appearance and motion cues. However, fully leveraging these complementary sources of information requires effectively modeling their interdependencies. In this paper, we introduce cross-modality token modulation, a novel approach designed to strengthen the interaction between appearance and motion cues. Our method establishes dense connections between tokens from each modality, enabling efficient intra-modal and inter-modal information propagation through relation transformer blocks. To improve learning efficiency, we incorporate a token masking strategy that addresses the limitations of relying solely on increased model complexity. Our approach achieves state-of-the-art performance across all public benchmarks, outperforming existing methods. |
| title | CMTM: Cross-Modal Token Modulation for Unsupervised Video Object Segmentation |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2604.14630 |