# CMTM: Cross-Modal Token Modulation for Unsupervised Video Object Segmentation

arXiv: https://arxiv.org/abs/2604.14630 · HTML: https://mlsanity.com/paper/2604.14630/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 16 Apr 2026.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark](https://mlsanity.com/paper/1809.03327/) (2018)
- [Video Classification with Channel-Separated Convolutional Networks](https://mlsanity.com/paper/1904.02811/) (2019)
- [Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement](https://mlsanity.com/paper/2010.07958/) (2020)
- [Full-Duplex Strategy for Video Object Segmentation](https://mlsanity.com/paper/2108.03151/) (2021)
- [Motion-Attentive Transition for Zero-Shot Video Object Segmentation](https://mlsanity.com/paper/2003.04253/) (2020)
- [Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2207.08485/) (2022)
- [Iteratively Selecting an Easy Reference Frame Makes Unsupervised Video Object Segmentation Easier](https://mlsanity.com/paper/2112.12402/) (2021)
- [D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos](https://mlsanity.com/paper/2111.07774/) (2021)
- [Guided Slot Attention for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2303.08314/) (2023)
- [SimulFlow: Simultaneously Extracting Feature and Identifying Target for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2311.18286/) (2023)
- [Improving Unsupervised Video Object Segmentation via Fake Flow Generation](https://mlsanity.com/paper/2407.11714/) (2024)

## Abstract (arXiv)

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.