THU-Warwick Submission for EPIC-KITCHEN Challenge 2025: Semi-Supervised Video Object Segmentation

In this report, we describe our approach to egocentric video object segmentation. Our method combines large-scale visual pretraining from SAM2 with depth-based geometric cues to handle complex scenes and long-term tracking. By integrating these signals in a unified framework, we achieve strong segmentation performance. On the VISOR test set, our method reaches a J&F score of 90.1%.

@article{gao2025_2506.06748,
  title={ THU-Warwick Submission for EPIC-KITCHEN Challenge 2025: Semi-Supervised Video Object Segmentation },
  author={ Mingqi Gao and Haoran Duan and Tianlu Zhang and Jungong Han },
  journal={arXiv preprint arXiv:2506.06748},
  year={ 2025 }
}