MOSEv2

MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes 🔥 Evaluation Server | 🏠 Homepage | 📄 Paper | 🔗 GitHub Download We recommend using huggingface-cli to download: pip install -U "huggingface_hub[cli]" huggingface-cli download FudanCVL/MOSEv2 --repo-type dataset --local-dir ./MOSEv2 --local-dir-use-symlinks False --max-workers 16 Dataset Summary MOSEv2 is a comprehensive video object segmentation dataset designed to advance… See the full description on the dataset page: https://huggingface.co/datasets/FudanCVL/MOSEv2.

Papers using MOSEv2 (2)

The 1st Solution For Mosev2 Challenge 2025: Long-term And Concept-aware Video Segmentation Via Sec2025LSVOS 2025 Challenge Report: Recent Advances In Complex Video Object Segmentation2025