This repository is a curated list of papers, datasets, and projects related to Video Object Segmentation (VOS). It serves as a comprehensive resource for researchers and practitioners in the field, providing links to recent advancements and foundational works. The primary benefit is a centralized, up-to-date overview of the VOS landscape.

How It Works

The repository categorizes VOS research by task type (e.g., Single-Object, Referring, Unsupervised, Audio-Visual) and publication venue/year. It links directly to papers, code repositories, and project pages, enabling users to quickly access relevant resources. The curation is community-driven, encouraging pull requests to maintain its comprehensiveness.

Quick Start & Requirements

This repository is a curated list and does not have a direct installation or execution command. It requires a web browser to access the linked resources.

Highlighted Details

• Extensive categorization of VOS tasks: SVOS, RVOS, UVOS, AVOS, VMAT, XVOS.
• Links to papers and code for recent (2023-2025) and earlier VOS research.
• Includes major VOS datasets like YouTube-VOS, DAVIS, VISOR, and MOSE.
• Lists active and finished VOS workshops and challenges.

Maintenance & Community

The repository is maintained by gaomingqi and welcomes community contributions via pull requests. Links to relevant conferences and journals are provided for tracking new publications.

Licensing & Compatibility

The repository itself is a list of links and does not have a specific license. The licenses of the linked papers and code repositories vary and must be checked individually.

Limitations & Caveats

As a curated list, the repository's content is dependent on community contributions and may not be exhaustive. The availability and quality of linked code repositories can vary.