{"slug": "vos-agent-the-1st-place-solution-for-the-8th-lsvos-challenge-mosev2-track", "title": "VOS-Agent: The 1st Place Solution for the 8th LSVOS Challenge (MOSEv2 Track)", "summary": "VOS-Agent, a collaborative framework built on SAM3, won first place in the MOSEv2 Track of the 8th LSVOS Challenge at ECCV 2026, achieving 69.82% on the official J&F metric. The framework uses a Target Perception and Routing Agent to assign sequences to regular, tiny, or semantic-dominated routes, with specialized agents for tiny and semantic-dominated targets.", "body_md": "arXiv:2608.12721v1 Announce Type: new\nAbstract: Complex video object segmentation requires robust target propagation under severe occlusion, disappearance and reappearance. Although SAM3 provides strong promptable mask propagation, a uniform inference path remains unreliable for tiny targets with insufficient visual evidence and semantic-dominated targets whose identities depend on explicit attributes. To this end, we present VOS-Agent, a collaborative framework that retains SAM3 as the shared dense segmentation module and conditionally activates specialized agents according to target characteristics. A Target Perception and Routing Agent assigns each sequence to a regular, tiny, or semantic-dominated route. Tiny targets are supported by a Visual Tracking Agent through confidence-aware box prompts, while semantic-dominated targets are handled by an MLLM-based Semantic Agent through description-guided localization and candidate verification. On the MOSEv2 test set, VOS-Agent achieves 69.82% on the official $\\mathcal{J}\\&\\dot{\\mathcal{F}}$ metric and ranks first in the MOSEv2 Track of the 8th LSVOS Challenge at ECCV 2026.", "url": "https://wpnews.pro/news/vos-agent-the-1st-place-solution-for-the-8th-lsvos-challenge-mosev2-track", "canonical_source": "https://arxiv.org/abs/2608.12721", "published_at": "2026-08-14 04:00:00+00:00", "updated_at": "2026-08-14 04:06:46.770444+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning", "artificial-intelligence"], "entities": ["VOS-Agent", "SAM3", "MOSEv2", "LSVOS Challenge", "ECCV 2026"], "alternates": {"html": "https://wpnews.pro/news/vos-agent-the-1st-place-solution-for-the-8th-lsvos-challenge-mosev2-track", "markdown": "https://wpnews.pro/news/vos-agent-the-1st-place-solution-for-the-8th-lsvos-challenge-mosev2-track.md", "text": "https://wpnews.pro/news/vos-agent-the-1st-place-solution-for-the-8th-lsvos-challenge-mosev2-track.txt", "jsonld": "https://wpnews.pro/news/vos-agent-the-1st-place-solution-for-the-8th-lsvos-challenge-mosev2-track.jsonld"}}