# Agreement-Based Audio-Visual Segmentation:Champion Report for the MeViS-Audio Track in the 8th LSVOS Challenge

arXiv: https://arxiv.org/abs/2608.09475 · HTML: https://mlsanity.com/paper/2608.09475/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 14 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 14 of 14)

- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions](https://mlsanity.com/paper/2308.08544/) (2023)
- [Qwen3-ASR Technical Report](https://mlsanity.com/paper/2601.21337/) (2026)
- [MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2508.05630/) (2025)
- [MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation](https://mlsanity.com/paper/2512.10945/) (2025)
- [MolmoPoint: Better Pointing for VLMs with Grounding Tokens](https://mlsanity.com/paper/2603.28069/) (2026)
- [The 1st Solution for 7th LSVOS RVOS Track: SaSaSa2VA](https://mlsanity.com/paper/2509.16972/) (2025)
- [3rd Place of MeViS-Audio Track of the 5th PVUW: VIRST-Audio](https://mlsanity.com/paper/2603.23126/) (2026)
- [APRVOS: 1st Place Winner of 5th PVUW MeViS-Audio Track](https://mlsanity.com/paper/2604.18665/) (2026)
- [2nd of the 5th PVUW MeViS-Audio Track: ASR-SaSaSa2VA](https://mlsanity.com/paper/2604.23935/) (2026)

## Abstract (arXiv)

The MeViS-Audio track asks a system to segment the objects described by a spoken motion expression throughout a video and to return empty masks when the described target is absent. We present a simple staged solution. Qwen3-ASR first converts speech into text. Several video mask tracks are then produced with complementary grounding and segmentation models. Instead of trusting a single prediction, we select the track that has the highest average mask agreement with the other candidates. A small set of explicit direction, count, and plural rules corrects queries that require more than ordinary single-object tracking. Finally, a video-level classifier combines visual, audio-visual, and within-video query scores to decide whether any target is present. The submitted system obtains 0.5952 J &F, 0.7931 no-target accuracy, 0.9205 target accuracy, and a final score of 0.769589. The challenge organizers notified our team that this result ranked first in the track.