Metraipolis › archive › dc_490ddd37cc03
CapMap-MS-TTA: 3rd Place Solution for the MUMU Track of the 8th LSVOS Challenge at ECCV 2026 — arXiv:2609.18206
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.18206
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T16:16:21.965Z
- SHA-256 of the archived text
cf31be7d7ee501c1eafd1ad90e773a36d20be8101e34cc52acf60ec09b148f82- Stable URL of this page
https://metraipolis.com/documento/dc_490ddd37cc03
How to cite
CapMap-MS-TTA: 3rd Place Solution for the MUMU Track of the 8th LSVOS Challenge at ECCV 2026 — arXiv:2609.18206 — arXiv (en), https://arxiv.org/abs/2609.18206 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_490ddd37cc03 (Metraipolis archive dc_490ddd37cc03, sha256 cf31be7d7ee501c1eafd1ad90e773a36d20be8101e34cc52acf60ec09b148f82)
BibTeX
@misc{dc490ddd37cc03,
title = {CapMap-MS-TTA: 3rd Place Solution for the MUMU Track of the 8th LSVOS Challenge at ECCV 2026 — arXiv:2609.18206},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.18206},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_490ddd37cc03; sha256 cf31be7d7ee501c1eafd1ad90e773a36d20be8101e34cc52acf60ec09b148f82},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18206. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The MUMU track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge requires a single unified multimodal model to jointly solve image tagging (Task A), open-vocabulary object detection (Task B), and English captioning (Task C) under strict resource constraints (<=0.5B parameters and <=8 GB peak GPU memory). We present CapMap-MS-TTA, a training-free submission built on Microsoft Florence-2-base (~231M parameters), combining caption keyword mapping with multi-scale flip test-time augmentation. Task C uses the native <DETAILED_CAPTION> pathway with length/token sanitization. Task A maps the same detailed caption into the official quality/scene/event vocabularies via an expanded keyword lexicon with whole-word matching and a lightweight expand-hints stage. Task B runs Florence-2 open detection (<OD>) with multi-scale and horizontal-flip test-time augmentation (TTA), followed by label-aware non-maximum suppression (NMS). Without fine-tuning, the system improves our reproduced Florence-2 baseline from 15.16 to a best public score of 16.4815, and ranks 3rd on the final MUMU leaderboard. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.18206 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T15:45:19.753Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).