Metraipolis › archive › dc_c00cb21326e0
DynEoMT: Learning Object Dynamicity from Online Segmentation Queries — arXiv:2609.14466
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14466
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T01:53:08.071Z
- SHA-256 of the archived text
0c5105f29feffa9bd7a2af3bab86367470ef6a5b755d998a57f3280926337de3- Stable URL of this page
https://metraipolis.com/documento/dc_c00cb21326e0
How to cite
DynEoMT: Learning Object Dynamicity from Online Segmentation Queries — arXiv:2609.14466 — arXiv (en), https://arxiv.org/abs/2609.14466 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c00cb21326e0 (Metraipolis archive dc_c00cb21326e0, sha256 0c5105f29feffa9bd7a2af3bab86367470ef6a5b755d998a57f3280926337de3)
BibTeX
@misc{dcc00cb21326e0,
title = {DynEoMT: Learning Object Dynamicity from Online Segmentation Queries — arXiv:2609.14466},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14466},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c00cb21326e0; sha256 0c5105f29feffa9bd7a2af3bab86367470ef6a5b755d998a57f3280926337de3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14466. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Video segmentation models recognize and track objects over time, but they do not indicate whether each segmented region moves independently of the observing camera. This dynamicity attribute cannot be inferred from semantics alone and is confounded by camera ego-motion. We introduce \method, an online framework that augments query-based video segmentation with region-level dynamicity prediction. It jointly produces the original segmentation outputs and a dynamic or static state for each predicted region. At inference, DynEoMT uses only the current frame and propagated queries, without optical flow, depth, camera pose, previous RGB frames, or feature maps. Because established video segmentation benchmarks do not annotate this attribute, we also introduce a class-agnostic offline supervision pipeline using camera-compensated optical flow and confidence-aware temporal filtering. Across VIPSeg, OVIS, YouTube-VIS 2022, and VSPW, DynEoMT achieves balanced accuracies of 84.3, 68.0, 68.6, and 87.6, respectively, while largely preserving segmentation performance. These results show that segmentation-region dynamicity can be learned from propagated queries, enabling its online prediction without a dedicated motion-processing pipeline at inference. The complete code will be released as open source to enable full reproduction of the method and experiments. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.14466 — 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 2026-10-16T01:25:23.585Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).