Metraipolis › archive › dc_26d11fc8a8e7

LVMT: Video Mask Transformer for Long-term Video Segmentation — arXiv:2609.34895

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34895
License (as archived)
CC0-1.0
Archived
2026-10-07T23:52:31.872Z
SHA-256 of the archived text
377afdfdb6f360475ae134d1235813149fd11de7e01bd51062f7fc678961a7dc
Stable URL of this page
https://metraipolis.com/documento/dc_26d11fc8a8e7

How to cite

LVMT: Video Mask Transformer for Long-term Video Segmentation — arXiv:2609.34895 — arXiv (en), https://arxiv.org/abs/2609.34895 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_26d11fc8a8e7 (Metraipolis archive dc_26d11fc8a8e7, sha256 377afdfdb6f360475ae134d1235813149fd11de7e01bd51062f7fc678961a7dc)
BibTeX
@misc{dc26d11fc8a8e7,
  title = {LVMT: Video Mask Transformer for Long-term Video Segmentation — arXiv:2609.34895},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34895},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_26d11fc8a8e7; sha256 377afdfdb6f360475ae134d1235813149fd11de7e01bd51062f7fc678961a7dc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34895. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing online video segmentation methods struggle to track objects in long, complex videos with long-term occlusions. We hypothesize that this limitation is caused by (i) the inability of their temporal propagation mechanism to adaptively select the object information that is propagated across time, and (ii) their inability to be trained on long videos due to memory requirements and vanishing gradients. To address the first limitation, we propose to use a lightweight GRU-based temporal propagation module that can learn to select which information it keeps in memory and propagates across time. Second, to allow training on long videos, we introduce Truncated Query Propagation (TQP), a training strategy in which the model processes a video in chunks of frames, where information about tracked objects is propagated between chunks but backpropagation is only conducted in individual chunks, enabling longer temporal supervision without out-of-memory issues, inference overhead, or vanishing gradients. The resulting model is called the Long-term Video Mask Transformer (LVMT). Extensive experiments on six benchmarks show that LVMT sets a new state of the art across a range of video segmentation tasks, while retaining the speed of the highly efficient model it is based on, making it 10X faster than the prior state of the art. Code: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.34895 — 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 2026-10-07T23:29:27.490Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).