Metraipolis › archive › dc_0cf4cd960c33

Motion-Saliency Complementary Masked Modeling for Point Cloud Video Understanding — arXiv:2608.30279

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30279
License (as archived)
CC0-1.0
Archived
2026-10-17T09:59:24.815Z
SHA-256 of the archived text
840d20a32c4ef4a53f1a06ea5dc0426d93ab059ae6516d5bf20917200c757db7
Stable URL of this page
https://metraipolis.com/documento/dc_0cf4cd960c33

How to cite

Motion-Saliency Complementary Masked Modeling for Point Cloud Video Understanding — arXiv:2608.30279 — arXiv (en), https://arxiv.org/abs/2608.30279 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0cf4cd960c33 (Metraipolis archive dc_0cf4cd960c33, sha256 840d20a32c4ef4a53f1a06ea5dc0426d93ab059ae6516d5bf20917200c757db7)
BibTeX
@misc{dc0cf4cd960c33,
  title = {Motion-Saliency Complementary Masked Modeling for Point Cloud Video Understanding — arXiv:2608.30279},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30279},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0cf4cd960c33; sha256 840d20a32c4ef4a53f1a06ea5dc0426d93ab059ae6516d5bf20917200c757db7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30279. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Point cloud video representation learning is crucial for 3D dynamic scene understanding. In this paper, we propose MoSaiC, a novel Motion-Saliency Complementary masked modeling framework for self-supervised point cloud video representation learning. MoSaiC couples three components: Curriculum Motion-Saliency Masking (CMSM), which guides the masking process toward motion-salient tokens under a curriculum schedule; Normal-Flow Motion (NFM) modeling, which supervises the local rigid rotation of each token in the Lie algebra so(3) as an explicit geometric motion target; and Cross-view Token Consistency Prediction (CTCP), which enforces consistency between two complementary masked views at the token level. Together, these components allow MoSaiC to effectively capture both appearance and motion dynamics. Extensive experiments on multiple downstream tasks, including action recognition, temporal action segmentation, and point-level semantic segmentation, demonstrate the effectiveness of our approach.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.30279 — 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 2026-10-17T09:28:48.127Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).