Metraipolis › archive › dc_7145777ffdba

ExQuery: Explicit Structured Query Priors for Temporal 3D Object Detection — arXiv:2611.09527

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09527
License (as archived)
CC0-1.0
Archived
2026-11-09T22:45:22.410Z
SHA-256 of the archived text
e16e7feb67612094424da37ec698459e428402fa8dc36df0320747f76a0b425d
Stable URL of this page
https://metraipolis.com/documento/dc_7145777ffdba

How to cite

ExQuery: Explicit Structured Query Priors for Temporal 3D Object Detection — arXiv:2611.09527 — arXiv (en), https://arxiv.org/abs/2611.09527 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7145777ffdba (Metraipolis archive dc_7145777ffdba, sha256 e16e7feb67612094424da37ec698459e428402fa8dc36df0320747f76a0b425d)
BibTeX
@misc{dc7145777ffdba,
  title = {ExQuery: Explicit Structured Query Priors for Temporal 3D Object Detection — arXiv:2611.09527},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09527},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7145777ffdba; sha256 e16e7feb67612094424da37ec698459e428402fa8dc36df0320747f76a0b425d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09527. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sparse query-based 3D detectors commonly encode heterogeneous semantic, geometric, and motion information into unified latent queries, including when explicit 3D anchors are used. We introduce ExQuery, an explicit structured query framework for temporal 3D object detection. Each decoded query is organized into a shared semantic context slice and physical-state-specific slices for center, dimensions, orientation, and velocity. This structure is preserved from prior encoding to branch-specific regression and is reused to reconstruct temporal queries: predicted physical states are transformed by ego motion, classification scores form soft semantic priors, and the reconstructed query is fused with the stored latent instance feature through gated affine modulation. Experiments on the nuScenes benchmark show that our method achieves competitive detection performance, and ablation studies validate the effectiveness of our proposed modules.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.09527 — 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 2026-11-09T22:37:47.229Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).