Metraipolis › archive › dc_2149a85d2926

PointEvent: Rethinking Event-based Tiny Object Detection via Serialized Motion Evidence Accumulation — arXiv:2609.20066

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.20066
License (as archived)
CC0-1.0
Archived
2026-10-10T03:24:02.665Z
SHA-256 of the archived text
dbe3b1efa2d397d1dc19f67c9f03639ba90a879ca9c959ec13aa2d4f912292bb
Stable URL of this page
https://metraipolis.com/documento/dc_2149a85d2926

How to cite

PointEvent: Rethinking Event-based Tiny Object Detection via Serialized Motion Evidence Accumulation — arXiv:2609.20066 — arXiv (en), https://arxiv.org/abs/2609.20066 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2149a85d2926 (Metraipolis archive dc_2149a85d2926, sha256 dbe3b1efa2d397d1dc19f67c9f03639ba90a879ca9c959ec13aa2d4f912292bb)
BibTeX
@misc{dc2149a85d2926,
  title = {PointEvent: Rethinking Event-based Tiny Object Detection via Serialized Motion Evidence Accumulation — arXiv:2609.20066},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.20066},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2149a85d2926; sha256 dbe3b1efa2d397d1dc19f67c9f03639ba90a879ca9c959ec13aa2d4f912292bb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20066. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Event cameras offer high temporal resolution and motion sensitivity for tiny UAV detection, yet distant targets generate sparse and fragmented events that are easily overwhelmed by clutter and ego-motion. Existing methods mainly rely on dense event representations or local sparse spatiotemporal modeling, resulting in redundant computation or fragmented modeling of motion continuity across distant asynchronous events. To address this limitation, we introduce serialized motion evidence accumulation, which treats motion continuity as an ordered evidence propagation process. Specifically, the same event stream is organized into locality-preserving spatiotemporal paths and chronology-preserving temporal paths through the latent complementary serializations. Based on this principle, we propose PointEvent, a lightweight event-wise state-space framework that alternates serialized scans across the complementary orders, progressively consolidating fragmented motion evidence beyond fixed local neighborhoods. A high-resolution event branch preserves fine-grained target responses, while compact context modulation suppresses interference. Experiments demonstrate that PointEvent achieves SOTA with the fewest parameters and fastest measured inference among the compared methods. Code: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.20066 — 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 2026-10-10T03:04:13.897Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).