Metraipolis › archive › dc_152b7193f4fc

Event-based Selective Attention for Multi-resolution Fast Region of Interest (ROI) Detection — arXiv:2609.17134

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.17134
License (as archived)
CC0-1.0
Archived
2026-10-15T21:44:28.637Z
SHA-256 of the archived text
9ba18b61743f804a8e7d811987850e7dfb1dee9115495f6f21717f4fefeae811
Stable URL of this page
https://metraipolis.com/documento/dc_152b7193f4fc

How to cite

Event-based Selective Attention for Multi-resolution Fast Region of Interest (ROI) Detection — arXiv:2609.17134 — arXiv (en), https://arxiv.org/abs/2609.17134 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_152b7193f4fc (Metraipolis archive dc_152b7193f4fc, sha256 9ba18b61743f804a8e7d811987850e7dfb1dee9115495f6f21717f4fefeae811)
BibTeX
@misc{dc152b7193f4fc,
  title = {Event-based Selective Attention for Multi-resolution Fast Region of Interest (ROI) Detection — arXiv:2609.17134},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17134},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_152b7193f4fc; sha256 9ba18b61743f804a8e7d811987850e7dfb1dee9115495f6f21717f4fefeae811},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17134. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neuromorphic vision systems operate under strict constraints on bandwidth, memory, and energy, particularly at the edge, motivating early mechanisms for data reduction and selective processing. In this work, we investigate a multi-scale training-free, saliency-based, bottom-up visual attention model that operates directly on low-resolution event-based input and selects Regions of Interest (ROI) from the visual scene. The model is evaluated across multiple downscaling factors applied to the incoming event stream, with input resolutions reduced by up to 256x relative to full resolution. Performance is assessed on the Prophesee Automotive dataset, the largest publicly available event-based dataset, demonstrating robust ROI selection across different scales on a real-world use-case. The proposed approach is capable of detecting ROIs belonging to multiple object classes, including various vehicle types, pedestrians, traffic lights, and traffic signs, with accuracy up to 70.8%, while operating at millisecond temporal resolution, 16x finer than the temporal resolution provided by the dataset ground truth. These results highlight the potential of combining early event downscaling with saliency-based attention as an effective front-end for efficient edge neuromorphic vision systems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.NE).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Neural and Evolutionary Computing (cs.NE).
Pagina del lavoro: https://arxiv.org/abs/2609.17134 — 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 2026-10-15T21:31:16.117Z dalla pagina https://arxiv.org/catchup/cs.NE/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).