Metraipolis › archive › dc_eb85338adc7e

Unified Vision-Centric Pedestrian Crossing Action Prediction via Adaptive Patch Projection and Proactive Spatial Rectification — arXiv:2609.07420

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07420
License (as archived)
CC0-1.0
Archived
2026-10-16T15:11:49.115Z
SHA-256 of the archived text
bdc2b314971016b3a528e48a991d8c7b2fd791986d8794f4247da9388150614b
Stable URL of this page
https://metraipolis.com/documento/dc_eb85338adc7e

How to cite

Unified Vision-Centric Pedestrian Crossing Action Prediction via Adaptive Patch Projection and Proactive Spatial Rectification — arXiv:2609.07420 — arXiv (en), https://arxiv.org/abs/2609.07420 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb85338adc7e (Metraipolis archive dc_eb85338adc7e, sha256 bdc2b314971016b3a528e48a991d8c7b2fd791986d8794f4247da9388150614b)
BibTeX
@misc{dceb85338adc7e,
  title = {Unified Vision-Centric Pedestrian Crossing Action Prediction via Adaptive Patch Projection and Proactive Spatial Rectification — arXiv:2609.07420},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07420},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb85338adc7e; sha256 bdc2b314971016b3a528e48a991d8c7b2fd791986d8794f4247da9388150614b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07420. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision cues are available and informative for pedestrian action prediction, but obtaining stable target-centric representations from video frames remains challenging without frame-level external perception cues. Thus, most methods rely on additional perception modules or multi-source information fusion, leaving the reliability of vision-centric setting an open question. To this end, we propose ViCross, a vision-centric pedestrian crossing action prediction framework powered by multimodal large language models, which maintains target-centric reasoning from video frames without additional perception modules beyond first-frame target initialization. While multimodal large language models exhibit strong visual understanding, applying them directly to vision-centric action prediction faces two challenges. First, accurately perceiving target pedestrians often requires high resolution inputs and dense visual tokenization, making full-frame encoding computationally prohibitive. ViCross tackles this with Variable Resolution Patch Mapping module for efficient token allocation while preserving key pedestrian details. Second, missing spatiotemporal priors hinder consistent cross frame reasoning. ViCross mitigates this with a Spatial Constraint Enhancement Strategy that captures past motion, future locations, and action semantics for training-time proactive spatial rectification. Extensive experiments show that ViCross delivers clear gains in vision-centric prediction settings and is competitive with multi-source fusion approaches in several settings. Code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.07420 — 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 2026-10-16T14:49:57.218Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).