SafePLUG: Empowering Multimodal LLMs with Pixel-Level Insight and Temporal Grounding for Traffic Accident Understanding
CHAIN · 2026 · 3 (1) · 53-72
DOI: 10.23919/chain.2026.000005 ↗Kurz gefasst
Fachartikel in der Zeitschrift CHAIN, 2026. Verfasst von Zihao Sheng und 7 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: U.S. Department of Transportation.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- U.S. Department of Transportation
Zitieren
APA
Sheng, Z., Huang, Z., Qu, Y., Chen, J., Luo, Y., Chen, Y., Leng, Y., & Chen, S. (2026). SafePLUG: Empowering Multimodal LLMs with Pixel-Level Insight and Temporal Grounding for Traffic Accident Understanding. CHAIN, 3(1), 53-72. https://doi.org/10.23919/chain.2026.000005
Vancouver
Sheng Z, Huang Z, Qu Y, Chen J, Luo Y, Chen Y, et al. SafePLUG: Empowering Multimodal LLMs with Pixel-Level Insight and Temporal Grounding for Traffic Accident Understanding. CHAIN. 2026;3(1):53-72. doi:10.23919/chain.2026.000005
BibTeX
@article{Sheng2026,
author = {Sheng, Zihao and Huang, Zilin and Qu, Yansong and Chen, Jiancong and Luo, Yuhao and Chen, Yen-Jung and Leng, Yue and Chen, Sikai},
title = {SafePLUG: Empowering Multimodal LLMs with Pixel-Level Insight and Temporal Grounding for Traffic Accident Understanding},
journal = {CHAIN},
year = {2026},
volume = {3},
number = {1},
pages = {53--72},
doi = {10.23919/chain.2026.000005}
}
EUVIMED