EUVIMEDEUVIMED entdecken
Crossref

EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction

Chengjie Ge, Xueyang Fu, Peng He, Kunyu Wang, Chengzhi Cao, Zheng-Jun Zha

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (3) · 3104-3112

DOI: 10.1609/aaai.v39i3.32319 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Chengjie Ge und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Leveraging its robust linear global modeling capability, Mamba has notably excelled in computer vision. Despite its success, existing Mamba-based vision models have overlooked the nuances of event-driven tasks, especially in video reconstruction. Event-based video reconstruction (EBVR) demands spatial translation invariance and close attention to local event relationships in the spatio-temporal domain. Unfortunately, conventional Mamba algorithms apply static window partitions and standard reshape scanning methods, leading to significant losses in local connectivity. To overcome these limitations, we introduce EventMamba—a specialized model designed for EBVR task. EventMamba innovates by incorporating random window offset (RWO) in the spatial domain, moving away from the restrictive fixed partitioning. Additionally, it features a new consistent traversal serialization approach in the spatio-temporal domain, which maintains the proximity of adjacent events both spatially and temporally. These enhancements enable EventMamba to retain Mamba’s robust modeling capabilities while significantly preserving the spatio-temporal locality of event data. Comprehensive testing on multiple datasets shows that EventMamba markedly enhances video reconstruction, drastically improving computation speed while delivering superior visual quality compared to Transformer-based methods.

Zitieren

APA

Ge, C., Fu, X., He, P., Wang, K., Cao, C., & Zha, Z. (2025). EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction. Proceedings of the AAAI Conference on Artificial Intelligence, 39(3), 3104-3112. https://doi.org/10.1609/aaai.v39i3.32319

Vancouver

Ge C, Fu X, He P, Wang K, Cao C, Zha Z. EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(3):3104-3112. doi:10.1609/aaai.v39i3.32319

BibTeX
@article{Ge2025,
  author = {Ge, Chengjie and Fu, Xueyang and He, Peng and Wang, Kunyu and Cao, Chengzhi and Zha, Zheng-Jun},
  title = {EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {3},
  pages = {3104--3112},
  doi = {10.1609/aaai.v39i3.32319}
}
Kostenlos starten →