Exportar Publicação

A publicação pode ser exportada nos seguintes formatos: referência da APA (American Psychological Association), referência do IEEE (Institute of Electrical and Electronics Engineers), BibTeX e RIS.

Exportar Referência (APA) 
Sezavar, A., Brites, C. & Ascenso, J. (2025). Low complexity learning-based lossless event-based compression. In Proceedings - 2024 International Symposium on Multimedia, ISM 2024. (pp. 85-92). Tokyo: IEEE.
Exportar Referência (IEEE) 
A. Sezavar et al.,  "Low complexity learning-based lossless event-based compression", in Proc. - 2024 Int. Symp. on Multimedia, ISM 2024, Tokyo, IEEE, 2025, pp. 85-92
Exportar BibTeX 
@inproceedings{sezavar2025_1777780388249,
	author = "Sezavar, A. and Brites, C. and Ascenso, J.",
	title = "Low complexity learning-based lossless event-based compression",
	booktitle = "Proceedings - 2024 International Symposium on Multimedia, ISM 2024",
	year = "2025",
	editor = "",
	volume = "",
	number = "",
	series = "",
	doi = "https://doi.ieeecomputersociety.org/10.1109/ISM63611.2024.00018",
	pages = "85-92",
	publisher = "IEEE",
	address = "Tokyo",
	organization = "",
	url = "https://www.multimediacomputing.org"
}
Exportar RIS 
TY  - CPAPER
TI  - Low complexity learning-based lossless event-based compression
T2  - Proceedings - 2024 International Symposium on Multimedia, ISM 2024
AU  - Sezavar, A.
AU  - Brites, C.
AU  - Ascenso, J.
PY  - 2025
SP  - 85-92
DO  - https://doi.ieeecomputersociety.org/10.1109/ISM63611.2024.00018
CY  - Tokyo
UR  - https://www.multimediacomputing.org
AB  - Event cameras are a cutting-edge type of visual sensors that capture data by detecting brightness changes at the pixel level asynchronously. These cameras offer numerous benefits over conventional cameras, including high temporal resolution, wide dynamic range, low latency, and lower power consumption. However, the substantial data rates they produce require efficient compression techniques, while also fulfilling other typical application requirements, such as the ability to respond to visual changes in real-time or near real-time. Additionally, many event-based applications demand high accuracy, making lossless coding desirable, as it retains the full detail of the sensor data. Learning-based methods show great potential due to their ability to model the unique characteristics of event data thus allowing to achieve high compression rates. This paper proposes a low-complexity lossless coding solution based on the quadtree representation that outperforms traditional compression algorithms in efficiency and speed, ensuring low computational complexity and minimal delay for real-time applications. Experimental results show that the proposed method delivers better compression ratios, i.e., with fewer bits per event, and lower computational complexity compared to current lossless data compression methods.
ER  -