130108 20241125101135.0 doi 10.1109/TPAMI.2023.3311336 sideral 136518 ART-2023-136518 eng Sabater, Alberto Universidad de Zaragoza Event transformer+. A multi-purpose solution for efficient event data processing 2023 Access copy available to the general public Unrestricted Event cameras record sparse illumination changes with high temporal resolution and high dynamic range. Thanks to their sparse recording and low consumption, they are increasingly used in applications such as AR/VR and autonomous driving. Current top-performing methods often ignore specific event-data properties, leading to the development of generic but computationally expensive algorithms, while event-aware methods do not perform as well. We propose Event Transformer++ , that improves our seminal work EvT with a refined patch-based event representation and a more robust backbone to achieve more accurate results, while still benefiting from event-data sparsity to increase its efficiency. Additionally, we show how our system can work with different data modalities and propose specific output heads, for event-stream classification (i.e. action recognition) and per-pixel predictions (dense depth estimation). Evaluation results show better performance to the state-of-the-art while requiring minimal computation resources, both on GPU and CPU. info:eu-repo/grantAgreement/ES/DGA/T45-23R info:eu-repo/grantAgreement/ES/MICINN/PID2021-125514NB-I00 info:eu-repo/semantics/openAccess All rights reserved http://www.europeana.eu/rights/rr-f/ 20.8 2023 ENGINEERING, ELECTRICAL & ELECTRONIC 3 / 353 = 0.008 2023 Q1 T1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE 2 / 197 = 0.01 2023 Q1 T1 6.158 2023 Applied Mathematics 2023 Q1 Artificial Intelligence 2023 Q1 Software 2023 Q1 Computer Vision and Pattern Recognition 2023 Q1 Computational Theory and Mathematics 2023 Q1 28.4 2023 info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion Montesano, Luis Universidad de Zaragoza (orcid)0000-0003-1183-349X Murillo, Ana C. Universidad de Zaragoza (orcid)0000-0002-7580-9037 5007 520 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Ingen.Sistemas y Automát. 5007 570 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Lenguajes y Sistemas Inf. 45, 12 (2023), 16013-16020 IEEE trans. pattern anal. mach. intell. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 0162-8828 3018574 http://zaguan.unizar.es/record/130108/files/texto_completo.pdf Postprint 3126318 http://zaguan.unizar.es/record/130108/files/texto_completo.jpg?subformat=icon icon Postprint oai:zaguan.unizar.es:130108 articulos driver 2024-11-22-12:00:39 ARTICLE