000130108 001__ 130108
000130108 005__ 20241125101135.0
000130108 0247_ $$2doi$$a10.1109/TPAMI.2023.3311336
000130108 0248_ $$2sideral$$a136518
000130108 037__ $$aART-2023-136518
000130108 041__ $$aeng
000130108 100__ $$aSabater, Alberto$$uUniversidad de Zaragoza
000130108 245__ $$aEvent transformer+. A multi-purpose solution for efficient event data processing
000130108 260__ $$c2023
000130108 5060_ $$aAccess copy available to the general public$$fUnrestricted
000130108 5203_ $$aEvent cameras record sparse illumination changes with high temporal resolution and high dynamic range. Thanks to their sparse recording and low consumption, they are increasingly used in applications such as AR/VR and autonomous driving. Current top-performing methods often ignore specific event-data properties, leading to the development of generic but computationally expensive algorithms, while event-aware methods do not perform as well. We propose Event Transformer++ , that improves our seminal work EvT with a refined patch-based event representation and a more robust backbone to achieve more accurate results, while still benefiting from event-data sparsity to increase its efficiency. Additionally, we show how our system can work with different data modalities and propose specific output heads, for event-stream classification (i.e. action recognition) and per-pixel predictions (dense depth estimation). Evaluation results show better performance to the state-of-the-art while requiring minimal computation resources, both on GPU and CPU.
000130108 536__ $$9info:eu-repo/grantAgreement/ES/DGA/T45-23R$$9info:eu-repo/grantAgreement/ES/MICINN/PID2021-125514NB-I00
000130108 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/
000130108 590__ $$a20.8$$b2023
000130108 592__ $$a6.158$$b2023
000130108 591__ $$aENGINEERING, ELECTRICAL & ELECTRONIC$$b3 / 353 = 0.008$$c2023$$dQ1$$eT1
000130108 593__ $$aApplied Mathematics$$c2023$$dQ1
000130108 591__ $$aCOMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE$$b2 / 197 = 0.01$$c2023$$dQ1$$eT1
000130108 593__ $$aArtificial Intelligence$$c2023$$dQ1
000130108 593__ $$aSoftware$$c2023$$dQ1
000130108 593__ $$aComputer Vision and Pattern Recognition$$c2023$$dQ1
000130108 593__ $$aComputational Theory and Mathematics$$c2023$$dQ1
000130108 594__ $$a28.4$$b2023
000130108 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000130108 700__ $$0(orcid)0000-0003-1183-349X$$aMontesano, Luis$$uUniversidad de Zaragoza
000130108 700__ $$0(orcid)0000-0002-7580-9037$$aMurillo, Ana C.$$uUniversidad de Zaragoza
000130108 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát.
000130108 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf.
000130108 773__ $$g45, 12 (2023), 16013-16020$$pIEEE trans. pattern anal. mach. intell.$$tIEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE$$x0162-8828
000130108 8564_ $$s3018574$$uhttps://zaguan.unizar.es/record/130108/files/texto_completo.pdf$$yPostprint
000130108 8564_ $$s3126318$$uhttps://zaguan.unizar.es/record/130108/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint
000130108 909CO $$ooai:zaguan.unizar.es:130108$$particulos$$pdriver
000130108 951__ $$a2024-11-22-12:00:39
000130108 980__ $$aARTICLE