000150271 001__ 150271
000150271 005__ 20250201165030.0
000150271 0247_ $$2doi$$a10.1109/CVPRW56347.2022.00301
000150271 0248_ $$2sideral$$a130997
000150271 037__ $$aART-2022-130997
000150271 041__ $$aeng
000150271 100__ $$aSabater, Alberto$$uUniversidad de Zaragoza
000150271 245__ $$aEvent Transformer. A sparse-aware solution for efficient event data processing
000150271 260__ $$c2022
000150271 5060_ $$aAccess copy available to the general public$$fUnrestricted
000150271 5203_ $$aEvent cameras are sensors of great interest for many applications that run in low-resource and challenging environments. They log sparse illumination changes with high temporal resolution and high dynamic range, while they present minimal power consumption. However, top-performing methods often ignore specific event-data properties, leading to the development of generic but computationally expensive algorithms. Efforts toward efficient solutions usually do not achieve top-accuracy results for complex tasks. This work proposes a novel framework, Event Transformer (EvT) 1 , that effectively takes advantage of event-data properties to be highly efficient and accurate. We introduce a new patch-based event representation and a compact transformer-like architecture to process it. EvT is evaluated on different event-based benchmarks for action and gesture recognition. Evaluation results show better or comparable accuracy to the state-of-the-art while requiring significantly less computation resources, which makes EvT able to work with minimal latency both on GPU and CPU.
000150271 536__ $$9info:eu-repo/grantAgreement/ES/DGA-FSE/T45-17R$$9info:eu-repo/grantAgreement/ES/MICIU-AEI-FEDER/PGC2018-098817-A-I00
000150271 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/
000150271 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000150271 700__ $$0(orcid)0000-0003-1183-349X$$aMontesano, Luis$$uUniversidad de Zaragoza
000150271 700__ $$0(orcid)0000-0002-7580-9037$$aMurillo, Ana C.$$uUniversidad de Zaragoza
000150271 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát.
000150271 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf.
000150271 773__ $$g2022 (2022), 2676-2685$$pIEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. workshops$$tIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops$$x2160-7508
000150271 8564_ $$s1157125$$uhttps://zaguan.unizar.es/record/150271/files/texto_completo.pdf$$yPostprint
000150271 8564_ $$s2725662$$uhttps://zaguan.unizar.es/record/150271/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint
000150271 909CO $$ooai:zaguan.unizar.es:150271$$particulos$$pdriver
000150271 951__ $$a2025-02-01-14:36:45
000150271 980__ $$aARTICLE