000118265 001__ 118265 000118265 005__ 20220914095756.0 000118265 0247_ $$2doi$$a10.1109/CVPRW53098.2021.00312 000118265 0248_ $$2sideral$$a127884 000118265 037__ $$aART-2021-127884 000118265 041__ $$aeng 000118265 100__ $$aSabater A.$$uUniversidad de Zaragoza 000118265 245__ $$aOne-shot action recognition in challenging therapy scenarios 000118265 260__ $$c2021 000118265 5060_ $$aAccess copy available to the general public$$fUnrestricted 000118265 5203_ $$aOne-shot action recognition aims to recognize new action categories from a single reference example, typically referred to as the anchor example. This work presents a novel approach for one-shot action recognition in the wild that computes motion representations robust to variable kinematic conditions. One-shot action recognition is then performed by evaluating anchor and target motion representations. We also develop a set of complementary steps that boost the action recognition performance in the most challenging scenarios. Our approach is evaluated on the public NTU-120 one-shot action recognition benchmark, outperforming previous action recognition models. Besides, we evaluate our framework on a real use-case of therapy with autistic people. These recordings are particularly challenging due to high-level artifacts from the patient motion. Our results provide not only quantitative but also online qualitative measures, essential for the patient evaluation and monitoring during the actual therapy. © 2021 IEEE. 000118265 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/ 000118265 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/submittedVersion 000118265 700__ $$aSantos L. 000118265 700__ $$aSantos-Victor J. 000118265 700__ $$aBernardino A. 000118265 700__ $$0(orcid)0000-0003-1183-349X$$aMontesano L.$$uUniversidad de Zaragoza 000118265 700__ $$0(orcid)0000-0002-7580-9037$$aMurillo A.C.$$uUniversidad de Zaragoza 000118265 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát. 000118265 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf. 000118265 773__ $$g(2021), 2771-2779$$pIEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. workshops$$tIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops$$x2160-7508 000118265 8564_ $$s1639449$$uhttps://zaguan.unizar.es/record/118265/files/texto_completo.pdf$$yPreprint 000118265 8564_ $$s2385820$$uhttps://zaguan.unizar.es/record/118265/files/texto_completo.jpg?subformat=icon$$xicon$$yPreprint 000118265 909CO $$ooai:zaguan.unizar.es:118265$$particulos$$pdriver 000118265 951__ $$a2022-09-13-14:49:24 000118265 980__ $$aARTICLE