One-shot action recognition in challenging therapy scenarios

Sabater A. (Universidad de Zaragoza) ; Santos L. ; Santos-Victor J. ; Bernardino A. ; Montesano L. (Universidad de Zaragoza) ; Murillo A.C. (Universidad de Zaragoza)

Resumen: One-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.

Idioma: Inglés

DOI: 10.1109/CVPRW53098.2021.00312

Año: 2021

Publicado en: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (2021), 2771-2779
ISSN: 2160-7508

Tipo y forma: Artículo (PrePrint)

Área (Departamento): Área Ingen.Sistemas y Automát. (Dpto. Informát.Ingenie.Sistms.)
Área (Departamento): Área Lenguajes y Sistemas Inf. (Dpto. Informát.Ingenie.Sistms.)