Landmark-based multimodal human action recognition


Human activity recognition has received a lot of attention recently, mainly thanks to the advancements in sensing technologies and systems’ increasing computational power. However, complexity in human movements, sensing devices’ noise and person-specific characteristics impose challenges that still remain to be overcome. In the proposed work, a novel, multi-modal human action recognition method is presented for handling the aforementioned issues. Each action is represented by a basis vector and spectral analysis is performed on an affinity matrix of new action feature vectors. Using modality-dependent kernel regressors for computing the affinity matrix, complexity is reduced and robust lowdimensional representations are achieved. The proposed scheme supports online adaptivity of modalities, in a dynamic fashion, according to their automatically inferred reliability. Evaluation on three publicly available datasets demonstrates the potential of the approach.

  • S. Asteriadis, P. Daras, "Landmark-based multimodal human action recognition", SPRINGER Multimedia Tools and Applications Journal (MTAP), DOI 10.1007/s11042-016-3945-6, Sept 2016

  • Full document available here.
    Contact Information

    Dr. Petros Daras, Principal Researcher Grade Α
    1st km Thermi – Panorama, 57001, Thessaloniki, Greece
    P.O.Box: 60361
    Tel.: +30 2310 464160 (ext. 156)
    Fax: +30 2310 464164