Learning sparse representations for view-independent human action recognition based on fuzzy distances

Iosifidis, Alexandros; Tefas, Anastasios; Pitas, Ioannis

doi:10.1016/j.neucom.2013.05.021

Cited by 7 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding the calculation of appropriate Graph Laplacian matricesL v which are employed for the incorporation of unlabeled data information on the calculation of the networks' output weights, an appropriate number of weights should be exploited for different training samples. Sparsity-based techniques [29] have been found to work well for this purpose, since they are able to automatically determine the number neighboring samples and the corresponding weights for the calculation of appropriate Laplacian matrices. However, such techniques are time-consuming.…”

Section: Discussionmentioning

confidence: 99%

Regularized extreme learning machine for multi-view semi-supervised action recognition

2014

Self Cite

View full text Add to dashboard Cite

In this paper, three novel classification algorithms aiming at (semi-)supervised action classification are proposed. Inspired by the effectiveness of discriminant subspace learning techniques and the fast and efficient Extreme Learning Machine (ELM) algorithm for Single-hidden Layer Feedforward Neural networks training, the ELM algorithm is extended by incorporating discrimination criteria in its optimization process, in order to enhance its classification performance. The proposed Discriminant ELM algorithm is extended, by incorporating proper regularization in its optimization process, in order to exploit information appearing in both labeled and unlabeled action instances. An iterative optimization scheme is proposed in order to address multi-view action classification. The proposed classification algorithms are evaluated on three publicly available action recognition databases providing state-of-the-art performance in all the cases.

show abstract

Section: Discussionmentioning

confidence: 99%