Internal Transfer Learning for Improving Performance in Human Action Recognition for Small Datasets - Université de technologie de Troyes Accéder directement au contenu
Article Dans Une Revue IEEE Access Année : 2017

Internal Transfer Learning for Improving Performance in Human Action Recognition for Small Datasets

Tian Wang
  • Fonction : Auteur
Yang Chen
  • Fonction : Auteur
Jie Chen

Résumé

Human action recognition nowadays plays a key role in varieties of computer vision applications. Many computer vision methods focus on algorithms designing classifiers with handcrafted features which are complex and inflexible. In this paper, we focus on the human action recognition problem and utilize 3D convolutional neural networks to automatically extract both spatial and temporal features for classification. Specifically, in order to address the training problems with small data sets, we propose an internal transfer learning strategy adapted to this framework, by incorporating the sub-data classification method into transfer learning. We evaluate our method on several data sets and obtain promising results. With the proposed strategy, the performance of human action recognition is improved obviously.

Dates et versions

hal-03320724 , version 1 (16-08-2021)

Identifiants

Citer

Tian Wang, Yang Chen, Mengyi Zhang, Jie Chen, Hichem Snoussi. Internal Transfer Learning for Improving Performance in Human Action Recognition for Small Datasets. IEEE Access, 2017, 5, pp.17627-17633. ⟨10.1109/ACCESS.2017.2746095⟩. ⟨hal-03320724⟩
13 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More