Skip to Main content Skip to Navigation
Journal articles

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

Abstract : 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.
Document type :
Journal articles
Complete list of metadata

https://hal-utt.archives-ouvertes.fr/hal-03320724
Contributor : Jean-Baptiste Vu Van Connect in order to contact the contributor
Submitted on : Monday, August 16, 2021 - 12:54:56 PM
Last modification on : Friday, August 27, 2021 - 3:14:06 PM

Links full text

Identifiers

Collections

UTT | CNRS

`

Citation

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, IEEE, 2017, 5, pp.17627-17633. ⟨10.1109/ACCESS.2017.2746095⟩. ⟨hal-03320724⟩

Share

Metrics

Record views

8