Skip to Main content Skip to Navigation
Conference papers

Human Action Recognition Based on Sub-data Learning

Abstract : Human action recognizing nowadays plays a key role in varieties of computer vision applications while at the same time it’s quite challenging for the requirement of accuracy and robustness. Most current computer vision methods focus on algorithms designing classifiers with handcrafted features which are complex and inflexible. To automatically extract both spatial and temporal features, in this paper we propose a method of human action recognition based on sub-data learning which combines the proposed 3D convolutional neural network (3DCNN) with the One-versus-One (OvO) algorithm. We also employ effective data augmentation to reduce overfitting. We evaluate our method on the KTH and UCF Sports dataset and achieve promising results.
Document type :
Conference papers
Complete list of metadata

https://hal-utt.archives-ouvertes.fr/hal-03320698
Contributor : Jean-Baptiste Vu Van Connect in order to contact the contributor
Submitted on : Monday, August 16, 2021 - 12:05:18 PM
Last modification on : Wednesday, October 13, 2021 - 7:16:03 PM

Identifiers

Collections

UTT | CNRS

Citation

Yang Chen, Tian Wang, Jiakun Li, Xiaowei Lv, Hichem Snoussi. Human Action Recognition Based on Sub-data Learning. Second CCF Chinese Conference, CCCV 2017: Computer Vision, Oct 2017, Tianjin, China. pp.617-626, ⟨10.1007/978-981-10-7305-2_52⟩. ⟨hal-03320698⟩

Share

Metrics

Record views

15