Realistic human action recognition: When deep learning meets VLAD

Lei Zhang, Yangyang Feng, Jiqing Han, Xiantong ZhenICASSP 2016 · OpenReview

Abstract

Human action recognition from realistic scenarios is extremely challenging due to large intra-class variation and complex background clutters. In this paper, by leveraging the strength of deep learning and vector of locally aggregated descriptors (VLAD), we propose a new methods for human action recognition from realistic datsets. We adopt stack convolu-tional independent subspace analysis (ISA) networks to learn 3D cuboid representation directly from spatio-temporal video data; we propose an improved VLAD by incorporating the spatio-temporal geometrical information to encode the deep learned local features. On two challenging realistic datasets: the YouTube action and HMDB51 datasets, the proposed method achieves state-of-the-art performance with an efficient linear SVM classifier, which is competitive with and even better than existing sophisticated algorithms.
BibTeX
@inproceedings{zhang2016realistic,
  author = {Lei Zhang and Yangyang Feng and Jiqing Han and Xiantong Zhen},
  title = {{Realistic human action recognition: When deep learning meets VLAD}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2016},
  url = {https://openreview.net/forum?id=0t2QZof7ERB},
}

Loading related content...

Figure