Video Classification Using Deep Autoencoder Network

We present a deep learning framework for video classification applicable to face recognition and dynamic texture recognition. A Deep Autoencoder Network Template (DANT) is designed whose weights are initialized by conducting unsupervised pre-training in a layer-wise fashion using Gaussian Restricted Boltzmann Machines. In order to obtain a class specific network and fine tune the weights for each class, the pre-initialized DANT is trained for each class of video sequences, separately. A majority voting technique based on the reconstruction error is employed for the classification task. The extensive evaluation and comparisons with state-of-the-art approaches on Honda/UCSD, DynTex, and YUPPEN databases demonstrate that the proposed method significantly improves the performance of dynamic texture classification.

Hajati Farshid, Tavakolian Mohammad

A4 Article in conference proceedings

Complex, Intelligent, and Software Intensive Systems. CISIS 2019

Hajati F., Tavakolian M. (2020) Video Classification Using Deep Autoencoder Network. In: Barolli L., Hussain F., Ikeda M. (eds) Complex, Intelligent, and Software Intensive Systems. CISIS 2019. Advances in Intelligent Systems and Computing, vol 993. Springer, Cham. https://doi.org/10.1007/978-3-030-22354-0_45

https://doi.org/10.1007/978-3-030-22354-0_45 http://urn.fi/urn:nbn:fi-fe202102266056