TY - GEN
T1 - Video Classification Using Deep Autoencoder Network
AU - Hajati, Farshid
AU - Tavakolian, Mohammad
PY - 2019/6/21
Y1 - 2019/6/21
N2 - 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.
AB - 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.
U2 - 10.1007/978-3-030-22354-0_45
DO - 10.1007/978-3-030-22354-0_45
M3 - Conference contribution
SN - 9783030223533
SN - 9783030223540
T3 - Advances in Intelligent Systems and Computing
SP - 208
EP - 518
BT - Proceedings of the 13th International Conference on Complex, Intelligent, and Software Intensive Systems (CISIS-2019)
A2 - Barolli, Leonard
A2 - Hussain, Farookh Khadeer
A2 - Ikeda, Makoto
PB - Springer Cham
CY - Switzerland
T2 - CISIS 2019: The 13th International Conference on Complex, Intelligent, and Software Intensive Systems
Y2 - 3 July 2019 through 5 July 2019
ER -