Recently, Recurrent Neural Network (RNN) based approach presents good performance in skeleton based action recognition. Utilizing deep layers of RNN or Long-Short Term Memory (LSTM) has its on weakness when handling long-sequence data because of vanishing or exploding gradients through time. Batch Normalized LSTM (BN-LSTM) is able to give a solution for the problem, with the merit of converging faster in training. In contrast, when deeply layered, BN-LSTM structure shows slow convergence and worse accuracy. In this work, we analyze deep-layered BN-LSTM shows slower convergence in early training phase in training scheme and, finally we propose a deep BN-LSTM structure with auxiliary classifier that is able to converge faster and gives better results at skeleton based action recognition problem. Some experiment are conducted with Penn Action dataset and our own Computer Assembling Video dataset, we verified our proposal shows better results in skeleton based action recognition.
|Title of host publication||IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||6|
|Publication status||Published - 2018 Jul 2|
|Event||3rd IEEE International Conference on Image Processing, Applications and Systems, IPAS 2018 - Sophia Antipolis, France|
Duration: 2018 Dec 12 → 2018 Dec 14
|Name||IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018|
|Conference||3rd IEEE International Conference on Image Processing, Applications and Systems, IPAS 2018|
|Period||18/12/12 → 18/12/14|
Bibliographical notePublisher Copyright:
© 2018 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition
- Hardware and Architecture
- Computer Graphics and Computer-Aided Design