Abstract
Long short-term memory (LSTM) is widely used for processing time sequence data like language and human skeletal data, and its importance is continuously increasing. In particular, recent studies have shown that higher performance can be obtained by using deep LSTM instead of single LSTM for language processing and action recognition tasks. In this paper, we compared the performance between single LSTM and deep LSTM for a different time sequence processing task, single object tracking. We verified that using deep LSTM can significantly improve the performance compared to single LSTM. This implies that deep LSTM is an effective model to overcome current technical limitations such as object deformation and occlusion. We expect this study will lead to the development of a stable tracker robust to object deformation and occlusion in the near future.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.