Journal of Computer and Communications

Volume 2, Issue 9 (July 2014)

ISSN Print: 2327-5219   ISSN Online: 2327-5227

Google-based Impact Factor: 1.35  Citations  

Learning Actions from the Identity in the Web

HTML  Download Download as PDF (Size: 600KB)  PP. 54-60  
DOI: 10.4236/jcc.2014.29008    3,220 Downloads   3,862 Views  


This paper proposes an efficient and simple method for identity recognition in uncontrolled videos. The idea is to use images collected from the web to learn representations of actions related with identity, use this knowledge to automatically annotate identity in videos. Our approach is unsupervised where it can identify the identity of human in the video like YouTube directly through the knowledge of his actions. Its benefits are two-fold: 1) we can improve retrieval of identity images, and 2) we can collect a database of action poses related with identity, which can then be used in tagging videos. We present the simple experimental evidence that using action images related with identity collected from the web, annotating identity is possible.

Share and Cite:

Ali, K. and Wang, T. (2014) Learning Actions from the Identity in the Web. Journal of Computer and Communications, 2, 54-60. doi: 10.4236/jcc.2014.29008.

Cited by

No relevant information.

Copyright © 2021 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.