University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Incremental Transfer Learning for Object Classification in Streaming Video

Kim, J and Collomosse, JP (2014) Incremental Transfer Learning for Object Classification in Streaming Video In: Proceedings of International Conference on Image Processing (ICIP), 2014-10-27 - 2014-10-30, Paris, France.

[img]
Preview
Text
Kim-ICIP-2014.pdf
Available under License : See the attached licence file.

Download (617kB) | Preview
[img]
Preview
Text (licence)
SRI_deposit_agreement.pdf
Available under License : See the attached licence file.

Download (33kB) | Preview

Abstract

We present a new incremental learning framework for realtime object recognition in video streams. ImageNet is used to bootstrap a set of one-vs-all incrementally trainable SVMs which are updated by user annotation events during streaming. We adopt an inductive transfer learning (ITL) approach to warp the video feature space to the ImageNet feature space, so enabling the incremental updates. Uniquely, the transformation used for the ITL warp is also learned incrementally using the same update events. We demonstrate a semiautomated video logging (SAVL) system using our incrementally learned ITL approach and show this to outperform existing SAVL which uses non-incremental transfer learning.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
AuthorsEmailORCID
Kim, JUNSPECIFIEDUNSPECIFIED
Collomosse, JPUNSPECIFIEDUNSPECIFIED
Date : October 2014
Identification Number : 10.1109/ICIP.2014.7025552
Contributors :
ContributionNameEmailORCID
PublisherIEEE, UNSPECIFIEDUNSPECIFIED
Additional Information : © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Depositing User : Symplectic Elements
Date Deposited : 18 Mar 2015 16:23
Last Modified : 19 Mar 2015 02:33
URI: http://epubs.surrey.ac.uk/id/eprint/805873

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800