Capitalizing The Collective Knowledge for Video Annotation Refinement using Dynamic Weighted Voting

Authors(2) :-Kirubai Dhanaraj, Rajkumar Kannan

Collective knowledge paves the way for most challenging task to be an interesting and improving efficiency in the field of multimedia annotations and retrievals. Automatic annotation is bridging the gap between low-level content and high-level semantic concepts. It has been an active research area in the field of multimedia retrieval, machine learning and social media environments. Even most automatic annotation approaches are often unsatisfactory, the annotation refinement has invited the attention of recent researchers. In this paper, a novel refinement algorithm is proposed using dynamic weighted voting based on mutual information. It leverages the collective knowledge of the social media like collection of videos, images, texts in the form of tags, and comments available online. The proposed algorithm invests collective knowledge to measure the relevance between the candidate annotations by assessing the probability and assigning a dynamic weights.

Authors and Affiliations

Kirubai Dhanaraj
Research Department of Computer Science Bishop Heber College, Tiruchirappalli, Tamil Nadu, India
Rajkumar Kannan
Research Department of Computer Science Bishop Heber College, Tiruchirappalli, Tamil Nadu, India

Annotation Refinement, Collective knowledge, dynamic-weighted voting, SURF feature, Multimedia annotation

  1. M.Guillaumin,T.Mensink,J.Verbeek and C.Schmid.TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotation.In Proc.Of ICCV,2009.
  2. X.Li and C.Snoek and M.Worring.Learning social tag relevance by neighbor voting.IEEE Transactions on Multimedia,11(7):1310-1322,2009
  3. L.Ballan,T.Urricho,and A.Del Bimbo.2014.A cross-media Model for Automatic Image Annotation.In Proc.of ACM ICMR.73-80
  4. Kirubai Dhanaraj,Rajkumar Kannan,Harnessing the Social Annotations for Tag Refinement in Cultural Multimedia,IJSRCEIT,2018,pp.1802-1808.
  5. T.Uriccho,L.Ballan,M.Beritini,and A.Del Bimbo,"An evalution of nearest-neighbor methods for tag refinement",in Proc.of IEEE International conference on multimedia & Expo (ICME),San Jose,CA,USA,2013.
  6. Emily Moxley,TaoMei,B.S.Manjunath,Video Annotation Through Search and Graph Reinforcement Mining,Published in IEEE Transaction on Multimedia Vol.12,No.3 April 2010 pp 184 – 193.
  7. L.Ballan,M.Bertini,T.Uricchio,A.Del Bimbo,Data-driven approaches for social image and video tagging,Multimedia Tools and Applications 74 (2015) 1443–1468.
  8. Z.Qian,P.Zhong,and R.Wang.2015.Tag refinement for user-contributed images via graph learning and nonnegative tensor factorization.IEEE Signal Processing Letters 22,9(2015),35-62.
  9. Kirubai Dhanaraj,Rajkumar Kannan,A State-of-the are Review: A Survey on Multimedia Tagging Techniques,IJSRST Volume 4,Issue 5,pp 377-386,2018.
  10. R.Kannan,G.Ghinea,S.Swaninathan,Salient region detection using patch level and region level image abstractions,2015,IEEE,Signal Processing Letters 22(6),pp 686-690.
  11. H.Li,L.Yi,Y.Guan,H.Zhang,DUT-WEBV: A benchmark dataset for performance evaluation of tag localization for web video,in: Proc.Of MMM,Huangshan,China,2013,pp.305–315.

Publication Details

Published in : Volume 4 | Issue 4 | March-April 2018
Date of Publication : 2018-04-30
License:  This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) : 750-754
Manuscript Number : IJSRSET1844218
Publisher : Technoscience Academy

Print ISSN : 2395-1990, Online ISSN : 2394-4099

Cite This Article :

Kirubai Dhanaraj, Rajkumar Kannan, " Capitalizing The Collective Knowledge for Video Annotation Refinement using Dynamic Weighted Voting, International Journal of Scientific Research in Science, Engineering and Technology(IJSRSET), Print ISSN : 2395-1990, Online ISSN : 2394-4099, Volume 4, Issue 4, pp.750-754, March-April-2018.
Journal URL :

Article Preview

Follow Us

Contact Us