Annotating Images with Suggestions - User Study of a Tagging System

  title={Annotating Images with Suggestions - User Study of a Tagging System},
  author={Michal Hradis and Ales L{\'a}n{\'i}k and Jir{\'i} Kr{\'a}l and Pavel Zemc{\'i}k and Pavel Smrz},
This paper explores the concept of image-wise tagging. It introduces a web-based user interface for image annotation, and a novel method for modeling dependencies of tags using Restricted Boltzmann Machines which is able to suggest probable tags for an image based on previously assigned tags. According to our user study, our tag suggestion methods improve both user experience and annotation speed. Our results demonstrate that large datasets with semantic labels (such as in TRECVID Semantic… CONTINUE READING

From This Paper

Topics from this paper.


Publications referenced by this paper.

, John Winn , and Andrew Zisserman . The Pascal Visual Object Classes ( VOC ) Challenge

  • Geoffrey E Hinton
  • International Journal of Computer Vision
  • 2007

Caltech-256 object category dataset

  • G Griffin, A Holub
  • 2007
1 Excerpt

Standards Large-Scale Concept Ontology for Multimedia

  • John R Smith, Milind Naphade, Jelena Tesic, Shih-fu Chang, Winston Hsu
  • 2006
1 Excerpt

Similar Papers

Loading similar papers…