Publication Details
Annotating images with suggestions - user study of a tagging system
Kolář Martin, Ph.D. (DCGM FIT BUT)
Král Jiří, Ing. (DITS FIT BUT)
Láník Aleš, Ing. (DCGM FIT BUT)
Zemčík Pavel, prof. Dr. Ing. (DCGM FIT BUT)
Smrž Pavel, doc. RNDr., Ph.D. (DCGM FIT BUT)
Restricted Boltzmann Machine, human-assisted learning, user interface, image tagging, crowdsourcing, image classification
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 Indexing) can be annotated much more efficiently with the proposed approach than with current class-domain-wise methods, and produce higher quality data.
@INPROCEEDINGS{FITPUB9990,
author = "Michal Hradi\v{s} and Martin Kol\'{a}\v{r} and Ji\v{r}\'{i} Kr\'{a}l and Ale\v{s} L\'{a}n\'{i}k and Pavel Zem\v{c}\'{i}k and Pavel Smr\v{z}",
title = "Annotating images with suggestions - user study of a tagging system",
pages = "155--166",
booktitle = "Advanced Concepts for Intelligent Vision Systems",
series = "Lecture Notes in Computer Science",
journal = "Lecture Notes in Computer Science",
number = 7517,
year = 2012,
location = "Brno, CZ",
publisher = "Springer Verlag",
ISBN = "978-3-642-33139-8",
ISSN = "0302-9743",
doi = "10.1007/978-3-642-33140-4\_14",
language = "english",
url = "https://www.fit.vut.cz/research/publication/9990"
}