Automatic image annotation using inverse maps from semantic embeddings

J. J. Thiagarajan, K. N. Ramamurthy, P. Sattigeri, P. T. Bremer, Andreas Spanias

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Human annotation in large scale image databases is time-consuming and error-prone. Since it is very hard to mine image databases using just visual features or textual descriptors, it is common to transform the image features into a semantically meaningful space. In this paper, we propose to perform image annotation in a semantic space inferred based on sparse representations. By constructing a semantic embedding for the visual features, that is constrained to be close to the tag embedding, we show that a robust inverse map can be used to predict the tags. Experiments using standard datasets show the effectiveness of the proposed approach in automatic image annotation when compared to existing methods.

Original languageEnglish (US)
Title of host publication2014 IEEE International Conference on Image Processing, ICIP 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3107-3111
Number of pages5
ISBN (Print)9781479957514
DOIs
StatePublished - Jan 28 2014

Fingerprint

Semantics
Experiments

Keywords

  • embedding
  • Image annotation
  • inverse map
  • RBF interpolation
  • sparse coding

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Thiagarajan, J. J., Ramamurthy, K. N., Sattigeri, P., Bremer, P. T., & Spanias, A. (2014). Automatic image annotation using inverse maps from semantic embeddings. In 2014 IEEE International Conference on Image Processing, ICIP 2014 (pp. 3107-3111). [7025628] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIP.2014.7025628

Automatic image annotation using inverse maps from semantic embeddings. / Thiagarajan, J. J.; Ramamurthy, K. N.; Sattigeri, P.; Bremer, P. T.; Spanias, Andreas.

2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 3107-3111 7025628.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Thiagarajan, JJ, Ramamurthy, KN, Sattigeri, P, Bremer, PT & Spanias, A 2014, Automatic image annotation using inverse maps from semantic embeddings. in 2014 IEEE International Conference on Image Processing, ICIP 2014., 7025628, Institute of Electrical and Electronics Engineers Inc., pp. 3107-3111. https://doi.org/10.1109/ICIP.2014.7025628
Thiagarajan JJ, Ramamurthy KN, Sattigeri P, Bremer PT, Spanias A. Automatic image annotation using inverse maps from semantic embeddings. In 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 3107-3111. 7025628 https://doi.org/10.1109/ICIP.2014.7025628
Thiagarajan, J. J. ; Ramamurthy, K. N. ; Sattigeri, P. ; Bremer, P. T. ; Spanias, Andreas. / Automatic image annotation using inverse maps from semantic embeddings. 2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 3107-3111
@inproceedings{fd7545affa8e424995b3474f67eac813,
title = "Automatic image annotation using inverse maps from semantic embeddings",
abstract = "Human annotation in large scale image databases is time-consuming and error-prone. Since it is very hard to mine image databases using just visual features or textual descriptors, it is common to transform the image features into a semantically meaningful space. In this paper, we propose to perform image annotation in a semantic space inferred based on sparse representations. By constructing a semantic embedding for the visual features, that is constrained to be close to the tag embedding, we show that a robust inverse map can be used to predict the tags. Experiments using standard datasets show the effectiveness of the proposed approach in automatic image annotation when compared to existing methods.",
keywords = "embedding, Image annotation, inverse map, RBF interpolation, sparse coding",
author = "Thiagarajan, {J. J.} and Ramamurthy, {K. N.} and P. Sattigeri and Bremer, {P. T.} and Andreas Spanias",
year = "2014",
month = "1",
day = "28",
doi = "10.1109/ICIP.2014.7025628",
language = "English (US)",
isbn = "9781479957514",
pages = "3107--3111",
booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Automatic image annotation using inverse maps from semantic embeddings

AU - Thiagarajan, J. J.

AU - Ramamurthy, K. N.

AU - Sattigeri, P.

AU - Bremer, P. T.

AU - Spanias, Andreas

PY - 2014/1/28

Y1 - 2014/1/28

N2 - Human annotation in large scale image databases is time-consuming and error-prone. Since it is very hard to mine image databases using just visual features or textual descriptors, it is common to transform the image features into a semantically meaningful space. In this paper, we propose to perform image annotation in a semantic space inferred based on sparse representations. By constructing a semantic embedding for the visual features, that is constrained to be close to the tag embedding, we show that a robust inverse map can be used to predict the tags. Experiments using standard datasets show the effectiveness of the proposed approach in automatic image annotation when compared to existing methods.

AB - Human annotation in large scale image databases is time-consuming and error-prone. Since it is very hard to mine image databases using just visual features or textual descriptors, it is common to transform the image features into a semantically meaningful space. In this paper, we propose to perform image annotation in a semantic space inferred based on sparse representations. By constructing a semantic embedding for the visual features, that is constrained to be close to the tag embedding, we show that a robust inverse map can be used to predict the tags. Experiments using standard datasets show the effectiveness of the proposed approach in automatic image annotation when compared to existing methods.

KW - embedding

KW - Image annotation

KW - inverse map

KW - RBF interpolation

KW - sparse coding

UR - http://www.scopus.com/inward/record.url?scp=84949928088&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949928088&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2014.7025628

DO - 10.1109/ICIP.2014.7025628

M3 - Conference contribution

SN - 9781479957514

SP - 3107

EP - 3111

BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -