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 language | English (US) |
|---|---|
| Title of host publication | 2014 IEEE International Conference on Image Processing, ICIP 2014 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 3107-3111 |
| Number of pages | 5 |
| ISBN (Print) | 9781479957514 |
| DOIs | |
| State | Published - Jan 28 2014 |
Fingerprint
Keywords
- embedding
- Image annotation
- inverse map
- RBF interpolation
- sparse coding
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
Cite this
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 proceeding › Conference contribution
}
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 -