A multiple instance learning approach to image annotation with saliency map

Tran Phuong Nhung; Cam Tu Nguyen; Jinhee Chun; Ha Vu Le; Takeshi Tokuyama

doi:10.5220/0004543901520159

A multiple instance learning approach to image annotation with saliency map

Tran Phuong Nhung, Cam Tu Nguyen, Jinhee Chun, Ha Vu Le, Takeshi Tokuyama

INF - System Information Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper presents a novel approach to image annotation based on multi-instance learning (MIL) and saliency map. Image Annotation is an automatic process of assigning labels to images so as to obtain semantic retrieval of images. This problem is often ambiguous as a label is given to the whole image while it may only corresponds to a small region in the image. As a result, MIL methods are suitable solutions to resolve the ambiguities during learning. On the other hand, saliency detection aims at detecting foreground/background regions in images. Once we obtain this information, labels and image regions can be aligned better, i.e., foreground labels (background labels) are more sensitive to foreground areas (background areas). Our proposed method, which is based on an ensemble of MIL classifiers from two views (background/foreground), improves annotation performance in comparison to baseline methods that do not exploit saliency information.

Original language	English
Title of host publication	IC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.
Publisher	SciTePress
Pages	152-159
Number of pages	8
ISBN (Print)	9789898565754
DOIs	https://doi.org/10.5220/0004543901520159
Publication status	Published - 2013
Event	5th International Conference on Knowledge Discovery and Information Retrieval, KDIR 2013 and the 5th International Conference on Knowledge Management and Information Sharing, KMIS 2013 - Vilamoura, Algarve, Portugal Duration: 2013 Sep 19 → 2013 Sep 22

Publication series

Name	IC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.

Other

Other	5th International Conference on Knowledge Discovery and Information Retrieval, KDIR 2013 and the 5th International Conference on Knowledge Management and Information Sharing, KMIS 2013
Country/Territory	Portugal
City	Vilamoura, Algarve
Period	13/9/19 → 13/9/22

Keywords

Image annotation
Multiple instance learning
Visual saliency

ASJC Scopus subject areas

Information Systems
Software

Access to Document

10.5220/0004543901520159

Cite this

Nhung, T. P., Nguyen, C. T., Chun, J., Le, H. V., & Tokuyama, T. (2013). A multiple instance learning approach to image annotation with saliency map. In IC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc. (pp. 152-159). (IC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.). SciTePress. https://doi.org/10.5220/0004543901520159

A multiple instance learning approach to image annotation with saliency map. / Nhung, Tran Phuong; Nguyen, Cam Tu; Chun, Jinhee; Le, Ha Vu; Tokuyama, Takeshi.

IC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.. SciTePress, 2013. p. 152-159 (IC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Nhung, TP, Nguyen, CT, Chun, J, Le, HV & Tokuyama, T 2013, A multiple instance learning approach to image annotation with saliency map. in IC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.. IC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc., SciTePress, pp. 152-159, 5th International Conference on Knowledge Discovery and Information Retrieval, KDIR 2013 and the 5th International Conference on Knowledge Management and Information Sharing, KMIS 2013, Vilamoura, Algarve, Portugal, 13/9/19. https://doi.org/10.5220/0004543901520159

Nhung TP, Nguyen CT, Chun J, Le HV, Tokuyama T. A multiple instance learning approach to image annotation with saliency map. In IC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.. SciTePress. 2013. p. 152-159. (IC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.). https://doi.org/10.5220/0004543901520159

Nhung, Tran Phuong ; Nguyen, Cam Tu ; Chun, Jinhee ; Le, Ha Vu ; Tokuyama, Takeshi. / A multiple instance learning approach to image annotation with saliency map. IC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.. SciTePress, 2013. pp. 152-159 (IC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.).

@inproceedings{e7c190ba96844a58aaac39c105199b55,

title = "A multiple instance learning approach to image annotation with saliency map",

abstract = "This paper presents a novel approach to image annotation based on multi-instance learning (MIL) and saliency map. Image Annotation is an automatic process of assigning labels to images so as to obtain semantic retrieval of images. This problem is often ambiguous as a label is given to the whole image while it may only corresponds to a small region in the image. As a result, MIL methods are suitable solutions to resolve the ambiguities during learning. On the other hand, saliency detection aims at detecting foreground/background regions in images. Once we obtain this information, labels and image regions can be aligned better, i.e., foreground labels (background labels) are more sensitive to foreground areas (background areas). Our proposed method, which is based on an ensemble of MIL classifiers from two views (background/foreground), improves annotation performance in comparison to baseline methods that do not exploit saliency information.",

keywords = "Image annotation, Multiple instance learning, Visual saliency",

author = "Nhung, {Tran Phuong} and Nguyen, {Cam Tu} and Jinhee Chun and Le, {Ha Vu} and Takeshi Tokuyama",

year = "2013",

doi = "10.5220/0004543901520159",

language = "English",

isbn = "9789898565754",

series = "IC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.",

publisher = "SciTePress",

pages = "152--159",

booktitle = "IC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.",

note = "5th International Conference on Knowledge Discovery and Information Retrieval, KDIR 2013 and the 5th International Conference on Knowledge Management and Information Sharing, KMIS 2013 ; Conference date: 19-09-2013 Through 22-09-2013",

}

TY - GEN

T1 - A multiple instance learning approach to image annotation with saliency map

AU - Nhung, Tran Phuong

AU - Nguyen, Cam Tu

AU - Chun, Jinhee

AU - Le, Ha Vu

AU - Tokuyama, Takeshi

PY - 2013

Y1 - 2013

N2 - This paper presents a novel approach to image annotation based on multi-instance learning (MIL) and saliency map. Image Annotation is an automatic process of assigning labels to images so as to obtain semantic retrieval of images. This problem is often ambiguous as a label is given to the whole image while it may only corresponds to a small region in the image. As a result, MIL methods are suitable solutions to resolve the ambiguities during learning. On the other hand, saliency detection aims at detecting foreground/background regions in images. Once we obtain this information, labels and image regions can be aligned better, i.e., foreground labels (background labels) are more sensitive to foreground areas (background areas). Our proposed method, which is based on an ensemble of MIL classifiers from two views (background/foreground), improves annotation performance in comparison to baseline methods that do not exploit saliency information.

AB - This paper presents a novel approach to image annotation based on multi-instance learning (MIL) and saliency map. Image Annotation is an automatic process of assigning labels to images so as to obtain semantic retrieval of images. This problem is often ambiguous as a label is given to the whole image while it may only corresponds to a small region in the image. As a result, MIL methods are suitable solutions to resolve the ambiguities during learning. On the other hand, saliency detection aims at detecting foreground/background regions in images. Once we obtain this information, labels and image regions can be aligned better, i.e., foreground labels (background labels) are more sensitive to foreground areas (background areas). Our proposed method, which is based on an ensemble of MIL classifiers from two views (background/foreground), improves annotation performance in comparison to baseline methods that do not exploit saliency information.

KW - Image annotation

KW - Multiple instance learning

KW - Visual saliency

UR - http://www.scopus.com/inward/record.url?scp=84887701872&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887701872&partnerID=8YFLogxK

U2 - 10.5220/0004543901520159

DO - 10.5220/0004543901520159

M3 - Conference contribution

AN - SCOPUS:84887701872

SN - 9789898565754

T3 - IC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.

SP - 152

EP - 159

BT - IC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.

PB - SciTePress

T2 - 5th International Conference on Knowledge Discovery and Information Retrieval, KDIR 2013 and the 5th International Conference on Knowledge Management and Information Sharing, KMIS 2013

Y2 - 19 September 2013 through 22 September 2013

ER -

A multiple instance learning approach to image annotation with saliency map

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this