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 - 2013/1/1
Y1 - 2013/1/1
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 -