Name:
Wu_Diverse_Image_Annotation_CVPR_2017_paper.pdf
Size:
1.369Mb
Format:
PDF
Description:
Accepted Manuscript
Type
Conference PaperKAUST Department
Visual Computing Center (VCC)Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Electrical Engineering Program
Date
2017-11-09Online Publication Date
2017-11-09Print Publication Date
2017-07Permanent link to this record
http://hdl.handle.net/10754/626228
Metadata
Show full item recordAbstract
In this work we study the task of image annotation, of which the goal is to describe an image using a few tags. Instead of predicting the full list of tags, here we target for providing a short list of tags under a limited number (e.g., 3), to cover as much information as possible of the image. The tags in such a short list should be representative and diverse. It means they are required to be not only corresponding to the contents of the image, but also be different to each other. To this end, we treat the image annotation as a subset selection problem based on the conditional determinantal point process (DPP) model, which formulates the representation and diversity jointly. We further explore the semantic hierarchy and synonyms among the candidate tags, and require that two tags in a semantic hierarchy or in a pair of synonyms should not be selected simultaneously. This requirement is then embedded into the sampling algorithm according to the learned conditional DPP model. Besides, we find that traditional metrics for image annotation (e.g., precision, recall and F1 score) only consider the representation, but ignore the diversity. Thus we propose new metrics to evaluate the quality of the selected subset (i.e., the tag list), based on the semantic hierarchy and synonyms. Human study through Amazon Mechanical Turk verifies that the proposed metrics are more close to the humans judgment than traditional metrics. Experiments on two benchmark datasets show that the proposed method can produce more representative and diverse tags, compared with existing image annotation methods.Citation
Wu B, Jia F, Liu W, Ghanem B (2017) Diverse Image Annotation. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Available: http://dx.doi.org/10.1109/cvpr.2017.656.Sponsors
This work is supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research. Baoyuan Wu is partially supported by Tencent AI Lab. We thank Fabian Caba for his help in conducting the online subject studies.Additional Links
http://ieeexplore.ieee.org/document/8100139/ae974a485f413a2113503eed53cd6c53
10.1109/cvpr.2017.656