-
A novel image tag completion method based on convolutional neural network
In the problems of image retrieval and annotation, complete textual tag ...
read it
-
A Joint Named-Entity Recognizer for Heterogeneous Tag-setsUsing a Tag Hierarchy
We study a variant of domain adaptation for named-entity recognition whe...
read it
-
Automatic Tag Recommendation for Painting Artworks Using Diachronic Descriptions
In this paper, we deal with the problem of automatic tag recommendation ...
read it
-
Constructing Hierarchical Image-tags Bimodal Representations for Word Tags Alternative Choice
This paper describes our solution to the multi-modal learning challenge ...
read it
-
Hybrid Generative/Discriminative Learning for Automatic Image Annotation
Automatic image annotation (AIA) raises tremendous challenges to machine...
read it
-
A Tree Adjoining Grammar Representation for Models Of Stochastic Dynamical Systems
Model structure and complexity selection remains a challenging problem i...
read it
-
A novel time-efficient frame adjustment strategy for RFID anti-collision
Recently, with the widespread popularization of radio frequency identifi...
read it
Adaptive Tag Selection for Image Annotation
Not all tags are relevant to an image, and the number of relevant tags is image-dependent. Although many methods have been proposed for image auto-annotation, the question of how to determine the number of tags to be selected per image remains open. The main challenge is that for a large tag vocabulary, there is often a lack of ground truth data for acquiring optimal cutoff thresholds per tag. In contrast to previous works that pre-specify the number of tags to be selected, we propose in this paper adaptive tag selection. The key insight is to divide the vocabulary into two disjoint subsets, namely a seen set consisting of tags having ground truth available for optimizing their thresholds and a novel set consisting of tags without any ground truth. Such a division allows us to estimate how many tags shall be selected from the novel set according to the tags that have been selected from the seen set. The effectiveness of the proposed method is justified by our participation in the ImageCLEF 2014 image annotation task. On a set of 2,065 test images with ground truth available for 207 tags, the benchmark evaluation shows that compared to the popular top-k strategy which obtains an F-score of 0.122, adaptive tag selection achieves a higher F-score of 0.223. Moreover, by treating the underlying image annotation system as a black box, the new method can be used as an easy plug-in to boost the performance of existing systems.
READ FULL TEXT
Comments
There are no comments yet.