Item type |
デフォルトアイテムタイプ_(フル)(1) |
公開日 |
2023-03-18 |
タイトル |
|
|
タイトル |
Completion of Missing Labels for Multi-Label Annotation by a Unified Graph Laplacian Regularization |
|
言語 |
en |
作成者 |
MOJOO, Jonathan
ZHAO, Yu
KAVITHA, Muthu Subash
MIYAO, Junichi
KURITA, Takio
|
アクセス権 |
|
|
アクセス権 |
open access |
|
アクセス権URI |
http://purl.org/coar/access_right/c_abf2 |
権利情報 |
|
|
権利情報 |
Copyright © 2020 The Institute of Electronics, Information and Communication Engineers |
主題 |
|
|
主題Scheme |
Other |
|
主題 |
multi-label image annotation |
主題 |
|
|
主題Scheme |
Other |
|
主題 |
regularization |
主題 |
|
|
主題Scheme |
Other |
|
主題 |
missing labels |
内容記述 |
|
|
内容記述 |
The task of image annotation is becoming enormously important for efficient image retrieval from the web and other large databases. However, huge semantic information and complex dependency of labels on an image make the task challenging. Hence determining the semantic similarity between multiple labels on an image is useful to understand any incomplete label assignment for image retrieval. This work proposes a novel method to solve the problem of multi-label image annotation by unifying two different types of Laplacian regularization terms in deep convolutional neural network (CNN) for robust annotation performance. The unified Laplacian regularization model is implemented to address the missing labels efficiently by generating the contextual similarity between labels both internally and externally through their semantic similarities, which is the main contribution of this study. Specifically, we generate similarity matrices between labels internally by using Hayashi's quantification method-type III and externally by using the word2vec method. The generated similarity matrices from the two different methods are then combined as a Laplacian regularization term, which is used as the new objective function of the deep CNN. The Regularization term implemented in this study is able to address the multi-label annotation problem, enabling a more effectively trained neural network. Experimental results on public benchmark datasets reveal that the proposed unified regularization model with deep CNN produces significantly better results than the baseline CNN without regularization and other state-of-the-art methods for predicting missing labels. |
|
言語 |
en |
内容記述 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
This work was partly supported by JSPS KAKENHI Grant Number 16K00239. |
出版者 |
|
|
出版者 |
The Institute of Electronics, Information and Communication Engineers |
出版者 |
|
|
出版者 |
電子情報通信学会 |
言語 |
|
|
言語 |
eng |
資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_6501 |
|
資源タイプ |
journal article |
出版タイプ |
|
|
出版タイプ |
VoR |
|
出版タイプResource |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
関連情報 |
|
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
10.1587/transinf.2019EDP7318 |
関連情報 |
|
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.1587/transinf.2019EDP7318 |
収録物識別子 |
|
|
収録物識別子タイプ |
ISSN |
|
収録物識別子 |
0916-8532 |
収録物識別子 |
|
|
収録物識別子タイプ |
ISSN |
|
収録物識別子 |
1745-1361 |
開始ページ |
|
|
開始ページ |
2154 |
書誌情報 |
IEICE Transactions on Information and Systems
IEICE Transactions on Information and Systems
巻 E103.D,
号 10,
p. 2154-2161,
発行日 2020-10-01
|
旧ID |
51543 |