| アイテムタイプ |
itemtype_ver1(1) |
| 公開日 |
2024-05-23 |
| タイトル |
|
|
タイトル |
Nonword-to-Image Generation Considering Perceptual Association of Phonetically Similar Words |
|
言語 |
en |
| 著者 |
Matsuhira, Chihaya
Kastner, Marc A.
Komamizu, Takahiro
Hirayama, Takatsugu
Doman, Keisuke
Ide, Ichiro
|
| 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 |
| 内容記述 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
Text-to-Image (T2I) generation has long been a popular field of multimedia processing. Recent advances in large-scale vision and language pretraining have brought a number of models capable of very high-quality T2I generation. However, they are reported to generate unexpected images when users input words that have no definition within a language (nonwords), including coined words and pseudo-words. To make the behavior of T2I generation models against nonwords more intuitive, we propose a method that considers phonetic information of text inputs. The phonetic similarity is adopted so that the generated images from a nonword contain the concept of its phonetically similar words. This is based on the psycholinguistic finding that humans would also associate nonwords with their phonetically similar words when they perceive the sound. Our evaluations confirm a better agreement of the generated images of the proposed method with both phonetic relationships and human expectations than a conventional T2I generation model. The cross-lingual comparison of generated images for a nonword highlights the differences in language-specific nonword-imagery correspondences. These results provide insight into the usefulness of the proposed method in brand naming and language learning. |
|
言語 |
en |
| 内容記述 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
MM '23: The 31st ACM International Conference on Multimedia Ottawa ON Canada 29 October 2023 |
|
言語 |
en |
| 出版者 |
|
|
出版者 |
Association for Computing Machinery |
|
言語 |
en |
| 言語 |
|
|
言語 |
eng |
| 資源タイプ |
|
|
資源タイプresource |
http://purl.org/coar/resource_type/c_5794 |
|
タイプ |
conference paper |
| 出版タイプ |
|
|
出版タイプ |
AM |
|
出版タイプResource |
http://purl.org/coar/version/c_ab4af688f83e57aa |
| 関連情報 |
|
|
関連タイプ |
isVersionOf |
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.1145/3607541.3616818 |
| 関連情報 |
|
|
関連タイプ |
isPartOf |
|
|
識別子タイプ |
ISBN |
|
|
関連識別子 |
979-8-4007-0278-5 |
| 書誌情報 |
en : McGE '23: Proceedings of the 1st International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice
p. 115-125,
発行日 2023-10
|
matsuhirac_ACMMM2023_McGE.pdf (8.7 MB)
