Item Type |
Article |
ID |
|
Preview |
Image |
|
Caption |
|
|
Full text |
KO11003001-20230304-0031.pdf
Type |
:application/pdf |
Download
|
Size |
:726.3 KB
|
Last updated |
:Feb 20, 2024 |
Downloads |
: 31 |
Total downloads since Feb 20, 2024 : 31
|
|
Release Date |
|
Title |
Title |
Nearest Neighbor Future Captioning : 物体配置タスクにおける衝突リスクに関する説明文生成
|
Kana |
Nearest Neighbor Future Captioning : ブッタイ ハイチ タスク ニ オケル ショウトツ リスク ニ カンスル セツメイブン セイセイ
|
Romanization |
Nearest Neighbor Future Captioning : buttai haichi tasuku ni okeru shōtotsu risuku ni kansuru setsumeibun seisei
|
|
Other Title |
|
Creator |
Name |
小松, 拓実
|
Kana |
コマツ, タクミ
|
Romanization |
Komatsu, Takumi
|
Affiliation |
慶應義塾大学理工学部情報工学科
|
Affiliation (Translated) |
|
Role |
|
Link |
|
|
Edition |
|
Place |
|
Publisher |
Name |
慶應義塾大学AI・高度プログラミングコンソーシアム
|
Kana |
ケイオウ ギジュク ダイガク AI・コウド プログラミング コンソーシアム
|
Romanization |
Keiō gijuku daigaku AI kōdo puroguramingu konsōshiamu
|
|
Date |
Issued (from:yyyy) |
2023
|
Issued (to:yyyy) |
|
Created (yyyy-mm-dd) |
|
Updated (yyyy-mm-dd) |
|
Captured (yyyy-mm-dd) |
|
|
Physical description |
|
Source Title |
Name |
AICカンファレンス予稿集
|
Name (Translated) |
|
Volume |
|
Issue |
|
Year |
2023
|
Month |
|
Start page |
31
|
End page |
31
|
|
ISSN |
|
ISBN |
|
DOI |
|
URI |
|
JaLCDOI |
|
NII Article ID |
|
Ichushi ID |
|
Other ID |
|
Doctoral dissertation |
Dissertation Number |
|
Date of granted |
|
Degree name |
|
Degree grantor |
|
|
Abstract |
Although Domestic Service Robots (DSRs) that support people in everyday environments have been widely investigated, the DSR’s ability to predict and describe future risks resulting from their own actions is still insufficient. In this study, we therefore focus on the linguistic explainability for the DSRs. Most existing methods do not explicitly model the region of possible collisions; thus, they do not properly generate descriptions for regions of possible collisions. In this paper, we propose Nearest Neighbor Future Captioning Model that introduces Nearest Neighbor Language Model to future captioning regarding possible collisions, which enhances the model output with a nearest neighbors retrieval mechanism. Moreover, we introduce Collision Attention Module, which extracts attention regions of possible collisions, which enables our model to generate descriptions that adequately reflect the objects associated with possible collisions. Experimental results demonstrated that our method outperformed baseline methods on the standard metrics.
|
|
Table of contents |
|
Keyword |
Nearest Neighbor Language Model explainability
|
|
NDC |
|
Note |
会議名 : AICカンファレンス2023
開催地 : 慶應義塾大学日吉キャンパス
日時 : 2023年3月4日
第2章ポスター発表要旨
ポスター要旨-6
|
|
Language |
|
Type of resource |
|
Genre |
|
Text version |
|
Related DOI |
|
Access conditions |
|
Last modified date |
|
Creation date |
|
Registerd by |
|
History |
|
Index |
|
Related to |
|