| Item Type |
Article |
| ID |
|
| Preview |
| Image |
|
| Caption |
|
|
| Full text |
KO11003001-20230304-0050.pdf
| Type |
:application/pdf |
Download
|
| Size |
:839.8 KB
|
| Last updated |
:Feb 20, 2024 |
| Downloads |
: 40 |
Total downloads since Feb 20, 2024 : 40
|
|
| Release Date |
|
| Title |
| Title |
Relational Future Captioning Model for explaining likely collisions in daily tasks
|
| Kana |
|
| Romanization |
|
|
| Other Title |
|
| Creator |
| Name |
神原, 元就
|
| Kana |
カンバラ, モトナリ
|
| Romanization |
Kambara, Motonari
|
| Affiliation |
慶應義塾大学
|
| Affiliation (Translated) |
Keio University
|
| Role |
|
| Link |
|
| Name |
杉浦, 孔明
 |
| Kana |
スギウラ, コウメイ
|
| Romanization |
Sugiura, Komei
|
| Affiliation |
慶應義塾大学
|
| Affiliation (Translated) |
Keio University
|
| 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 |
50
|
| End page |
54
|
|
| ISSN |
|
| ISBN |
|
| DOI |
|
| URI |
|
| JaLCDOI |
|
| NII Article ID |
|
| Ichushi ID |
|
| Other ID |
|
| Doctoral dissertation |
| Dissertation Number |
|
| Date of granted |
|
| Degree name |
|
| Degree grantor |
|
|
| Abstract |
Domestic service robots that support daily tasks are a promising solution for elderly or disabled people. It is crucial for domestic service robots to explain the collision risk before they perform actions. In this paper, our aim is to generate a caption about a future event. We propose the Relational Future Captioning Model (RFCM), a crossmodal language generation model for the future captioning task. The RFCM has the Relational Self-Attention Encoder to extract the relationships between events more effectively than the conventional self-attention in transformers. We conducted comparison experiments, and the results show the RFCM outperforms a baseline method on two datasets.
|
|
| Table of contents |
|
| Keyword |
| Relational Self-Attention
|
|
| 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3章既発表セッション要旨
既発表要旨-3
|
|
| Language |
|
| Type of resource |
|
| Genre |
|
| Text version |
|
| Related DOI |
|
| Access conditions |
|
| Last modified date |
|
| Creation date |
|
| Registerd by |
|
| History |
| Feb 20, 2024 | | インデックス を変更 |
| Feb 20, 2024 | | Creator Name,Creator Kana,Creator Romanization,Creator Affiliation,Creator Affiliation (Translated),Creator Role,Creator Link,Note 注記 を変更 |
|
|
| Index |
|
| Related to |
|
