| Paper Abstract and Keywords |
| Presentation |
2025-02-18 16:10
Experimental Discussion on the Attention Mechanism of HEVC and 3D CG Images Using Vision Transformer
Norifumi Kawabata (Computational Imaging Lab) |
| Abstract |
(in Japanese) |
(See Japanese page) |
| (in English) |
It is important to create media content based on a preliminary understanding of what people pay attention to and what they are interested in when they observe images. Many computer vision studies have been conducted on the Region Of Interest (ROI) when humans gaze at images. We specifically measured the Region Of Interest (ROI) between image coding and the gazing point by using saliency maps. However, we did not sufficiently consider factors other than area as an evaluation index, and the accuracy was not sufficient. Therefore, we thought that the knowledge of the Vision Transformer, which was derived the field of natural language processing and built in the field of computer vision, could be used to estimate the Region Of Interest (ROI) with higher accuracy. In this study, we experimentally examined whether Region Of Interest (ROI) estimation can be performed on HEVC encoded 3D CG images by using the Attention mechanism of the Vision Transformer, and whether Region Of Interest (ROI) evaluation of images can be performed by image analysis. |
| Keyword |
(in Japanese) |
(See Japanese page) |
| (in English) |
3D CG Image / H.265/HEVC / Vision Transformer (ViT) / Region Of Interest (ROI) / Attention Map / Artificial Intelligence (AI) Architecture / / |
| Reference Info. |
ITE Tech. Rep., vol. 49, no. 4, ME2025-19, pp. 96-101, Feb. 2025. |
| Paper # |
ME2025-19 |
| Date of Issue |
2025-02-11 (MMS, ME, AIT, SIP) |
| ISSN |
Online edition: ISSN 2424-1970 |
| Download PDF |
|
| Conference Information |
| Committee |
ME AIT MMS IEICE-IE IEICE-ITS SIP |
| Conference Date |
2025-02-18 - 2025-02-19 |
| Place (in Japanese) |
(See Japanese page) |
| Place (in English) |
Hokkaido Univ. |
| Topics (in Japanese) |
(See Japanese page) |
| Topics (in English) |
Image Processing, etc. |
| Paper Information |
| Registration To |
ME |
| Conference Code |
2025-02-ME-AIT-MMS-IE-ITS-SIP |
| Language |
Japanese |
| Title (in Japanese) |
(See Japanese page) |
| Sub Title (in Japanese) |
(See Japanese page) |
| Title (in English) |
Experimental Discussion on the Attention Mechanism of HEVC and 3D CG Images Using Vision Transformer |
| Sub Title (in English) |
|
| Keyword(1) |
3D CG Image |
| Keyword(2) |
H.265/HEVC |
| Keyword(3) |
Vision Transformer (ViT) |
| Keyword(4) |
Region Of Interest (ROI) |
| Keyword(5) |
Attention Map |
| Keyword(6) |
Artificial Intelligence (AI) Architecture |
| Keyword(7) |
|
| Keyword(8) |
|
| 1st Author's Name |
Norifumi Kawabata |
| 1st Author's Affiliation |
Computational Imaging Lab (Computational Imaging Lab) |
| 2nd Author's Name |
|
| 2nd Author's Affiliation |
() |
| 3rd Author's Name |
|
| 3rd Author's Affiliation |
() |
| 4th Author's Name |
|
| 4th Author's Affiliation |
() |
| 5th Author's Name |
|
| 5th Author's Affiliation |
() |
| 6th Author's Name |
|
| 6th Author's Affiliation |
() |
| 7th Author's Name |
|
| 7th Author's Affiliation |
() |
| 8th Author's Name |
|
| 8th Author's Affiliation |
() |
| 9th Author's Name |
|
| 9th Author's Affiliation |
() |
| 10th Author's Name |
|
| 10th Author's Affiliation |
() |
| 11th Author's Name |
|
| 11th Author's Affiliation |
() |
| 12th Author's Name |
|
| 12th Author's Affiliation |
() |
| 13th Author's Name |
|
| 13th Author's Affiliation |
() |
| 14th Author's Name |
|
| 14th Author's Affiliation |
() |
| 15th Author's Name |
|
| 15th Author's Affiliation |
() |
| 16th Author's Name |
|
| 16th Author's Affiliation |
() |
| 17th Author's Name |
|
| 17th Author's Affiliation |
() |
| 18th Author's Name |
|
| 18th Author's Affiliation |
() |
| 19th Author's Name |
|
| 19th Author's Affiliation |
() |
| 20th Author's Name |
|
| 20th Author's Affiliation |
() |
| 21st Author's Name |
|
| 21st Author's Affiliation |
() |
| 22nd Author's Name |
|
| 22nd Author's Affiliation |
() |
| 23rd Author's Name |
|
| 23rd Author's Affiliation |
() |
| 24th Author's Name |
|
| 24th Author's Affiliation |
() |
| 25th Author's Name |
|
| 25th Author's Affiliation |
() |
| 26th Author's Name |
/ / |
| 26th Author's Affiliation |
()
() |
| 27th Author's Name |
/ / |
| 27th Author's Affiliation |
()
() |
| 28th Author's Name |
/ / |
| 28th Author's Affiliation |
()
() |
| 29th Author's Name |
/ / |
| 29th Author's Affiliation |
()
() |
| 30th Author's Name |
/ / |
| 30th Author's Affiliation |
()
() |
| 31st Author's Name |
/ / |
| 31st Author's Affiliation |
()
() |
| 32nd Author's Name |
/ / |
| 32nd Author's Affiliation |
()
() |
| 33rd Author's Name |
/ / |
| 33rd Author's Affiliation |
()
() |
| 34th Author's Name |
/ / |
| 34th Author's Affiliation |
()
() |
| 35th Author's Name |
/ / |
| 35th Author's Affiliation |
()
() |
| 36th Author's Name |
/ / |
| 36th Author's Affiliation |
()
() |
| Speaker |
Author-1 |
| Date Time |
2025-02-18 16:10:00 |
| Presentation Time |
15 minutes |
| Registration for |
ME |
| Paper # |
MMS2025-19, ME2025-19, AIT2025-19, SIP2025-19 |
| Volume (vol) |
vol.49 |
| Number (no) |
no.4 |
| Page |
pp.96-101 |
| #Pages |
6 |
| Date of Issue |
2025-02-11 (MMS, ME, AIT, SIP) |