| Paper Abstract and Keywords |
| Presentation |
2026-02-20 15:15
VLM-based Zero-shot Dense Video Captioning of Instructional Videos Using Hand-Centric Object Context
Riku Yamaguchi, Yota Yamamoto, Ryosuke Furuta, Yukinobu Taniguchi (TUS) |
| Abstract |
(in Japanese) |
(See Japanese page) |
| (in English) |
Against the background of labor shortages in the manufacturing and service industries, there is growing demand for automating skill transfer and manual generation using instructional videos. Dense Video Captioning (DVC), which simultaneously generates temporal scene segments and corresponding textual captions from videos, has emerged as a core technology for this purpose. However, conventional DVC methods require large amounts of annotated training data, posing a significant limitation for practical deployment. Furthermore, zero-shot approaches based on Vision-Language Models (VLMs) tend to produce inaccurate captions and excessive scene segmentation in instructional videos due to fine-grained hand actions and reduced object visibility. To address these issues, this study proposes a zero-shot DVC method that temporally aggregates object class information in hand-centric regions and incorporates it as semantic context into VLM prompts to explicitly represent semantic task changes. Experimental results on cooking and assembly video datasets show that the proposed method outperforms baseline approaches in both caption quality and scene segmentation accuracy. |
| Keyword |
(in Japanese) |
(See Japanese page) |
| (in English) |
Instructional Video Analysis / Dense Video Captioning / Vision-Language Model / Zero-shot / Hand-Centric Object Recognition / / / |
| Reference Info. |
ITE Tech. Rep., vol. 50, no. 5, ME2026-36, pp. 157-160, Feb. 2026. |
| Paper # |
ME2026-36 |
| Date of Issue |
2026-02-12 (MMS, ME, AIT, SIP) |
| ISSN |
Online edition: ISSN 2424-1970 |
| Download PDF |
|
| Conference Information |
| Committee |
IEICE-IE IEICE-ITS MMS ME AIT SIP |
| Conference Date |
2026-02-19 - 2026-02-20 |
| Place (in Japanese) |
(See Japanese page) |
| Place (in English) |
|
| Topics (in Japanese) |
(See Japanese page) |
| Topics (in English) |
|
| Paper Information |
| Registration To |
ME |
| Conference Code |
2026-02-IE-ITS-MMS-ME-AIT-SIP |
| Language |
Japanese |
| Title (in Japanese) |
(See Japanese page) |
| Sub Title (in Japanese) |
(See Japanese page) |
| Title (in English) |
VLM-based Zero-shot Dense Video Captioning of Instructional Videos Using Hand-Centric Object Context |
| Sub Title (in English) |
|
| Keyword(1) |
Instructional Video Analysis |
| Keyword(2) |
Dense Video Captioning |
| Keyword(3) |
Vision-Language Model |
| Keyword(4) |
Zero-shot |
| Keyword(5) |
Hand-Centric Object Recognition |
| Keyword(6) |
|
| Keyword(7) |
|
| Keyword(8) |
|
| 1st Author's Name |
Riku Yamaguchi |
| 1st Author's Affiliation |
Tokyo University of Science (TUS) |
| 2nd Author's Name |
Yota Yamamoto |
| 2nd Author's Affiliation |
Tokyo University of Science (TUS) |
| 3rd Author's Name |
Ryosuke Furuta |
| 3rd Author's Affiliation |
Tokyo University of Science (TUS) |
| 4th Author's Name |
Yukinobu Taniguchi |
| 4th Author's Affiliation |
Tokyo University of Science (TUS) |
| 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 |
2026-02-20 15:15:00 |
| Presentation Time |
15 minutes |
| Registration for |
ME |
| Paper # |
MMS2026-36, ME2026-36, AIT2026-36, SIP2026-36 |
| Volume (vol) |
vol.50 |
| Number (no) |
no.5 |
| Page |
pp.157-160 |
| #Pages |
4 |
| Date of Issue |
2026-02-12 (MMS, ME, AIT, SIP) |