BioVL-QR: Egocentric Biochemical Vision-and-Language Dataset Using Micro QR Codes

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Nishimoto, Tomohiro, Nishimura, Taichi, Yamamoto, Koki, Shirai, Keisuke, Kameko, Hirotaka, Haneji, Yuto, Yoshida, Tomoya, Kajimura, Keiya, Cui, Taiyu, Nishiwaki, Chihiro, Daikoku, Eriko, Okuda, Natsuko, Ono, Fumihito, Mori, Shinsuke
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912401326080000
author Nishimoto, Tomohiro
Nishimura, Taichi
Yamamoto, Koki
Shirai, Keisuke
Kameko, Hirotaka
Haneji, Yuto
Yoshida, Tomoya
Kajimura, Keiya
Cui, Taiyu
Nishiwaki, Chihiro
Daikoku, Eriko
Okuda, Natsuko
Ono, Fumihito
Mori, Shinsuke
author_facet Nishimoto, Tomohiro
Nishimura, Taichi
Yamamoto, Koki
Shirai, Keisuke
Kameko, Hirotaka
Haneji, Yuto
Yoshida, Tomoya
Kajimura, Keiya
Cui, Taiyu
Nishiwaki, Chihiro
Daikoku, Eriko
Okuda, Natsuko
Ono, Fumihito
Mori, Shinsuke
contents This paper introduces BioVL-QR, a biochemical vision-and-language dataset comprising 23 egocentric experiment videos, corresponding protocols, and vision-and-language alignments. A major challenge in understanding biochemical videos is detecting equipment, reagents, and containers because of the cluttered environment and indistinguishable objects. Previous studies assumed manual object annotation, which is costly and time-consuming. To address the issue, we focus on Micro QR Codes. However, detecting objects using only Micro QR Codes is still difficult due to blur and occlusion caused by object manipulation. To overcome this, we propose an object labeling method combining a Micro QR Code detector with an off-the-shelf hand object detector. As an application of the method and BioVL-QR, we tackled the task of localizing the procedural steps in an instructional video. The experimental results show that using Micro QR Codes and our method improves biochemical video understanding. Data and code are available through https://nishi10mo.github.io/BioVL-QR/
format Preprint
id arxiv_https___arxiv_org_abs_2404_03161
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BioVL-QR: Egocentric Biochemical Vision-and-Language Dataset Using Micro QR Codes
Nishimoto, Tomohiro
Nishimura, Taichi
Yamamoto, Koki
Shirai, Keisuke
Kameko, Hirotaka
Haneji, Yuto
Yoshida, Tomoya
Kajimura, Keiya
Cui, Taiyu
Nishiwaki, Chihiro
Daikoku, Eriko
Okuda, Natsuko
Ono, Fumihito
Mori, Shinsuke
Computer Vision and Pattern Recognition
Computation and Language
Multimedia
This paper introduces BioVL-QR, a biochemical vision-and-language dataset comprising 23 egocentric experiment videos, corresponding protocols, and vision-and-language alignments. A major challenge in understanding biochemical videos is detecting equipment, reagents, and containers because of the cluttered environment and indistinguishable objects. Previous studies assumed manual object annotation, which is costly and time-consuming. To address the issue, we focus on Micro QR Codes. However, detecting objects using only Micro QR Codes is still difficult due to blur and occlusion caused by object manipulation. To overcome this, we propose an object labeling method combining a Micro QR Code detector with an off-the-shelf hand object detector. As an application of the method and BioVL-QR, we tackled the task of localizing the procedural steps in an instructional video. The experimental results show that using Micro QR Codes and our method improves biochemical video understanding. Data and code are available through https://nishi10mo.github.io/BioVL-QR/
title BioVL-QR: Egocentric Biochemical Vision-and-Language Dataset Using Micro QR Codes
topic Computer Vision and Pattern Recognition
Computation and Language
Multimedia
url https://arxiv.org/abs/2404.03161