Jove
Visualize
お問い合わせ
JoVE
x logofacebook logolinkedin logoyoutube logo
JoVEについて
概要リーダーシップブログJoVEヘルプセンター
著者向け
出版プロセス編集委員会範囲と方針査読よくある質問投稿
図書館員向け
推薦の声購読アクセスリソース図書館諮問委員会よくある質問
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experimentsアーカイブ
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教員リソースセンター教員サイト
利用規約
プライバシーポリシー
ポリシー

関連する概念動画

Data Collection by Observations01:08

Data Collection by Observations

Data collection refers to a systematic way of obtaining, observing, measuring, and analyzing accurate information. Observational studies are one of the most widely used methods of data collection. It involves collecting data by observing the behavior and physical characteristics of a sample without making any modifications to the sample.
An astronomer viewing the motion and brightness of stars in the sky and recording the data is an example of observational data collection. A botanist recording...
Data Collection I01:30

Data Collection I

Data collection gathers information needed to make accurate judgments about a patient's present condition. During a health history interview, subjective data is collected from the patient, their caregivers, or family members, and objective data is collected through observations and physical assessment. Patients are the primary source of subjective data. Thus information gathered from patients through interviews, observations, and physical examination is primary data. Secondary sources of data...
Data Collection II01:29

Data Collection II

The nursing history captures and records the patient's health status, so that a care plan evolves to meet the patient's individual needs. The nursing health history is a part of the initial assessment. A comprehensive history covers all health dimensions and plays a significant role in the assessment process. A comprehensive history includes the patient's biographical information, reasons for seeking health care, expectations, present and past health history, medications, and family,...
Data Reporting and Recording01:24

Data Reporting and Recording

Reporting and recording are crucial in data documentation. The timely, thorough, and accurate documentation of facts is essential when recording patient data. Failure to record findings during an assessment or interpretation of a problem will result in loss of information and make the patient document unreliable. The reader is left with general impressions if the information is not specific. A recording is documenting data of the individual's health information in a traceable, secure, and...

こちらも読む

関連記事

共著者、ジャーナル、引用グラフによってこの研究に関連する記事。

並び替え
Same author

Integrative multi-omics analysis uncovers the critical role of plant-derived ferulic acid influencing the occurrence of tomato Fusarium foot rot disease.

Microbiological research·2026
Same author

A cloud-edge adaptive lightweight network with dynamic inference enables real-time ultrasound image segmentation.

Scientific reports·2026
Same author

VideoPASTA: 7K Preference Pairs That Matter for Video-LLM Alignment.

Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing·2026
Same author

ChartQA-X: Generating Explanations for Visual Chart Reasoning.

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision·2026
Same author

ViDscribe: Multimodal AI for Customizing Audio Description and Question Answering in Online Videos.

Extended abstracts on Human factors in computing systems. CHI Conference·2026
Same author

DescribePro: Collaborative Audio Description with Human-AI Interaction.

ASSETS. Annual ACM Conference on Assistive Technologies·2026

関連する実験動画

Updated: Jun 15, 2026

Automated Interactive Video Playback for Studies of Animal Communication
07:21

Automated Interactive Video Playback for Studies of Animal Communication

Published on: February 9, 2011

13.6K

VideoA11y: アクセス可能なビデオ記述のための方法とデータセット

Chaoyu Li1, Sid Padmanabhuni1, Maryam S Cheema1

  • 1School of Computing and Augmented Intelligence, Arizona State University, Tempe, Arizona, USA.

Proceedings of the SIGCHI conference on human factors in computing systems. CHI Conference
|September 2, 2025
PubMed
まとめ

VideoA11yは,視覚障害者や視覚障害者のためのより良いビデオ説明を作成するために,マルチモダルの大型言語モデル (MLLMs) を使用しています. このアプローチは,現在の方法と比較してアクセシビリティとユーザー満足度を大幅に改善します.

キーワード:
盲目や視力低下者マルチモダルの大型言語モデルビデオアクセシビリティビデオ説明ビデオ 理解

さらに関連する動画

Portable Intermodal Preferential Looking IPL: Investigating Language Comprehension in Typically Developing Toddlers and Young Children with Autism
10:11

Portable Intermodal Preferential Looking IPL: Investigating Language Comprehension in Typically Developing Toddlers and Young Children with Autism

Published on: December 14, 2012

18.5K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.1K

関連する実験動画

Last Updated: Jun 15, 2026

Automated Interactive Video Playback for Studies of Animal Communication
07:21

Automated Interactive Video Playback for Studies of Animal Communication

Published on: February 9, 2011

13.6K
Portable Intermodal Preferential Looking IPL: Investigating Language Comprehension in Typically Developing Toddlers and Young Children with Autism
10:11

Portable Intermodal Preferential Looking IPL: Investigating Language Comprehension in Typically Developing Toddlers and Young Children with Autism

Published on: December 14, 2012

18.5K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.1K

科学分野:

  • コンピュータ科学
  • 人とコンピュータの相互作用
  • 人工知能

背景:

  • 視覚障害者や視覚障害者のアクセシビリティに ビデオ説明は不可欠です
  • 既存のAIで生成された記述は,トレーニングデータの制限により,BLVユーザーのニーズを満たすことができず,しばしば品質が欠けている.

研究 の 目的:

  • BLVユーザー向けに高品質のビデオ記述を生成するためのマルチモダルの大型言語モデル (MLLMs) とアクセシビリティガイドラインを用いたアプローチ (VideoA11y) を開発する.
  • VideoA11y-40Kデータセットを作成し,BLVユーザー向けの記述されたビデオの最大のコレクションを作成します.

主な方法:

  • MLLMとビデオアクセシビリティのガイドラインを活用して説明を作成します.
  • ビデオA11y-40Kのデータセットを整理し,4万件のビデオを記述した.
  • 視覚障害者やBLVの参加者とプロの記述者の間で実験を行い,記述の質を評価する.

主要な成果:

  • VideoA11yの記述は,初心者のアノテーションよりも優れていることが判明しました.
  • 生成された記述は,明確性,正確性,客観性,記述性,およびユーザー満足度において,訓練された人間の注釈に匹敵する品質を示した.
  • VideoA11y-40Kデータセットで微調整されたMLLMは,高品質のアクセシブルなビデオ記述を生成しました.

結論:

  • VideoA11yのアプローチは,BLVユーザーにとってアクセシブルなビデオ記述を生成します.
  • VideoA11y-40KデータセットとMLLMの微調整は,ビデオアクセシビリティの分野を進めている.
  • この作品は,BLVの個人のビジュアルコンテンツへのアクセスを改善するためのスケーラブルなソリューションを提供します.