VQA: Visual Question Answering
| Autor: | Jiasen Lu, Margaret Mitchell, C. Lawrence Zitnick, Stanislaw Antol, Dhruv Batra, Aishwarya Agrawal, Devi Parikh |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Questions and answers
Information retrieval Closed set Computer science 020207 software engineering Context (language use) 02 engineering and technology Task (project management) Image (mathematics) Artificial Intelligence 0202 electrical engineering electronic engineering information engineering Question answering 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Software Natural language Mirroring |
| Zdroj: | International Journal of Computer Vision. 123:4-31 |
| ISSN: | 1573-1405 0920-5691 |
| Popis: | We propose the task of free-form and open-ended Visual Question Answering (VQA). Given an image and a natural language question about the image, the task is to provide an accurate natural language answer. Mirroring real-world scenarios, such as helping the visually impaired, both the questions and answers are open-ended. Visual questions selectively target different areas of an image, including background details and underlying context. As a result, a system that succeeds at VQA typically needs a more detailed understanding of the image and complex reasoning than a system producing generic image captions. Moreover, VQA is amenable to automatic evaluation, since many open-ended answers contain only a few words or a closed set of answers that can be provided in a multiple-choice format. We provide a dataset containing $$\sim $$~0.25 M images, $$\sim $$~0.76 M questions, and $$\sim $$~10 M answers (www.visualqa.org), and discuss the information it provides. Numerous baselines and methods for VQA are provided and compared with human performance. Our VQA demo is available on CloudCV (http://cloudcv.org/vqa). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink