allenai/aokvqa
Official repository for the A-OKVQA dataset
This project provides a comprehensive dataset to help AI researchers and developers build smarter visual question-answering systems. It includes diverse images paired with questions that require common sense and real-world knowledge, not just information found directly in the image. The dataset takes in images and natural language questions, and outputs the correct answer along with a rationale explaining the reasoning. It's designed for AI researchers and machine learning engineers working on advanced computer vision and natural language processing models.
113 stars. No commits in the last 6 months.
Use this if you are developing or evaluating AI models that need to answer complex questions about images by applying common sense and broad world knowledge.
Not ideal if your visual question answering tasks only require direct observation from an image without needing external knowledge or complex reasoning.
Stars
113
Forks
14
Language
Python
License
Apache-2.0
Category
Last pushed
May 08, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/allenai/aokvqa"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
asahi417/lm-question-generation
Multilingual/multidomain question generation datasets, models, and python library for question...
SparkJiao/SLQA
An Unofficial Pytorch Implementation of Multi-Granularity Hierarchical Attention Fusion Networks...
MurtyShikhar/Question-Answering
TensorFlow implementation of Match-LSTM and Answer pointer for the popular SQuAD dataset.
hsinyuan-huang/FlowQA
Implementation of conversational QA model: FlowQA (with slight improvement)
liamdugan/summary-qg
Code for the ACL 2022 Paper "A Feasibility Study of Answer-Agnostic Question Generation for Education"