HyperAIHyperAI

Command Palette

Search for a command to run...

Console

DAQUAR Real-World Image Question Answering Dataset

Date

3 years ago

Size

414.12 MB

Organization

Publish URL

www.mpi-inf.mpg.de

Paper URL

arxiv.org

Tags

Object Detection
Dataset Download
Join the Discord Community
Featured Image

DAQUAR, short for DAtaset for QUestion Answering on Real-world images, is a dataset for human question answering on images. The images in this dataset come from the NYU-Depth v2 dataset, all of which are RGBD images of indoor scenes, of which 795 are used for training and 654 are used for testing. There are two main types of question/answer pairs in DAQUAR: automatically generated and manually annotated.

DAQUAR.torrent
Seeding 0Downloading 3Completed 525Total Downloads 631
  • DAQUAR/
    • README.md
      1.2 KB
    • README.txt
      2.4 KB
      • data/
          • Consensus data on DAQUAR/
            • human_answers-consensus
              827.56 KB
          • DAQUAR builds upon NYU Depth v2 by N. Silberman et.al./
            • nyu_depth_images.tar
              411.98 MB
          • Full DAQUAR (all classes)/
            • qa.894.raw.test.txt
              412.32 MB
            • qa.894.raw.train.txt
              412.72 MB
            • qa.894.raw.txt
              413.46 MB
            • test.txt
              413.46 MB
            • train.txt
              413.47 MB
          • Metrics measuring performance/
            • calculate_wups.py
              413.48 MB
            • compute_consensus.py
              413.48 MB
            • gt_questions.txt
              413.48 MB
            • pred_answers.txt
              413.48 MB
          • Reduced DAQUAR (37 classes and 25 test images)/
            • qa.37.raw.reduced.test.txt
              413.5 MB
            • qa.37.raw.train.txt
              413.72 MB
            • qa.37.raw.txt
              414.12 MB
            • sampled_test_names.txt
              414.12 MB

Build AI with AI

From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.

AI Co-coding
Ready-to-use GPUs
Best Pricing
Get Started

Hyper Newsletters

Subscribe to our latest updates
We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning
Powered by MailChimp
DAQUAR Real-World Image Question Answering Dataset | Datasets | HyperAI