Visual Question Answering (VQA) is a dataset containing open-ended questions about images. These questions require an understanding of vision, language and commonsense knowledge to answer. The first version of the dataset was released in October 2015. VQA v2.0 was released in April 2017.

Visual Question Answering (VQA) v2.0 is a dataset containing open-ended questions about images. These questions require an understanding of vision, language and commonsense knowledge to answer. It is the second version of the VQA dataset.

265,016 images (COCO and abstract scenes) At least 3 questions (5.4 questions on average) per image 10 ground truth answers per question 3 plausible (but likely incorrect) answers per question Automatic evaluation metric

The first version of the dataset was released in October 2015.

A BitTorrent file to download data with the title 'VQA: Visual Question Answering Dataset'

Our dataset consists of the images associated with textual questions. One entry (instance) in our dataset is a question-image pair labeled with the ground truth coordinates of a bounding box containing the visual answer to the given question. The images were obtained from a CC BY-licensed subset of the Microsoft Common Objects in Context dataset, MS COCO. All data labeling was performed on the Toloka crowdsourcing platform, https://toloka.ai/.

Our dataset has 45,199 instances split among three subsets: train (38,990 instances), public test (1,705 instances), and private test (4,504 instances). The entire train dataset was available for everyone since the start of the challenge. The public test dataset was available since the evaluation phase of the competition, but without any ground truth labels. After the end of the competition, public and private sets were released.

The datasets will be provided as files in the comma-separated values (CSV) format containing the following columns.

    Column
    Type
    Description


    image
    string
    URL of an image on a public content delivery network


    width
    integer
    image width


    height
    integer
    image height


    left
    integer
    bounding box coordinate: left


    top
    integer
    bounding box coordinate: top


    right
    integer
    bounding box coordinate: right


    bottom
    integer
    bounding box coordinate: bottom


    question
    string
    question in English

This upload also contains a ZIP file with the images from MS COCO.

PitVQA dataset comprises 25 videos of endoscopic pituitary surgeries from the National Hospital of Neurology and Neurosurgery in London, United Kingdom, similar to the dataset used in the MICCAI PitVis challenge. All patients provided informed consent, and the study was registered with the local governance committee. The surgeries were recorded using a high-definition endoscope (Karl Storz Endoscopy) with a resolution of 720p and stored as MP4 files. All videos were annotated for the surgical phases, steps, instruments present and operation notes guided by a standardised annotation framework, which was derived from a preceding international consensus study on pituitary surgery workflow. Annotation was performed collaboratively by 2 neurosurgical residents with operative pituitary experience and checked by an attending neurosurgeon. We extracted image frames from each video at 1 fps and removed any frames that were blurred or occluded. Ultimately, we obtained a total of 109,173 frames, with the videos of minimum and maximum length yielding 2,443 and 7,179 frames, respectively. We acquired frame-wise question-answer pairs for all the categories of the annotation. Overall, there are 884,242 question-answer pairs from 109,173 frames, which is around 8 pairs for each frame. There are 59 classes overall, including 4 phases, 15 steps, 18 instruments, 3 variations of instruments present in a frame, 5 positions of the instruments, and 14 operation notes in the annotation classes. The length of the questions ranges from a minimum of 7 words to a maximum of 12 words.The details description of the original videos can be found at the MICCAI PitVis challenge and the videos can be directly download from UCL HDR portal.

ST-VQA aims to highlight the importance of exploiting high-level semantic information present in images as textual cues in the VQA process.

DocCVQA is a Document Visual Question Answering dataset, where the questions are posed over a whole collection of 14,362 scanned documents. Therefore, the task can be seen as a retrieval-style evidence seeking task where given a question, the aim is to identify and retrieve all the documents in a large document collection that are relevant to answering this question as well as provide the answer.

This are the image features extracted from Inception v3 network to be included for solving the VQA problem.

Dataset Card for VQA-RAD

  Dataset Description

VQA-RAD is a dataset of question-answer pairs on radiology images. The dataset is intended to be used for training and testing Medical Visual Question Answering (VQA) systems. The dataset includes both open-ended questions and binary "yes/no" questions. The dataset is built from MedPix, which is a free open-access online database of medical images. The question-answer pairs were manually generated by a team of clinicians.… See the full description on the dataset page: https://huggingface.co/datasets/flaviagiammarino/vqa-rad.

The dataset is aimed to perform Visual Question Answering on multipage industry scanned documents. The questions and answers are reused from Single Page DocVQA (SP-DocVQA) dataset. The images also corresponds to the same in original dataset with previous and posterior pages with a limit of up to 20 pages per document.

The dataset is used for image captioning and visual question answering.

The Visual Question Answering (VQA) technology market is experiencing robust growth, driven by increasing demand for advanced image analysis and AI-powered solutions across diverse industries. The market, estimated at $2 billion in 2025, is projected to expand at a Compound Annual Growth Rate (CAGR) of 25% from 2025 to 2033. This significant growth is fueled by several key factors. The proliferation of big data and the advancements in deep learning algorithms are enabling more accurate and efficient VQA systems. Furthermore, the rising adoption of VQA in sectors such as healthcare (for medical image analysis), retail (for enhanced customer experience), and autonomous vehicles (for scene understanding) is significantly boosting market expansion. The increasing availability of powerful cloud computing resources further facilitates the development and deployment of complex VQA models. While challenges such as data bias and the need for robust annotation techniques remain, the overall market outlook for VQA technology is extremely positive. Segmentation analysis reveals strong growth across various application areas. The software industry currently leads in VQA adoption, followed by the computer and electronics industries. Within the technology itself, image classification and image identification are the dominant segments, indicating a strong focus on practical applications. Geographically, North America and Europe currently hold the largest market shares, but the Asia-Pacific region is expected to witness substantial growth in the coming years, driven by increasing investments in AI and technological advancements in countries like China and India. Key players like Toshiba Corporation, Amazon Science, and Cognex are actively contributing to market growth through continuous innovation and strategic partnerships. The competitive landscape is dynamic, with both established tech giants and emerging startups vying for market share. The long-term outlook suggests that VQA technology will continue to be a critical component of various emerging technologies and will play a pivotal role in shaping the future of artificial intelligence.

The Visual Question Answering (VQA) Technology market is poised for significant growth due to its increasing adoption across various industries. With a market size of XXX million in 2025, the market is projected to grow at a CAGR of XX% during the forecast period 2025-2033. This growth is attributed to the rising demand for automated systems for complex tasks, advancements in artificial intelligence (AI), and the increasing availability of image and video data. VQA technology has applications in the software, computer, and electronic industries, providing solutions for image identification, image classification, and other tasks. Various factors are driving the growth of the VQA technology market. The increasing adoption of AI-powered solutions, the growing need for efficient and accurate image processing, and the rising demand for automated customer service are major factors driving the market. Moreover, the advancements in natural language processing (NLP) and computer vision technologies further enhance the capabilities of VQA systems. However, the availability of limited training data for VQA models and the need for specialized hardware for processing large datasets pose certain challenges to the market's growth. Despite these challenges, the increasing R&D investments by market players and the collaborative efforts to develop standardized datasets are expected to create new growth opportunities in the coming years.

TextVQA requires models to read and reason about text in an image to answer questions based on them. In order to perform well on this task, models need to first detect and read text in the images. Models then need to reason about this to answer the question. Current state-of-the-art models fail to answer questions in TextVQA because they do not have text reading and reasoning capabilities. See the examples in the image to compare ground truth answers and corresponding predictions by a state-of-the-art model. Challenge link: https://eval.ai/web/challenges/challenge-page/874/

Source code of our visual analysis system to explore scene-graph-based visual question answering. This approach is built on top of the state-of-the-art GraphVQA framework which was trained on the GQA dataset. Instructions on how to use our system can be found in the README.

MIMIC CXR [1] is a large publicly available dataset of chest radiographs in DICOM format with free-text radiology reports. In addition, labels for the presence of 12 different chest-related pathologies, as well as of any support devices, and overall normal/abnormal status were made available via the MIMIC Chest X-ray JPG (MIMIC-CXR-JPG) [2] labels, which were generated using the CheXpert and NegBio algorithms.

Based on these labels, we created a visual question answering dataset comprising 224 questions for 48 cases from the official test set, and 111 questions for 23 validation cases. A majority (68%) of the questions are close-ended (answerable with yes or no), and focus on the presence of one out of 15 chest pathologies, or any support device, or generically on any abnormality, whereas the remaining open-ended questions inquire about the location, size, severity or type of a pathology/device, if present in the specific case, indicated by the MIMIC-CXR-JPG labels.

For each question and case we also provide a reference answer, which was authored by a board-certified radiologist (with 17 years of post-residency experience) based on the chest X-ray and original radiology report

Source code of our extended visual analysis system to explore scene-graph-based visual question answering. This approach is built on top of the state-of-the-art GraphVQA framework which was trained on the GQA dataset. Additionally, it is an improved version of our system that can be found here Instructions on how to use our system can be found in the README.

VQA-RAD consists of 3,515 question–answer pairs on 315 radiology images.

open-source-metrics/visual-question-answering-checkpoint-downloads dataset hosted on Hugging Face and contributed by the HF Datasets community

In recent years, visual question answering (VQA) has attracted attention from the research community because of its highly potential applications (such as virtual assistance on intelligent cars, assistant devices for blind people, or information retrieval from document images using natural language as queries) and challenge. The VQA task requires methods that have the ability to fuse the information from questions and images to produce appropriate answers. Neural visual question answering models have achieved tremendous growth on large-scale datasets which are mostly for resource-rich languages such as English. However, available datasets narrow the VQA task as the answers selection task or answer classification task. We argue that this form of VQA is far from human ability and eliminates the challenge of the answering aspect in the VQA task by just selecting answers rather than generating them. In this paper, we introduce the OpenViVQA (Open-domain Vietnamese Visual Question Answering) dataset, the first large-scale dataset for VQA with open-ended answers in Vietnamese, consists of 11,000+ images associated with 37,000+ question–answer pairs (QAs).