All

What are you looking for?

All
Projects
Results
Organizations

Quick search

  • Projects supported by TA ČR
  • Excellent projects
  • Projects with the highest public support
  • Current projects

Smart search

  • That is how I find a specific +word
  • That is how I leave the -word out of the results
  • “That is how I can find the whole phrase”

Vqa and Visual Reasoning: An Overview of Approaches, Datasets, and Future Direction

The result's identifiers

  • Result code in IS VaVaI

    <a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3ASJSEXNPY" target="_blank" >RIV/00216208:11320/23:SJSEXNPY - isvavai.cz</a>

  • Result on the web

    <a href="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4455698" target="_blank" >https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4455698</a>

  • DOI - Digital Object Identifier

    <a href="http://dx.doi.org/10.2139/ssrn.4455698" target="_blank" >10.2139/ssrn.4455698</a>

Alternative languages

  • Result language

    angličtina

  • Original language name

    Vqa and Visual Reasoning: An Overview of Approaches, Datasets, and Future Direction

  • Original language description

    "Visual Question Answering (VQA) is a challenging and fascinating area of research in computer vision, deep learning, and natural language processing that has recently piqued the interest of AI researchers from a variety of fields. The inputs for this task are an image and a written question about the image. The answer can be generated intelligently or selected from a set of options related to the image. We have seen a rapid development of VQA and visual reasoning in tasks based on deep learning and massive amounts of annotated data over the last five years. In this article, we will present a comprehensive literature review of the current state of the art in VQA and visual reasoning from four perspectives: problem definition and challenges, approaches, existing datasets, and evaluation matrices. We discussed the datasets' limitations and thoroughly examined the current models. Finally, we investigate potential future research directions in this area in order to generate new ideas and creative approaches to solving current problems and developing new applications."

  • Czech name

  • Czech description

Classification

  • Type

    O - Miscellaneous

  • CEP classification

  • OECD FORD branch

    10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Result continuities

  • Project

  • Continuities

Others

  • Publication year

    2023

  • Confidentiality

    S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů