Vol. 2 No. 2 (2022): Journal of AI-Assisted Scientific Discovery
Articles

Visual Question Answering - Challenges and Solutions: Studying challenges and solutions in visual question answering (VQA) systems for understanding and answering questions about images

PDF
  • Dr. Carlos Hernández
Dr. Carlos Hernández
Associate Professor of Information Technology, National Autonomous University of Mexico (UNAM)
Cover

Published 19-09-2022

Keywords

  • VQA,
  • Attention Mechanisms,
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

How to Cite

[1]
Dr. Carlos Hernández, “Visual Question Answering - Challenges and Solutions: Studying challenges and solutions in visual question answering (VQA) systems for understanding and answering questions about images”, Journal of AI-Assisted Scientific Discovery, vol. 2, no. 2, pp. 88–97, Sep. 2022, Accessed: Sep. 19, 2024. [Online]. Available: https://scienceacadpress.com/index.php/jaasd/article/view/117

Abstract

Visual Question Answering (VQA) is a challenging task that requires machines to comprehend images and answer natural language questions about them. This paper presents an overview of the challenges faced by VQA systems and explores the solutions proposed to address these challenges. We discuss the complexities of multimodal understanding, the need for common-sense reasoning, and the importance of interpretability in VQA. We also highlight the role of large-scale datasets and benchmarking in advancing the field. Additionally, we examine recent trends such as attention mechanisms, graph-based reasoning, and pre-trained models in improving VQA performance. Through this paper, we aim to provide insights into the current state of VQA research and directions for future work.

PDF

Downloads

Download data is not yet available.

References

  1. K. Joel Prabhod, “ASSESSING THE ROLE OF MACHINE LEARNING AND COMPUTER VISION IN IMAGE PROCESSING,” International Journal of Innovative Research in Technology, vol. 8, no. 3, pp. 195–199, Aug. 2021, [Online]. Available: https://ijirt.org/Article?manuscript=152346
  2. Sadhu, Amith Kumar Reddy, and Ashok Kumar Reddy Sadhu. "Fortifying the Frontier: A Critical Examination of Best Practices, Emerging Trends, and Access Management Paradigms in Securing the Expanding Internet of Things (IoT) Network." Journal of Science & Technology 1.1 (2020): 171-195.
  3. Tatineni, Sumanth, and Anjali Rodwal. “Leveraging AI for Seamless Integration of DevOps and MLOps: Techniques for Automated Testing, Continuous Delivery, and Model Governance”. Journal of Machine Learning in Pharmaceutical Research, vol. 2, no. 2, Sept. 2022, pp. 9-41, https://pharmapub.org/index.php/jmlpr/article/view/17.
  4. Pulimamidi, Rahul. "Leveraging IoT Devices for Improved Healthcare Accessibility in Remote Areas: An Exploration of Emerging Trends." Internet of Things and Edge Computing Journal 2.1 (2022): 20-30.
  5. Gudala, Leeladhar, et al. "Leveraging Biometric Authentication and Blockchain Technology for Enhanced Security in Identity and Access Management Systems." Journal of Artificial Intelligence Research 2.2 (2022): 21-50.
  6. Sadhu, Ashok Kumar Reddy, and Amith Kumar Reddy. "Exploiting the Power of Machine Learning for Proactive Anomaly Detection and Threat Mitigation in the Burgeoning Landscape of Internet of Things (IoT) Networks." Distributed Learning and Broad Applications in Scientific Research 4 (2018): 30-58.
  7. Tatineni, Sumanth, and Venkat Raviteja Boppana. "AI-Powered DevOps and MLOps Frameworks: Enhancing Collaboration, Automation, and Scalability in Machine Learning Pipelines." Journal of Artificial Intelligence Research and Applications 1.2 (2021): 58-88.