• Home
  • Search
  • A New Design of VQA System based on Weighted Contextual Features
  • https://doi.org/10.1109/ickg55886.2022.00045Copy DOI Icon

A New Design of VQA System based on Weighted Contextual Features

  • Nov 1, 2022
  • Yu Wang +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Visual question answering (VQA) is a challenging task that requires a deep understanding of language and images. Currently, most VQA algorithms focus on finding the correlations between basic question embeddings and image features by using an element-wise product or bilinear pooling between these two vectors. Some algorithms also use attention models to extract features. In this paper, deeper analyses of these attention features are enabled by capturing their importance by weighting their contextual information. A novel interpretable VQA system leveraging weighted attention contextual features (WACF) is proposed for VQA tasks. This is a multimodal system which can assign adaptive weights to the features of questions and images themselves and to their contextual features based on their importance. Our new model yields state-of-the-art results on the MS COCO VQA datasets for open-ended question tasks.

Similar Papers
  • Conference Article
  • Citations1

An Interpretable Multimodal Visual Question Answering System using Attention-based Weighted Contextual Features

  • May 05, 2020
  • Yu Wang +2
  • Conference Article
  • Citations2

VQAR: Review on Information Retrieval Techniques based on Computer Vision and Natural Language Processing

  • Mar 01, 2019
  • Shivangi Modi +1
  • Research Article
  • Citations1

Counting in Visual Question Answering: Methods, Datasets, and Future Work

  • Oct 20, 2023
  • International Journal of Image and Graphics
  • Tesfayee Meshu Welde +1
  • Book Chapter
  • Citations2

A VQA System for Medical Image Classification Using Transfer Learning

  • Jan 01, 2021
  • C Dhanush +2
  • PDF
  • Research Article
  • Citations86

MedFuseNet:\xa0An\xa0attention-based multimodal deep learning model for visual question answering in the medical domain

  • Oct 06, 2021
  • Scientific Reports
  • Dhruv Sharma +2
  • Book Chapter
  • Citations2

A-VQA: Attention Based Visual Question Answering Technique for Handling Improper Count of Occluded Object

  • Jan 01, 2021
  • Shivangi Modi +1
  • Book Chapter
  • Citations3

Optimal Image Feature Ranking and Fusion for Visual Question Answering

  • Sep 09, 2020
  • Sruthy Manmadhan +1
  • Research Article
  • Citations49

Medical knowledge-based network for Patient-oriented Visual Question Answering

  • Dec 21, 2022
  • Information Processing & Management
  • Jian Huang +7
  • Conference Article

Bridging the Gap: Leveraging Textual and Visual Contexts for PreciseMedical Visual Question Answering

  • Aug 08, 2024
  • Pratiksh Kumar +3
  • Abstract

Understanding the diagnosis and management of external eye disease: Gurwood AS: Br J Optom Disp 1995;3:155–163

  • May 01, 1996
  • International Contact Lens Clinic
  • Research Article
  • Citations45

A survey of methods, datasets and evaluation metrics for visual question answering

  • Oct 15, 2021
  • Image and Vision Computing
  • Himanshu Sharma +1
  • Book Chapter
  • Citations49

Visual Question Answering Using Deep Learning: A Survey and Performance Analysis

  • Jan 01, 2021
  • Yash Srivastava +3
  • Research Article
  • Citations2

VADS: Visuo-Adaptive DualStrike attack on visual question answer

  • Aug 31, 2024
  • Computer Vision and Image Understanding
  • Boyuan Zhang +4
  • PDF
  • Research Article
  • Citations412

Multiscale Feature Extraction and Fusion of Image and Text in VQA

  • Apr 11, 2023
  • International Journal of Computational Intelligence Systems
  • Siyu Lu +5
  • Book Chapter
  • Citations276

Revisiting Visual Question Answering Baselines

  • Jan 01, 2016
  • Allan Jabri +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.