• Home
  • Search
  • Question-Guided Hybrid Convolution for Visual Question Answering
  • Cite Icon96
  • https://doi.org/10.1007/978-3-030-01246-5_29Copy DOI Icon

Question-Guided Hybrid Convolution for Visual Question Answering

  • Jan 1, 2018
  • Peng Gao +6 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In this paper, we propose a novel Question-Guided Hybrid Convolution (QGHC) network for Visual Question Answering (VQA). Most state-of-the-art VQA methods fuse the high-level textual and visual features from the neural network and abandon the visual spatial information when learning multi-modal features.To address these problems, question-guided kernels generated from the input question are designed to convolute with visual features for capturing the textual and visual relationship in the early stage. The question-guided convolution can tightly couple the textual and visual information but also introduce more parameters when learning kernels. We apply the group convolution, which consists of question-independent kernels and question-dependent kernels, to reduce the parameter size and alleviate over-fitting. The hybrid convolution can generate discriminative multi-modal features with fewer parameters. The proposed approach is also complementary to existing bilinear pooling fusion and attention based VQA methods. By integrating with them, our method could further boost the performance. Extensive experiments on public VQA datasets validate the effectiveness of QGHC.

Similar Papers
  • PDF
  • Research Article
  • Citations1

Multi-modality guided cross-attention for visual question answering

  • Jul 25, 2025
  • Multimedia Tools and Applications
  • Muhammad Zeeshan Khan +4
  • Book Chapter

Multi-view Visual Question Answering Dataset for Real Environment Applications

  • Jan 01, 2020
  • Yue Qiu +3
  • Conference Article
  • Citations3

Multi-Channel Co-Attention Network for Visual Question Answering

  • Jul 01, 2020
  • Weidong Tian +3
  • Research Article
  • Citations67

Dual self-attention with co-attention networks for visual question answering

  • Apr 09, 2021
  • Pattern Recognition
  • Yun Liu +6
  • Conference Article

VIG: Visual Information-Guided Knowledge-Based Visual Question Answering

  • May 08, 2024
  • Heng Liu +5
  • Conference Article
  • Citations22

Lightweight Visual Question Answering using Scene Graphs

  • Oct 26, 2021
  • Sai Vidyaranya Nuthalapati +6
  • Conference Article
  • Citations59

Visual Question Answering as Reading Comprehension

  • Jun 01, 2019
  • Hui Li +3
  • Research Article
  • Citations4

PGCL: Prompt guidance and self-supervised contrastive learning-based method for Visual Question Answering

  • Apr 16, 2024
  • Expert Systems with Applications
  • Ling Gao +5
  • 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
  • Conference Article
  • Citations1

An Visual Question Answering System using Cross-Attention Network

  • Aug 17, 2023
  • R Dhana Lakshmi +1
  • Research Article
  • Citations503

Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering

  • Sep 11, 2018
  • International Journal of Computer Vision
  • Yash Goyal +5
  • Research Article
  • Citations13

GFSNet: Gaussian Fourier with sparse attention network for visual question answering

  • Mar 15, 2025
  • Artificial Intelligence Review
  • Xiang Shen +4
  • Conference Article
  • Citations2

A Survey on Visual Question Answering

  • Oct 01, 2021
  • Mrinal Banchhor +1
  • Research Article
  • Citations20

Selective residual learning for Visual Question Answering

  • Apr 10, 2020
  • Neurocomputing
  • Jongkwang Hong +2
  • Research Article
  • Citations24

Enhancing robust VQA via contrastive and self-supervised learning

  • Nov 02, 2024
  • Pattern Recognition
  • Runlin Cao +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.