mlsanityData to 7 Oct 2026

DDVT: Dynamic Dual-level Vision Transformer Fusion Network for Answer Grounding in Visual Question Answering

arXiv 2607.23921 ↗First posted 27 Jul 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Answer grounding in visual question answering aims to locate the region from a given natural language question associated with the visual content of an image, which has garnered significant attention due to its practical applications. In this paper, we introduce the Dynamic Dual-level Vision Transformer Fusion Network (DDVT) for answer grounding in visual question answering. Specifically, we propose a question-guided dynamic regional-level module (QGDR) that combines complementary image context through ROI Align and text content, enabling precise localization of text-related visual content. Moreover, we present a cross-modal multi-scale aggregation module (CMA) that enhances feature fusion between pixel-level and region-level features, facilitating the effective localization of visual content associated with grounded answers. Furthermore, we fuse the located visual content with text features to locate the region and provide answers to questions posed about the image. Experimental results demonstrate that our DDVT outperforms state-of-the-art methods on several widely-used benchmarks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 41 references that are in the map. First posted on arXiv 27 Jul 2026.

Builds on

27 of 41 references.

References · 27

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  5. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,548
  6. 2017Deformable Convolutional Networkscited by 1,481
  7. 2017Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answeringcited by 1,310
  8. 2022Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Taskscited by 420
  9. 2021Dynamic Neural Networks: A Surveycited by 405
  10. 2021LAVT: Language-Aware Vision Transformer for Referring Image Segmentationcited by 347
  11. 2019Deep Modular Co-Attention Networks for Visual Question Answeringcited by 338
  12. 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 328
15 more
  1. 2019CondConv: Conditionally Parameterized Convolutions for Efficient Inferencecited by 273
  2. 2017Adaptive Neural Networks for Efficient Inferencecited by 161
  3. 2019Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networkscited by 118
  4. 2018Dynamic Fusion with Intra- and Inter- Modality Attention Flow for Visual Question Answeringcited by 113
  5. 2020Boundary-preserving Mask R-CNNcited by 74
  6. 2018Pythia v0.1: the Winning Entry to the VQA Challenge 2018cited by 62
  7. 2019Language-Conditioned Graph Networks for Relational Reasoningcited by 55
  8. 2017VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentationcited by 50
  9. 2022Grounding Answers for Visual Questions Asked by Visually Impaired Peoplecited by 47
  10. 2021Dynamic Resolution Networkcited by 31
  11. 2021Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsulescited by 22
  12. 2016Automatic Generation of Grounded Visual Questionscited by 19
  13. 2023DynaMask: Dynamic Mask Selection for Instance Segmentationcited by 10
  14. 2022Tell Me the Evidence? Dual Visual-Linguistic Interaction for Answer Groundingcited by 1
  15. 2023The style transformer with common knowledge optimization for image-text retrievalcited by 1

Built on by

Not cited yet.