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

arXiv: https://arxiv.org/abs/2607.23921 · HTML: https://mlsanity.com/paper/2607.23921/

## 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 (most cited first, 27 of 27)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks](https://mlsanity.com/paper/2206.08916/) (2022)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [LAVT: Language-Aware Vision Transformer for Referring Image Segmentation](https://mlsanity.com/paper/2112.02244/) (2021)
- [Deep Modular Co-Attention Networks for Visual Question Answering](https://mlsanity.com/paper/1906.10770/) (2019)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [CondConv: Conditionally Parameterized Convolutions for Efficient Inference](https://mlsanity.com/paper/1904.04971/) (2019)
- [Adaptive Neural Networks for Efficient Inference](https://mlsanity.com/paper/1702.07811/) (2017)
- [Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks](https://mlsanity.com/paper/1909.08174/) (2019)
- [Dynamic Fusion with Intra- and Inter- Modality Attention Flow for Visual Question Answering](https://mlsanity.com/paper/1812.05252/) (2018)
- [Boundary-preserving Mask R-CNN](https://mlsanity.com/paper/2007.08921/) (2020)
- [Pythia v0.1: the Winning Entry to the VQA Challenge 2018](https://mlsanity.com/paper/1807.09956/) (2018)
- [Language-Conditioned Graph Networks for Relational Reasoning](https://mlsanity.com/paper/1905.04405/) (2019)
- [VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation](https://mlsanity.com/paper/1708.04686/) (2017)
- [Grounding Answers for Visual Questions Asked by Visually Impaired People](https://mlsanity.com/paper/2202.01993/) (2022)
- [Dynamic Resolution Network](https://mlsanity.com/paper/2106.02898/) (2021)
- [Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules](https://mlsanity.com/paper/2105.04836/) (2021)
- [Automatic Generation of Grounded Visual Questions](https://mlsanity.com/paper/1612.06530/) (2016)
- [DynaMask: Dynamic Mask Selection for Instance Segmentation](https://mlsanity.com/paper/2303.07868/) (2023)
- [Tell Me the Evidence? Dual Visual-Linguistic Interaction for Answer Grounding](https://mlsanity.com/paper/2207.05703/) (2022)
- [The style transformer with common knowledge optimization for image-text retrieval](https://mlsanity.com/paper/2303.00448/) (2023)

## 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.