# Visual Grounding with Attention-Driven Constraint Balancing

arXiv: https://arxiv.org/abs/2407.03243 · HTML: https://mlsanity.com/paper/2407.03243/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 48 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Builds on (most cited first, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [MAttNet: Modular Attention Network for Referring Expression Comprehension](https://mlsanity.com/paper/1801.08186/) (2018)
- [LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models](https://mlsanity.com/paper/2403.15388/) (2024)
- [Visual7W: Grounded Question Answering in Images](https://mlsanity.com/paper/1511.03416/) (2015)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [TransVG: End-to-End Visual Grounding with Transformers](https://mlsanity.com/paper/2104.08541/) (2021)
- [Image Captioning with Semantic Attention](https://mlsanity.com/paper/1603.03925/) (2016)
- [Modeling Context Between Objects for Referring Expression Understanding](https://mlsanity.com/paper/1608.00525/) (2016)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [A Fast and Accurate One-Stage Approach to Visual Grounding](https://mlsanity.com/paper/1908.06354/) (2019)
- [Learning to Assemble Neural Module Tree Networks for Visual Grounding](https://mlsanity.com/paper/1812.03299/) (2018)
- [Improving One-stage Visual Grounding by Recursive Sub-query Construction](https://mlsanity.com/paper/2008.01059/) (2020)
- [A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension](https://mlsanity.com/paper/1909.07072/) (2019)
- [Dynamic Graph Attention for Referring Expression Comprehension](https://mlsanity.com/paper/1909.08164/) (2019)
- [Modeling Relationships in Referential Expressions with Compositional Modular Networks](https://mlsanity.com/paper/1611.09978/) (2016)
- [Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks](https://mlsanity.com/paper/1812.04794/) (2018)
- [Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs](https://mlsanity.com/paper/2003.00387/) (2020)
- [Grounding Referring Expressions in Images by Variational Context](https://mlsanity.com/paper/1712.01892/) (2017)
- [On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering](https://mlsanity.com/paper/2002.10215/) (2020)
- [Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning](https://mlsanity.com/paper/2205.00272/) (2022)

## Built on by (most cited first, 7 of 7)

- [Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning](https://mlsanity.com/paper/2410.00255/) (2024)
- [textscGUI-Spotlight: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding](https://mlsanity.com/paper/2510.04039/) (2025)
- [GuirlVG: Incentivize GUI Visual Grounding via Empirical Exploration on Reinforcement Learning](https://mlsanity.com/paper/2508.04389/) (2025)
- [VGent: Visual Grounding via Modular Design for Disentangling Reasoning and Prediction](https://mlsanity.com/paper/2512.11099/) (2025)
- [RGBT-GroundBench: Visual Grounding Beyond RGB in Complex Real-World Scenarios](https://mlsanity.com/paper/2512.24561/) (2025)
- [ExpVG: Investigating the Design Space of Visual Grounding in Multimodal Large Language Model](https://mlsanity.com/paper/2508.08066/) (2025)
- [Mixture-of-Thought-Tokens: Unifying Perception and Reasoning for Free-form Multimodal Grounding](https://mlsanity.com/paper/2607.24407/) (2026)

## Abstract (arXiv)

Unlike Object Detection, Visual Grounding task necessitates the detection of an object described by complex free-form language. To simultaneously model such complex semantic and visual representations, recent state-of-the-art studies adopt transformer-based models to fuse features from both modalities, further introducing various modules that modulate visual features to align with the language expressions and eliminate the irrelevant redundant information. However, their loss function, still adopting common Object Detection losses, solely governs the bounding box regression output, failing to fully optimize for the above objectives. To tackle this problem, in this paper, we first analyze the attention mechanisms of transformer-based models. Building upon this, we further propose a novel framework named Attention-Driven Constraint Balancing (AttBalance) to optimize the behavior of visual features within language-relevant regions. Extensive experimental results show that our method brings impressive improvements. Specifically, we achieve constant improvements over five different models evaluated on four different benchmarks. Moreover, we attain a new state-of-the-art performance by integrating our method into QRNet.