# Grounded Image Text Matching with Mismatched Relation Reasoning

arXiv: https://arxiv.org/abs/2308.01236 · HTML: https://mlsanity.com/paper/2308.01236/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 67 references that are in the map.
- First posted on arXiv 2 Aug 2023.

## Builds on (most cited first, 30 of 55)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [MAttNet: Modular Attention Network for Referring Expression Comprehension](https://mlsanity.com/paper/1801.08186/) (2018)
- [Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping](https://mlsanity.com/paper/2002.06305/) (2020)
- [Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering](https://mlsanity.com/paper/1712.00377/) (2017)
- [Large-Scale Adversarial Training for Vision-and-Language Representation Learning](https://mlsanity.com/paper/2006.06195/) (2020)
- [TransVG: End-to-End Visual Grounding with Transformers](https://mlsanity.com/paper/2104.08541/) (2021)
- [Counterfactual VQA: A Cause-Effect Look at Language Bias](https://mlsanity.com/paper/2006.04315/) (2020)
- [Modeling Context Between Objects for Referring Expression Understanding](https://mlsanity.com/paper/1608.00525/) (2016)
- [Vision-Language Pre-Training with Triple Contrastive Learning](https://mlsanity.com/paper/2202.10401/) (2022)
- [Exploring Length Generalization in Large Language Models](https://mlsanity.com/paper/2207.04901/) (2022)
- [Visual Semantic Reasoning for Image-Text Matching](https://mlsanity.com/paper/1909.02701/) (2019)
- [Referring Transformer: A One-step Approach to Multi-task Visual Grounding](https://mlsanity.com/paper/2106.03089/) (2021)
- [VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena](https://mlsanity.com/paper/2112.07566/) (2021)
- [Inferring and Executing Programs for Visual Reasoning](https://mlsanity.com/paper/1705.03633/) (2017)
- [Learning to Reason: End-to-End Module Networks for Visual Question Answering](https://mlsanity.com/paper/1704.05526/) (2017)
- [Invariance, Causality and Robustness](https://mlsanity.com/paper/1812.08233/) (2018)
- [Similarity Reasoning and Filtration for Image-Text Matching](https://mlsanity.com/paper/2101.01368/) (2021)
- [Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks](https://mlsanity.com/paper/2106.04537/) (2021)
- [Dynamic Graph Attention for Referring Expression Comprehension](https://mlsanity.com/paper/1909.08164/) (2019)
- [Probing Image-Language Transformers for Verb Understanding](https://mlsanity.com/paper/2106.09141/) (2021)
- [Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone](https://mlsanity.com/paper/2206.07643/) (2022)
- [Modeling Relationships in Referential Expressions with Compositional Modular Networks](https://mlsanity.com/paper/1611.09978/) (2016)
- [Explainable and Explicit Visual Reasoning over Scene Graphs](https://mlsanity.com/paper/1812.01855/) (2018)

## Built on by (most cited first, 8 of 8)

- [FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension](https://mlsanity.com/paper/2409.14750/) (2024)
- [Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context](https://mlsanity.com/paper/2510.20229/) (2025)
- [New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration](https://mlsanity.com/paper/2502.20104/) (2025)
- [Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats](https://mlsanity.com/paper/2511.17254/) (2025)
- [Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval](https://mlsanity.com/paper/2509.09118/) (2025)
- [Language-Driven Object-Oriented Two-Stage Method for Scene Graph Anticipation](https://mlsanity.com/paper/2509.05661/) (2025)
- [EventRR: Event Referential Reasoning for Referring Video Object Segmentation](https://mlsanity.com/paper/2508.07171/) (2025)
- [DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset](https://mlsanity.com/paper/2601.10305/) (2026)

## Abstract (arXiv)

This paper introduces Grounded Image Text Matching with Mismatched Relation (GITM-MR), a novel visual-linguistic joint task that evaluates the relation understanding capabilities of transformer-based pre-trained models. GITM-MR requires a model to first determine if an expression describes an image, then localize referred objects or ground the mismatched parts of the text. We provide a benchmark for evaluating pre-trained models on this task, with a focus on the challenging settings of limited data and out-of-distribution sentence lengths. Our evaluation demonstrates that pre-trained models lack data efficiency and length generalization ability. To address this, we propose the Relation-sensitive Correspondence Reasoning Network (RCRN), which incorporates relation-aware reasoning via bi-directional message propagation guided by language structure. RCRN can be interpreted as a modular program and delivers strong performance in both length generalization and data efficiency.