# Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structures

arXiv: https://arxiv.org/abs/2505.11726 · HTML: https://mlsanity.com/paper/2505.11726/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 57 references that are in the map.
- First posted on arXiv 16 May 2025.

## Builds on (most cited first, 26 of 26)

- [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)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [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)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [Visual Dialog](https://mlsanity.com/paper/1611.08669/) (2016)
- [Grounding of Textual Phrases in Images by Reconstruction](https://mlsanity.com/paper/1511.03745/) (2015)
- [Contrastive Learning for Weakly Supervised Phrase Grounding](https://mlsanity.com/paper/2006.09920/) (2020)
- [SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations](https://mlsanity.com/paper/2104.08667/) (2021)
- [Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment](https://mlsanity.com/paper/1903.11649/) (2019)
- [InterPreT: Interactive Predicate Learning from Language Feedback for Generalizable Task Planning](https://mlsanity.com/paper/2405.19758/) (2024)
- [What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues](https://mlsanity.com/paper/1909.00421/) (2019)
- [Multi-task Learning Based Neural Bridging Reference Resolution](https://mlsanity.com/paper/2003.03666/) (2020)
- [VD-PCR: Improving Visual Dialog with Pronoun Coreference Resolution](https://mlsanity.com/paper/2205.14693/) (2022)
- [Who are you referring to? Coreference resolution in image narrations](https://mlsanity.com/paper/2211.14563/) (2022)
- [J-CRe3: A Japanese Conversation Dataset for Real-world Reference Resolution](https://mlsanity.com/paper/2403.19259/) (2024)
- [Semi-supervised multimodal coreference resolution in image narrations](https://mlsanity.com/paper/2310.13619/) (2023)
- [Multi-task Learning for Japanese Predicate Argument Structure Analysis](https://mlsanity.com/paper/1904.02244/) (2019)

## Abstract (arXiv)

Multimodal reference resolution, including phrase grounding, aims to understand the semantic relations between mentions and real-world objects. Phrase grounding between images and their captions is a well-established task. In contrast, for real-world applications, it is essential to integrate textual and multimodal reference resolution to unravel the reference relations within dialogue, especially in handling ambiguities caused by pronouns and ellipses. This paper presents a framework that unifies textual and multimodal reference resolution by mapping mention embeddings to object embeddings and selecting mentions or objects based on their similarity. Our experiments show that learning textual reference resolution, such as coreference resolution and predicate-argument structure analysis, positively affects performance in multimodal reference resolution. In particular, our model with coreference resolution performs better in pronoun phrase grounding than representative models for this task, MDETR and GLIP. Our qualitative analysis demonstrates that incorporating textual reference relations strengthens the confidence scores between mentions, including pronouns and predicates, and objects, which can reduce the ambiguities that arise in visually grounded dialogues.