# Learning to Ground Visual Objects for Visual Dialog

arXiv: https://arxiv.org/abs/2109.06013 · HTML: https://mlsanity.com/paper/2109.06013/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 56 references that are in the map.
- First posted on arXiv 13 Sep 2021.

## Builds on (most cited first, 30 of 45)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [Visual Dialog](https://mlsanity.com/paper/1611.08669/) (2016)
- [Meshed-Memory Transformer for Image Captioning](https://mlsanity.com/paper/1912.08226/) (2019)
- [Hierarchical Question-Image Co-Attention for Visual Question Answering](https://mlsanity.com/paper/1606.00061/) (2016)
- [Exploring Models and Data for Image Question Answering](https://mlsanity.com/paper/1505.02074/) (2015)
- [Relation-Aware Graph Attention Network for Visual Question Answering](https://mlsanity.com/paper/1903.12314/) (2019)
- [Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering](https://mlsanity.com/paper/1505.05612/) (2015)
- [Image Chat: Engaging Grounded Conversations](https://mlsanity.com/paper/1811.00945/) (2018)
- [Two Causal Principles for Improving Visual Dialog](https://mlsanity.com/paper/1911.10496/) (2019)
- [Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline](https://mlsanity.com/paper/1912.02379/) (2019)
- [VD-BERT: A Unified Vision and Dialog Transformer with BERT](https://mlsanity.com/paper/2004.13278/) (2020)
- [Visual Coreference Resolution in Visual Dialog using Neural Module Networks](https://mlsanity.com/paper/1809.01816/) (2018)
- [Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog](https://mlsanity.com/paper/1902.00579/) (2019)
- [Factor Graph Attention](https://mlsanity.com/paper/1904.05880/) (2019)
- [Recursive Visual Attention in Visual Dialog](https://mlsanity.com/paper/1812.02664/) (2018)

## Built on by (most cited first, 10 of 10)

- [Federated Class-Incremental Learning](https://mlsanity.com/paper/2203.11473/) (2022)
- [PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts](https://mlsanity.com/paper/2305.14839/) (2023)
- [GoG: Relation-aware Graph-over-Graph Network for Visual Dialog](https://mlsanity.com/paper/2109.08475/) (2021)
- [Target-Aware Spatio-Temporal Reasoning via Answering Questions in Dynamics Audio-Visual Scenarios](https://mlsanity.com/paper/2305.12397/) (2023)
- [Improving Cross-Modal Understanding in Visual Dialog via Contrastive Learning](https://mlsanity.com/paper/2204.07302/) (2022)
- [Unified Multimodal Model with Unlikelihood Training for Visual Dialog](https://mlsanity.com/paper/2211.13235/) (2022)
- [CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual Question Answering](https://mlsanity.com/paper/2405.07451/) (2024)
- [VDialogUE: A Unified Evaluation Benchmark for Visually-grounded Dialogue](https://mlsanity.com/paper/2309.07387/) (2023)
- [Enhancing Visual Dialog State Tracking through Iterative Object-Entity Alignment in Multi-Round Conversations](https://mlsanity.com/paper/2408.06725/) (2024)
- [V2Dial: Unification of Video and Visual Dialog via Multimodal Experts](https://mlsanity.com/paper/2503.02063/) (2025)

## Abstract (arXiv)

Visual dialog is challenging since it needs to answer a series of coherent questions based on understanding the visual environment. How to ground related visual objects is one of the key problems. Previous studies utilize the question and history to attend to the image and achieve satisfactory performance, however these methods are not sufficient to locate related visual objects without any guidance. The inappropriate grounding of visual objects prohibits the performance of visual dialog models. In this paper, we propose a novel approach to Learn to Ground visual objects for visual dialog, which employs a novel visual objects grounding mechanism where both prior and posterior distributions over visual objects are used to facilitate visual objects grounding. Specifically, a posterior distribution over visual objects is inferred from both context (history and questions) and answers, and it ensures the appropriate grounding of visual objects during the training process. Meanwhile, a prior distribution, which is inferred from context only, is used to approximate the posterior distribution so that appropriate visual objects can be grounded even without answers during the inference process. Experimental results on the VisDial v0.9 and v1.0 datasets demonstrate that our approach improves the previous strong models in both generative and discriminative settings by a significant margin.