$\mathbb{VD}$-$\mathbb{GR}$: Boosting $\mathbb{V}$isual $\mathbb{D}$ialog with Cascaded Spatial-Temporal Multi-Modal $\mathbb{GR}$aphs

arXiv (Cornell University)(2023)

引用 0|浏览5
暂无评分
摘要
We propose $\mathbb{VD}$-$\mathbb{GR}$ - a novel visual dialog model that combines pre-trained language models (LMs) with graph neural networks (GNNs). Prior works mainly focused on one class of models at the expense of the other, thus missing out on the opportunity of combining their respective benefits. At the core of $\mathbb{VD}$-$\mathbb{GR}$ is a novel integration mechanism that alternates between spatial-temporal multi-modal GNNs and BERT layers, and that covers three distinct contributions: First, we use multi-modal GNNs to process the features of each modality (image, question, and dialog history) and exploit their local structures before performing BERT global attention. Second, we propose hub-nodes that link to all other nodes within one modality graph, allowing the model to propagate information from one GNN (modality) to the other in a cascaded manner. Third, we augment the BERT hidden states with fine-grained multi-modal GNN features before passing them to the next $\mathbb{VD}$-$\mathbb{GR}$ layer. Evaluations on VisDial v1.0, VisDial v0.9, VisDialConv, and VisPro show that $\mathbb{VD}$-$\mathbb{GR}$ achieves new state-of-the-art results across all four datasets.
更多
查看译文
关键词
spatial-temporal,multi-modal
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要